Semantic segmentation has attracted increasing attention due to its important role in self-driving, and it is often realized by supervised learning with large number of well labeled maps. However, the labeled images are hard to be obtained in most circumstances, and the common way for unsupervised semantic segmentation is usually implemented by transferring the knowledge from source supervised domain to target unsupervised domain. Most researches focus on encouraging target predictions to be closer to the source ones through a weight-sharing network, and achieve certain performance. However, these methods often suffer from the domain shift problem that the networks are often trained towards the source domain and lead to performance degradation. In this paper, we propose a target-targeted domain adaptation approach by focusing the training on target domain. Our model consists of two components: the Image-to-image Translation (IIT) module to translate the source image to target domain and the Target-targeted Segmentation Adaptation (TSA) module to focus the semantic segmentation on target domain. The IIT module deals with image space alignment while the TSA module bridges the domain gap at the segmentation map level. In addition, we design a closed-loop learning to promote each other by employing feedback from TSA to IIT. Extensive experiments on GTA5 and SYNTHIA to Cityscapes demonstrate the effectiveness of our method in domain adaptation of unsupervised semantic segmentation.

With the expansion of data, increasing imbalanced data has emerged. When the imbalance ratio (IR) of data is high, most existing imbalanced learning methods decline seriously in classification performance. In this paper, we systematically investigate the highly imbalanced data classification problem, and propose an uncorrelated cost-sensitive multiset learning (UCML) approach for it. Specifically, UCML first constructs multiple balanced subsets through random partition, and then employs the multiset feature learning (MFL) to learn discriminant features from the constructed multiset. To enhance the usability of each subset and deal with the non-linearity issue existed in each subset, we further propose a deep metric based UCML (DM-UCML) approach. DM-UCML introduces the generative adversarial network technique into the multiset constructing process, such that each subset can own similar distribution with the original dataset. To cope with the non-linearity issue, DM-UCML integrates deep metric learning with MFL, such that more favorable performance can be achieved. In addition, DM-UCML designs a new discriminant term to enhance the discriminability of learned metrics. Experiments on eight traditional highly class-imbalanced datasets and two large-scale datasets indicate that: the proposed approaches outperform state-of-the-art highly imbalanced learning methods and are more robust to high IR.

Recent representative scene parsing methods based on Convolutional Neural Networks (CNN) have greatly improved spatial resolution of pixel-wise labelling by exploiting multi-scale features and refined boundaries. However, the vast majority of previous works only utilize the color or textural information of images, without considering the depth information, which is beneficial for semantic reasoning. In this paper, we take advantages of the mutual benefit and strong correlation between depth information and semantic information in scene parsing by introducing the Built-in Depth-Semantic Coupled Encoding (BDSCE) module, which adaptively fuses RGB and depth features, and selectively highlights the depth-discriminative features. The proposed BDSCE module is compatible with existing CNN based methods, and can greatly improve scene parsing performance, particularly in those categories that have clear depth distinction and might be misclassified with RGB-only features. Furthermore, we also extend our proposed module to other urban scene semantic reasoning tasks such as vehicle detection and road segmentation, which are implemented by effectively learning and exploiting the encoded depth-semantics and transferring the learned representations with fine-tuning. The extensive experiments on the popular datasets Cityscapes and KITTI demonstrate that our method performs quite well and can significantly improve the state-of-the-art methods.

Semantic segmentation and depth estimation play important roles in the field of autonomous driving. In recent years, the advantages of Convolutional Neural Networks (CNNs) have allowed these two topics to flourish. However, people always solve these two tasks separately and rarely solve them in a united model. In this paper, we propose a Mutual Encouragement Network (MENet), which includes a semantic segmentation branch and a disparity regression branch, and simultaneously generates semantic map and visual disparity. In the cost volume construction phase, the depth information is embedded in the semantic segmentation branch to increase contextual understanding. Similarly, the semantic information is also included in the disparity regression branch to generate more accurate disparity. Two branches mutually promote each other during training phase and inference phase. We conducted our method on the popular dataset KITTI, and the experimental results show that our method can outperform the state-of-the-art methods on both visual disparity generation and semantic segmentation. In addition, extensive ablation studies also demonstrate that the two tasks in our method can facilitate each other significantly with the proposed approach.

Foreground and background cues can assist humans in quickly understanding visual scenes. In computer vision, however, it is difficult to detect salient objects when they touch the image boundary. Hence, detecting salient objects robustly under such circumstances without sacrificing precision and recall can be challenging. In this paper, we propose a novel model for salient region detection, namely, the foreground-center-background (FCB) saliency model. Its main highlights as follows. First, we use regional color volume as the foreground, together with perceptually uniform color differences within regions to detect salient regions. This can highlight salient objects robustly, even when they touched the image boundary, without greatly sacrificing precision and recall. Second, we employ center saliency to detect salient regions together with foreground and background cues, which improves saliency detection performance. Finally, we propose a novel and simple yet efficient method that combines foreground, center, and background saliency. Experimental validation with three well-known benchmark data sets indicates that the FCB model outperforms several state-of-the-art methods in terms of precision, recall, F-measure, and particularly, the mean absolute error. Salient regions are brighter than those of some existing state-of-the-art methods.

Semantic segmentation-based scene parsing plays an important role in automatic driving and autonomous navigation. However, most of the previous models only consider static images, and fail to parse sequential images because they do not take the spatial-temporal continuity between consecutive frames in a video into account. In this paper, we propose a depth embedded recurrent predictive parsing network (RPPNet), which analyzes preceding consecutive stereo pairs for parsing result. In this way, RPPNet effectively learns the dynamic information from historical stereo pairs, so as to correctly predict the representations of the next frame. The other contribution of this paper is to systematically study the video scene parsing (VSP) task, in which we use the RPPNet to facilitate conventional image paring features by adding spatial-temporal information. The experimental results show that our proposed method RPPNet can achieve fine predictive parsing results on cityscapes and the predictive features of RPPNet can significantly improve conventional image parsing networks in VSP task.

With the expansion of data, increasing imbalanced data has emerged. When the imbalance ratio of data is high, most existing imbalanced learning methods decline in classification performance. To address this problem, a few highly imbalanced learning methods have been presented. However, most of them are still sensitive to the high imbalance ratio. This work aims to provide an effective solution for the highly imbalanced data classification problem. We conduct highly imbalanced learning from the perspective of feature learning. We partition the majority class into multiple blocks with each being balanced to the minority class and combine each block with the minority class to construct a balanced sample set. Multiset feature learning (MFL) is performed on these sets to learn discriminant features. We thus propose an uncorrelated cost-sensitive multiset learning (UCML) approach. UCML provides a multiple sets construction strategy, incorporates the cost-sensitive factor into MFL, and designs a weighted uncorrelated constraint to remove the correlation among multiset features. Experiments on five highly imbalanced datasets indicate that: UCML outperforms state-of-the-art imbalanced learning methods.

Person re-identification has been widely studied due to its importance in surveillance and forensics applications. In practice, gallery images are high resolution (HR), while probe images are usually low resolution (LR) in the identification scenarios with large variation of illumination, weather, or quality of cameras. Person re-identification in this kind of scenarios, which we call super-resolution (SR) person re-identification, has not been well studied. In this paper, we propose a semi-coupled low-rank discriminant dictionary learning (SLD2L) approach for SR person re-identification task. With the HR and LR dictionary pair and mapping matrices learned from the features of HR and LR training images, SLD2L can convert the features of the LR probe images into HR features. To ensure that the converted features have favorable discriminative capability and the learned dictionaries can well characterize intrinsic feature spaces of the HR and LR images, we design a discriminant term and a low-rank regularization term for SLD2L. Moreover, considering that low resolution results in different degrees of loss for different types of visual appearance features, we propose a multi-view SLD2L (MVSLD2L) approach, which can learn the type-specific dictionary pair and mappings for each type of feature. Experimental results on multiple publicly available data sets demonstrate the effectiveness of our proposed approaches for the SR person re-identification task.

In real-word visual applications, distribution mismatch between samples from different domains may significantly degrade classification performance. To improve the generalization capability of classifier across domains, domain adaptation has attracted a lot of interest in computer vision. This work focuses on unsupervised domain adaptation which is still challenging because no labels are available in the target domain. Most of the attention has been dedicated to seeking domain-invariant feature by exploring the shared structure between domains, ignoring the valuable discriminative information contained in the labeled source data. In this paper, we propose a Dictionary Evolution (DE) approach to construct discriminative features robust to domain shift. Specifically, DE aims to adapt a discriminative dictionary learnt based on labeled source samples to unlabeled target samples through a gradual transition process. We show that the learnt dictionary is endowed with cross-domain data representation ability and powerful discriminant capability. Empirical results on real world data sets demonstrate the advantages of the proposed approach over competing methods.

Sparse subspace learning has been demonstrated to be effective in data mining and machine learning. In this paper, we cast the unsupervised feature selection scenario as a matrix factorization problem from the view of sparse subspace learning. By minimizing the reconstruction residual, the learned feature weight matrix with the l2,1-norm and the non-negative constraints not only removes the irrelevant features, but also captures the underlying low dimensional structure of the data points. Meanwhile in order to enhance the model's robustness, we attempt to solve our problem by l1-norm error function which is resistant to outliers and sparse noise. An efficient iterative algorithm is introduced to optimize this non-convex and non-smooth objective function and the proof of its convergence is given. Particularly, differ from conventional non-negative updating rules, we design a novel multiplicative update rule to iteratively solve the feature weight matrix, and we validate its non-negativity. Comparative experiments on various original datasets with and without malicious pollution demonstrate performance superiority of our model.

Feature selection, selecting the most informative subset of features, is an important research direction in dimension reduction. The combinatorial search in feature selection is essentially a binary optimization problem, known as NP hard, which can be alleviated by learning feature weights. Traditional feature weights algorithms rely on heuristic search path. These approaches neglect the interaction and dependency between different features, and thus provide no guarantee for optimality. In this paper, we propose a novel joint feature weights learning framework, which imposes both nonnegative and$\ell _{2,1}$-norm constraints on the feature weights matrix. The nonnegative property ensures the physical significance of learned feature weights. Meanwhile,$\ell _{2,1}$-norm minimization achieves joint selection of the most relevant features by exploiting the whole feature space. More importantly, an efficient iterative algorithm with proved convergence is designed to optimize a convex objective function. Using this framework as a platform, we propose new supervised and unsupervised joint feature selection methods. Particularly, in the proposed unsupervised method, nonnegative graph embedding is developed to exploit intrinsic structure in the weighted space. Comparative experiments on seven real-world data sets indicate that our framework is both effective and efficient.

A general assumption in pattern recognition is that training samples and testing samples come from the same distribution. However, the accuracy rate of classification will dramatically drop when the assumption is invalid. Domain adaptation tries to alleviate the problem via correcting the mismatch of sample distribution in source and target domains. In this paper, we propose a Kernel Subspace Alignment (KSA) approach for unsupervised domain adaptation. The basic idea of KSA is to extract nonlinear feature separately for both the source and target domain, then align the two feature coordinate systems to make the feature invariant to domain shift. Experimental results show that KSA outperforms competitive approaches for unsupervised domain adaptation.

Disulfide connectivity is an important protein structural characteristic. Accurately predicting disulfide connectivity solely from protein sequence helps to improve the intrinsic understanding of protein structure and function, especially in the post-genome era where large volume of sequenced proteins without being functional annotated is quickly accumulated. In this study, a new feature extracted from the predicted protein 3D structural information is proposed and integrated with traditional features to form discriminative features. Based on the extracted features, a random forest regression model is performed to predict protein disulfide connectivity. We compare the proposed method with popular existing predictors by performing both cross-validation and independent validation tests on benchmark datasets. The experimental results demonstrate the superiority of the proposed method over existing predictors. We believe the superiority of the proposed method benefits from both the good discriminative capability of the newly developed features and the powerful modelling capability of the random forest. The web server implementation, called TargetDisulfide, and the benchmark datasets are freely available at: http://csbio.njust.edu.cn/bioinf/TargetDisulfide for academic use.

Multi-view feature learning is an attractive research topic with great practical success. Canonical correlation analysis (CCA) has become an important technique in multi-view learning, since it can fully utilize the inter-view correlation. In this paper, we mainly study the CCA based multi-view supervised feature learning technique where the labels of training samples are known. Several supervised CCA based multi-view methods have been presented, which focus on investigating the supervised correlation across different views. However, they take no account of the intra-view correlation between samples. Researchers have also introduced the discriminant analysis technique into multi-view feature learning, such as multi-view discriminant analysis (MvDA). But they ignore the canonical correlation within each view and between all views. In this paper, we propose a novel multi-view feature learning approach based on intra-view and inter-view supervised correlation analysis (I2SCA), which can explore the useful correlation information of samples within each view and between all views. The objective function of I2SCA is designed to simultaneously extract the discriminatingly correlated features from both inter-view and intra-view. It can obtain an analytical solution without iterative calculation. And we provide a kernelized extension of I2SCA to tackle the linearly inseparable problem in the original feature space. Four widely-used datasets are employed as test data. Experimental results demonstrate that our proposed approaches outperform several representative multi-view supervised feature learning methods.

Object registration has been widely discussed with the development of various range sensing technologies. In most work, however, the point clouds of reference and target are generated by the same technology, such as a Kinect range camera, LiDAR sensor, or Structure from Motion technique. Cases in which reference and target point clouds are generated by different technologies are rarely discussed. Due to the significant differences across various point cloud data in terms of point cloud density, sensing noise, scale, occlusion etc., object registration between such different point clouds becomes extremely difficult. In this study, we address for the first time an even more challenging case in which the differently-sourced point clouds are acquired from a real street view. One is generated on the basis of an image sequence through the SfM process, and the other is produced directly by the LiDAR system. We propose a two-stage matching and registration algorithm to achieve object registration between these two different point clouds. The experiments are based on real building object point cloud data and demonstrate the effectiveness and efficiency of the proposed solution. The newly proposed solution can be further developed to contribute to several related applications, such as Location Based Service.

The perspective of image manifold and associated manifold learning methods have demonstrated promising results in finding the underlying structure from images in the high dimensional space. Conventional manifold learning methods construct the similarity relationship of image set only based on the pairwise Euclidean distance of images, so they may obtain deceptive similarity and suffer performance degradation. In this paper, we present an Neighboring Similarity Integration(NSI) algorithm to explore image manifold under probability preserving principle. NSI is based on the neighboring similarity of image samples and the local structures of image manifold, and can increases the estimation accuracy of similarity and enhance the learning ability for image manifold. The experimental results of image visualization problem on Yale and MNIST databases are presented to demonstrate the effectiveness of the proposed method.

Recently, various graph-based methods have be proposed for salient object detection. These algorithms represent image points and their similarity as nodes and edges in a graph. Although the edge structure and weighting are the heart of these methods, the graph construction has not been studied in detail. In this paper, we exploit image priors, including spatial priors, color priors, and a central bias prior, to construct the graph. We connect nodes which are spatially close in the image, nodes which have similar color features, and the boundary nodes along the borders of the image, while weighting edges according to both their color similarity and spatial proximity. Moreover, we propose a new sine spatial distance instead of the commonly-used Euclidean spatial distance, which better captures the central bias in scenes. Extensive experiments show that our method outperforms thirteen state-of-the-art methods on four different image databases.

Partially occluded or illuminated faces pose a significant obstacle for robust, real-world face recognition. The problem of how to characterize the error caused by occlusion or illumination is still a challenging task. There must exist some close relationship between the error metric and error distribution. However, some metric (e.g. Z2-norm) can't characterize this error distribution completely. By some experiments, we found that nuclear norm is more suitable for characterizing the occluded or illuminated error distribution. Thus, a nuclear norm regularized sparse coding model is presented. Such a problem is solved by using ALM (or ADMM). In addition, we use nuclear norm as a metric to characterize the distance between reconstruction samples and classes. The experiments for image classification and face reconstruction demonstrate that our algorithm is robust to some face variations such as occlusion and illumination, and thus can act as a fast solver for matrix regression problem.

Nonlocal regularization has been verified as an effective way to estimate optical flow. Most work in this line constructs the regularizer by only considering the structure of regular grid-like nonlocal neighborhood, but not explicitly takes advantage of the global structure. In this paper, we propose to construct a super pixel based region tree to explicitly incorporate the global structure information into the regularizer. To make use of this non-regular nonlocal (NRNL) regularizer to obtain region-wise smooth and discontinuity preserving flow filed, we first reconstruct the flow for each super pixel by sparse representation, and then dynamically select the super pixel flow with the lowest energy as the optimally-recovered flow field, which corresponds to the optimal sub-region tree. Finally, we update the flow alternatively through continuous optimization. Incorporating the super pixel and sparse representation method not only constrains the nonlocal information that comes from homogeneous region, but also removes the intermediate flow field noise. Experiments on the Middlebury benchmark demonstrate the effectiveness of our method.

Canonical correlation analysis (CCA) has been widely applied to information fusion. It only considers the correlated information of the paired data, but ignores the correlated information between the samples in the same class. Furthermore, class information is useful for CCA, but there is little class information in the scenarios of real applications. Thus, it is difficult to utilize the correlated information between the samples in the same class. To utilize the correlated information between the samples, we propose a method named Unsupervised Discriminant Canonical Correlation Analysis (UDCCA). In UDCCA, the class membership and mapping are iteratively computed by using the normalized spectral clustering and generalized Eigen value methods alternatively. The experimental results on the MFD dataset and ORL dataset show that UDCCA outperforms traditional CCA and its variants in most situations.

BACKGROUND: Vitamins are typical ligands that play critical roles in various metabolic processes. The accurate identification of the vitamin-binding residues solely based on a protein sequence is of significant importance for the functional annotation of proteins, especially in the post-genomic era, when large volumes of protein sequences are accumulating quickly without being functionally annotated. RESULTS: In this paper, a new predictor called TargetVita is designed and implemented for predicting protein-vitamin binding residues using protein sequences. In TargetVita, features derived from the position-specific scoring matrix (PSSM), predicted protein secondary structure, and vitamin binding propensity are combined to form the original feature space; then, several feature subspaces are selected by performing different feature selection methods. Finally, based on the selected feature subspaces, heterogeneous SVMs are trained and then ensembled for performing prediction. CONCLUSIONS: The experimental results obtained with four separate vitamin-binding benchmark datasets demonstrate that the proposed TargetVita is superior to the state-of-the-art vitamin-specific predictor, and an average improvement of 10% in terms of the Matthews correlation coefficient (MCC) was achieved over independent validation tests. The TargetVita web server and the datasets used are freely available for academic use at http://csbio.njust.edu.cn/bioinf/TargetVita or http://www.csbio.sjtu.edu.cn/bioinf/TargetVita.

Sparse representation has been a very active research area in recent years. Similarity analysis is an attractive research topic in the field of pattern recognition. In this paper, we take advantage of sparse representation in similarity analysis, and propose a novel unsupervised feature extraction approach, named similarity preserving analysis based on sparse representation (SPASR). SPASR projects samples from a high-dimensional space into a low-dimensional subspace, where the sparse reconstructive similarity relations among samples and the similarities of original samples and sparsely reconstructed samples are preserved. Experiments on the AR face database and COIL-20 object database demonstrate that the proposed SPASR approach outperforms several representative unsupervised subspace learning methods.

Hierarchy plays a crucial role in the development of the granular computing. In this paper, three different hierarchies are considered for judging whether a granulation structure is finer or coarser than another one. The first hierarchy is based on the set containment of information granulations, the second hierarchy is based on the cardinal numbers of information granulations while the third hierarchy is based on the sum of cardinal numbers of information granulations. Through introducing set distance and knowledge distance, we investigate the algebraic lattices, in which the derived partial orders are corresponding to the three different hierarchies, respectively. From the viewpoint of distance, these results look forward to provide a more comprehensible perspective for the study of hierarchies on granulation structures.

Accurately identifying the protein-ligand binding sites or pockets is of significant importance for both protein function analysis and drug design. Although much progress has been made, challenges remain, especially when the 3D structures of target proteins are not available or no homology templates can be found in the library, where the template-based methods are hard to be applied. In this paper, we report a new ligand-specific template-free predictor called TargetS for targeting protein-ligand binding sites from primary sequences. TargetS first predicts the binding residues along the sequence with ligand-specific strategy and then further identifies the binding sites from the predicted binding residues through a recursive spatial clustering algorithm. Protein evolutionary information, predicted protein secondary structure, and ligand-specific binding propensities of residues are combined to construct discriminative features; an improved AdaBoost classifier ensemble scheme based on random undersampling is proposed to deal with the serious imbalance problem between positive (binding) and negative (nonbinding) samples. Experimental results demonstrate that TargetS achieves high performances and outperforms many existing predictors. TargetS web server and data sets are freely available at: http://www.csbio.sjtu.edu.cn/bioinf/TargetS/ for academic use.

A sparse representation-based classifier (SRC) is developed and shows great potential for real-world face recognition. This paper presents a dimensionality reduction method that fits SRC well. SRC adopts a class reconstruction residual-based decision rule, we use it as a criterion to steer the design of a feature extraction method. The method is thus called the SRC steered discriminative projection (SRC-DP). SRC-DP maximizes the ratio of between-class reconstruction residual to within-class reconstruction residual in the projected space and thus enables SRC to achieve better performance. SRC-DP provides low-dimensional representation of human faces to make the SRC-based face recognition system more efficient. Experiments are done on the AR, the extended Yale B, and PIE face image databases, and results demonstrate the proposed method is more effective than other feature extraction methods based on the SRC.

In this paper, we propose a new multiscale saliency detection algorithm based on principal component analysis. To measure saliency of pixels in a given image, we first segment the image into patches and then use the principal component analysis to reduce the dimensions, in which it throw out dimensions that are noises with respect to the saliency calculation. The saliency of a patch is computed as the dissimilarities of colors and the spatial distance between it and other patches. Finally, we implement our algorithm through multiple scales so it can further decrease the saliency of background. Our method was compared with other saliency detection approaches using two public image datasets. Experimental results show that our method outperforms current state-of-the-art methods on predicting human fixations and salient object segmentation.

The neighborhood system based rough set is a generalization of Pawlak's rough set model since the former uses the neighborhood system instead of the partition for constructing target approximation. In this paper, the neighborhood system based rough set approach is employed to deal with the incomplete information system. By the coverings induced by the maximal consistent blocks and the support sets of the descriptors, respectively, two neighborhood systems based rough sets are explored. By comparing with the original maximal consistent block and descriptor based rough sets, the neighborhood system based rough sets hold the same lower approximations and the smaller upper approximations. Furthermore, the concept of attribute reduction is introduced into the neighborhood systems and the corresponding rough sets. The judgement theorems and discernibility functions to compute reducts are also presented. Some numerical examples are employed to substantiate the conceptual arguments.

Subspace learning is an effective and widely used image feature extraction and classification technique. However, for the large-scale image recognition issue in real-world applications, many subspace learning methods often suffer from large computational burden. In order to reduce the computational time and improve the recognition performance of subspace learning technique under this situation, we introduce the idea of parallel computing which can reduce the time complexity by splitting the original task into several subtasks. We develop a parallel subspace learning framework. In this framework, we first divide the sample set into several subsets by designing two random data division strategies that are equal data division and unequal data division. These two strategies correspond to equal and unequal computational abilities of nodes under parallel computing environment. Next, we calculate projection vectors from each subset in parallel. The graph embedding technique is employed to provide a general formulation for parallel feature extraction. After combining the extracted features from all nodes, we present a unified criterion to select most distinctive features for classification. Under the developed framework, we separately propose supervised and unsupervised parallel subspace learning approaches, which are called parallel linear discriminant analysis (PLDA) and parallel locality preserving projection (PLPP). PLDA selects features with the largest Fisher scores by estimating the weighted and unweighted sample scatter, while PLPP selects features with the smallest Laplacian scores by constructing a whole affinity matrix. Theoretically, we analyze the time complexities of proposed approaches and provide the fundamental supports for applying random division strategies. In the experiments, we establish two real parallel computing environments and employ four public image and video databases as the test data. Experimental results demonstrate that the proposed approaches outperform several related supervised and unsupervised subspace learning methods, and significantly reduce the computational time.

Feature extraction is one of the most important problems in image recognition tasks. In many applications such as face recognition, it is desirable to eliminate the redundancy among the extracted discriminant features. In this paper, we propose two novel feature extraction approaches named local uncorrelated discriminant transform (LUDT) and weighted global uncorrelated discriminant transform (WGUDT) for face recognition, respectively. LUDT and WGUDT separately construct the local uncorrelated constraints and the weighted global uncorrelated constraints. Then they iteratively calculate the optimal discriminant vectors that maximize the Fisher criterion under the corresponding statistical uncorrelated constraints, respectively. The proposed LUDT and WGUDT approaches are evaluated on the public AR and FERET face databases. Experimental results demonstrate that the proposed approaches outperform several representative feature extraction methods.

Manifold learning is an effective feature extraction technique, which seeks a low-dimensional space where the manifold structure, in terms of local neighborhood, of the data set can be well preserved. A typical manifold learning method constructs a local neighborhood centered at individual samples. In this paper, we propose to construct local neighborhoods that centered at subclass centers, and seek an embedded space where such neighborhood is well preserved. We show from a probability perspective that, neighbors of a subclass center would contain more intra-class data than inter-class data, which may be desirable for discrimination. Meanwhile, we simultaneously enhance the discriminative power of extracted features by maximizing the Fisher ratio of embedded data based on subclass centers. Experimental results on CAS-PEAL and FERET face databases demonstrate that our proposed approach is more effective than most typical manifold learning methods and their supervised extensions in classification performance.

A new fuzzy clustering algorithm using multi-prototype representation of clusters is proposed in this paper to discover clusters with arbitrary shapes and sizes. Intra-cluster non-consistency and inter-cluster overlap are proposed as two mistake measurements to guide the splitting and merging step of the algorithm. In the splitting step, clusters with the largest intra-cluster non-consistency are iteratively split such that the resulting subclusters only contain data from the same class. In the following merging step, subclusters with the largest inter-cluster overlap are iteratively merged until a pre-determined cluster number is achieved. A multi-prototype representation of clusters is used in the merging step to handle the clusters with different size and shapes. Experimental results on synthetic and real datasets demonstrate the effectiveness and robustness of the proposed algorithm.

In this paper, we propose a two-phase test sample representation method for face recognition. The first phase of the proposed method seeks to represent the test sample as a linear combination of all the training samples and exploits the representation ability of each training sample to determine M “nearest neighbors” for the test sample. The second phase represents the test sample as a linear combination of the determined M nearest neighbors and uses the representation result to perform classification. We propose this method with the following assumption: the test sample and its some neighbors are probably from the same class. Thus, we use the first phase to detect the training samples that are far from the test sample and assume that these samples have no effects on the ultimate classification decision. This is helpful to accurately classify the test sample. We will also show the probability explanation of the proposed method. A number of face recognition experiments show that our method performs very well.

In this paper, a kernel uncorrelated adjacent-class discriminant analysis (KUADA) approach is proposed for image recognition. The optimal nonlinear discriminant vector obtained by this approach can differentiate one class and its adjacent classes, i.e., its nearest neighbor classes, by constructing the specific between-class and within-class scatter matrices in kernel space using the Fisher criterion. In this manner, KUADA acquires all discriminant vectors class by class. Furthermore, KUADA makes every discriminant vector satisfy locally statistical uncorrelated constraints by using the corresponding class and part of its most adjacent classes. Experimental results on the public AR and CAS-PEAL face databases demonstrate that the proposed approach outperforms several representative nonlinear discriminant methods.

Automated cell phenotype image classification is an interesting bioinformatics problem. In this paper, an automated cell phase classification framework is investigated for zebra fish presomitic mesoderm (PSM) images. Low image resolution, gradual transitions between adjacent categories and irregularity of real cell images make this classification task tough but intriguing. The proposed framework first segments zebra fish image into cell patches by a two-stage segmentation procedure, then extracts feature set NF9, which designed especially for this low resolution image set, on each cell patch, and finally employs support vector machine (SVM) as cell classifier. At present, the total accuracy by NF9 is 75%.

The general computational models of visual attention are to obtain multi-scale feature maps in terms of visual properties like intensity, color and orientation, and then combine them to get one saliency map. But due to the lack of object edge information and reasonable feature combination strategy, the visual saliency map of the image is a blur map. Being aware of these, we propose a new scheme for saliency extraction. In this paper, we firstly put forward a sparse embedding feature combination strategy, inspired by sparse representation. The strategy is used to combine the salient regions from the individual feature maps based on a novel feature sparse indicator that measures the contribution of each map to saliency. Then we combine traditional visual attention with edge information. Results on different scene images show that our method outperforms other traditional feature combination strategies.

This paper presents a new segmentation method based on division of space which chooses principal curves to extract strokes of characters and form the initial stroke set. The strokes in the initial set are disposed by the fuzzy theorems and grouped based on the confidence of the classifiers. The training sample space is constructed by the Affinity Propagation (AP) algorithm and the Biomimetic Pattern Recognition (BPR) theory. The strokes are arranged in a sequence divided by calculating the distance of each subsequence to the relative subspace. Finally, with the maximum posterior (MAP) criterion, the optimal segmentation hypotheses described in a probabilistic model is found. Our system is validated by experimental results from samples of real Chinese bank checks, achieving a correct rate of without 95.23% rejection.

This paper discusses the problem of what kind of learning model is suitable for the tasks of feature extraction for data representation and suggests two evaluation criteria for nonlinear feature extractors: reconstruction error minimization and similarity preservation. Based on the suggested evaluation criteria, a new type of principal curve-similarity preserving principal curve (SPPC) is proposed. SPPCs minimize the reconstruction error under the condition that the similarity between similar samples are preserved in the extracted features, thus giving researchers effective and reliable cognition of the inner structure of data sets. The existence and properties of SPPCs are analyzed; a practical learning algorithm is proposed and high dimensional extensions of SPPCs are also discussed. Experimental results show the virtues of SPPCs in preserving inner structures of data sets and discovering manifolds with high nonlinearity.

In this paper, a novel discriminant feature extraction algorithm employing center-based distance is proposed for face recognition. This new method, which is a supervised linear dimensionality reduction and feature extraction approach, computes the center-based distance between each training sample-pairs in the same class and the distance between each training sample-pair belonging to different classes. Then the high-dimensional data are embedded into a low-dimensional space, preserving the within-class geometric structure on a submanifold via maximum variance projection. Many experiments on ORL and Yale face database indicate that this method is highly effective.

This paper presents a new nonparametric linear feature extraction method coined geometrically intuitive marginal discriminant analysis (IMDA). Motivated by the law of cosines in trigonometry, we characterize the square local margin by a weighted difference of the square between-class distance and the square within-class distance. Based on this characterization, we design a class margin criterion which is used to determine an optimal transform matrix such that the class margin is maximized in the transformed space. The proposed method was applied to face recognition and evaluated on the Yale and the FERET databases. Experimental results demonstrate the effectiveness of the proposed method.

The purpose of this paper is to present a new rough set model for generating negative rules from the incomplete information system. A negative rule indicates that if an object does not satisfy the attribute-value pairs in the condition part, then we can exclude the decision part from such object. The proposed rough set model is constructed on the basis of a difference relation. Such difference relation is a binary relation without any constraints. Moreover, to simplify the negative rules generated from the difference relation-based rough approximations, the concepts of lower, upper approximate and rough reducts are also proposed. Some numerical examples are employed to substantiate the conceptual arguments.

This paper introduces the minimal local reconstruction error (MLRE) as a similarity measure and presents a MLRE-based classier. From the geometric meaning of the minimal local reconstruction error, we derive that the MLRE-based classifier is a generalization of the conventional nearest neighbor classier and the nearest neighbor line and plane classifiers. We further apply the MLRE measure to characterize the within-class and between-class local scatters and then develop a MLRE measure based discriminant feature extraction method. The proposed MLRE-based feature extraction method is in line with the MLRE-based classification method in spirit, thus the two methods can be seamlessly combined in applications. The experimental results on the CENPARMI handwritten numeral database and the FERET face image database show effectiveness of the proposed MLRE-based feature extraction and classification method.

In this paper, a new particle swarm based stereo algorithm is presented. Our motivation is to improve the accuracy of the disparity map by removing the mismatches caused by both occlusions and false targets. In our approach, the stereo matching problem is divided into two steps, including partial matching of segmented image and particle swarm optimization of the rest. The algorithm first takes advantage of SAD and Dynamic Programming to remove the mismatches mainly caused by visibility problems; after the first step, the algorithm selects all the rest image segmented regions, takes them as a particle and uses particle swarm to optimization it. In the second step, the cost function is defined on the pixel level, as well as on the segmented level, while the pixel level measures the data similarity based the current disparity map, the segmented level incorporates a smooth term. Results obtained for benchmark indicate that the proposed method is able to get rather accurate disparity maps.

In this paper, a reformative scatter difference discriminant criterion (SDDC) with fuzzy set theory is studied. The scatter difference between between-class and within-class as discriminant criterion is effective to overcome the singularity problem of the within-class scatter matrix due to small sample size problem occurred in classical Fisher discriminant analysis. However, the conventional SDDC assumes the same level of relevance of each sample to the corresponding class. So, a fuzzy maximum scatter difference analysis (FMSDA) algorithm is proposed, in which the fuzzy k-nearest neighbor (FKNN) is implemented to achieve the distribution information of original samples, and this information is utilized to redefine corresponding scatter matrices which are different to the conventional SDDC and effective to extract discriminative features from overlapping (outlier) samples. Experiments conducted on FERET face databases demonstrate the effectiveness of the proposed method.

Maximum margin criterion (MMC) based feature extraction method is more efficient than LDA for calculating the discriminant vectors since it does not need to calculate the inverse within-class scatter matrix. However, MMC ignores the discriminative information within the local structures of samples. In this paper, we develop a novel criterion to address the issue, namely local maximum margin criterion (Local MMC). We define the total Laplacian matrix, within-class Laplacian matrix and between-class Laplacian matrix using the samples similar weighting. Local MMC gets the discriminant vectors by maximizing the difference between between-class laplacian matrix and within-class laplacian matrix. Experiments on FERET face database show the effectiveness of the proposed local MMC based feature extraction method.

In this paper, we propose a novel method for feature extraction and recognition, namely, complete fuzzy LDA (CFLDA). CFLDA combines the complete LDA and fuzzy set theory. CFLDA redefines the fuzzy between-class scatter matrix and fuzzy within-class scatter matrix that make fully of the distribution of sample and simultaneously extract the irregular discriminative information and regular discriminative information. Experiments on the Yale and FERET face databases show that CFLDA can work well and surpass fuzzy Fisherface.

This paper develops an unsupervised discriminant projection (UDP) technique for dimensionality reduction of high-dimensional data in small sample size cases. UDP can be seen as a linear approximation of a multimanifolds-based learning framework which takes into account both the local and nonlocal quantities. UDP characterizes the local scatter as well as the nonlocal scatter, seeking to find a projection that simultaneously maximizes the nonlocal scatter and minimizes the local scatter. This characteristic makes UDP more intuitive and more powerful than the most up-to-date method, Locality Preserving Projection (LPP), which considers only the local scatter for clustering or classification tasks. The proposed method is applied to face and palm biometrics and is examined using the Yale, FERET, and AR face image databases and the PolyU palmprint database. The experimental results show that UDP consistently outperforms LPP and PCA and outperforms LDA when the training sample size per class is small. This demonstrates that UDP is a good choice for real-world biometrics applications.

The literature on independent component analysis (ICA)-based face recognition generally evaluates its performance using standard principal component analysis (PCA) within two architectures, ICA Architecture I and ICA Architecture II. In this correspondence, we analyze these two ICA architectures and find that ICA Architecture I involves a vertically centered PCA process (PCA I), while ICA Architecture II involves a whitened horizontally centered PCA process (PCA II). Thus, it makes sense to use these two PCA versions as baselines to reevaluate the performance of ICA-based face-recognition systems. Experiments on the FERET, AR, and AT&T face-image databases showed no significant differences between ICA Architecture I (II) and PCA I (II), although ICA Architecture I (or II) may, in some cases, significantly outperform standard PCA. It can be concluded that the performance of ICA strongly depends on the PCA process that it involves. Pure ICA projection has only a trivial effect on performance in face recognition.

This paper develops a "non-locality" preserving projection (NLPP) technique for feature extraction. In contrast to the existing locality preserving projection (LPP), a technique based on the characterization of the local scatter, NLPP is a method based on the characterization of the non-local scatter. Intuitively, NLPP should be more effective than LPP when the non-local information plan a dominant role in discrimination. NLPP is tested using the PolyU palmprint database and the experimental results show that NLPP outperforms PCA, LDA and LPP

In the existing LDA models, class mean vector is always estimated by the class sample average. In small sample size problems such as face recognition, however, the class sample average does not suffice to provide an accurate estimate of the class mean based on a few of given samples, particularly when there are outliers in the sample set. To overcome this weakness, we use the class median vector to estimate the class mean vector in LDA modeling. The class median vector has two advantages over the class sample average: (1) the class median (image) vector preserves useful details in the sample images and (2) the class median vector is robust to outliers that exist in training sample set. The proposed median LDA model is evaluated using three popular face image databases. All experiment results indicate that median LDA is more effective than the common LDA and PCA.

The topologies of data distributions are very important for data description. Usually, it is not easy to find a description that can give us an intuitional understanding of the topologies for general distributions. In this paper, a novel concept, a topology graph, is proposed as a description for the principal topology of data distribution. The topology graph builds a one-to-one correspondence between the principal topology of the distribution and the topology itself: annularity features of the principal topology correspond to the loops of the graph, and the divarication features correspond to the branches of the graph. In general, the topology graph can be considered as the skeleton of the data distribution. A divide-and-combine learning strategy is developed to find the topology graphs for general data distributions. The learning strategy is focused on the constrained local description learning and automatic topology generation. Following the learning strategy, a cluster growing algorithm is developed. Experimental results on both artificial datasets and real-world applications show good performance of the proposed algorithm.

The standard PCA was always used as baseline algorithm to evaluate ICA-based face recognition systems in the previous research. In this paper, we examine the two architectures of ICA for image representation and find that ICA Architecture I involves a PCA process by vertically centering (PCA I), while ICA Architecture II involves a whitened PCA process by horizontally centering (PCA II). So, it is reasonable to use these two PCA versions as baseline algorithms to revaluate the ICA-based face recognition systems. The experiments were performed on the FERET face database. The experimental results show there is no significant performance differences between ICA Architecture I (II) and PCA I (II), although ICA Architecture II significantly outperforms the standard PCA. It can be concluded that the performance of ICA strongly depends on its involved PCA process. The pure ICA projection has little effect on the performance of face recognition.

Fisher Linear Discriminant Analysis (LDA) has been successfully used as a data discriminantion technique for face recognition. This paper has developed a novel subspace approach in determining the optimal projection. This algorithm effectively solves the small sample size problem and eliminates the possibility of losing discriminative information. Through the theoretical derivation, we compared our method with the typical PCA-based LDA methods, and also showed the relationship between our new method and perturbation-based method. The feasibility of the new algorithm has been demonstrated by comprehensive evaluation and comparison experiments with existing LDA-based methods.

This paper examines the theory of kernel Fisher discriminant analysis (KFD) in a Hilbert space and develops a two-phase KFD framework, i.e., kernel principal component analysis (KPCA) plus Fisher linear discriminant analysis (LDA). This framework provides novel insights into the nature of KFD. Based on this framework, the authors propose a complete kernel Fisher discriminant analysis (CKFD) algorithm. CKFD can be used to carry out discriminant analysis in "double discriminant subspaces." The fact that, it can make full use of two kinds of discriminant information, regular and irregular, makes CKFD a more powerful discriminator. The proposed algorithm was tested and evaluated using the FERET face database and the CENPARMI handwritten numeral database. The experimental results show that CKFD outperforms other KFD algorithms.

We propose a new kernel direct discriminant analysis (KDDA) algorithm in this paper. First, a recently advocated direct linear discriminant analysis (DLDA) algorithm is overviewed. Then the new KDDA algorithm is developed which can be considered as a kernel version of the DLDA algorithm. The design of the minimum distance classifier in the new kernel subspace is then discussed. The results of experiments on two well-known facial databases show the effectiveness of the proposed method in face recognition. The results of experiments also confirm that DLDA can be viewed as a special case of the proposed KDDA algorithm. 1.

Kernel method-based feature extraction algorithms such as kernel Fisher discriminant analysis (KFDA) have widely been applied to image recognition tasks such as face recognition. For current feature extraction methods based on kernel method, the computation cost to construct kernel matrix mainly depends on the dimension of the original input training samples. Since the dimension of an image vector in face recognition tasks is over ten thousand, kernel-based algorithms have to consume considerable time to build the kernel matrix. In this paper, a fusion of PCA and KFDA for face recognition, shortly called PCA+KFDA, is developed. The algorithm includes two stages: firstly, the classical principal component analysis (PCA) is employed to condense the dimension of face image vector. What follows, kernel Fisher discriminant analysis (KFDA) is applied to the reduced dimensional training samples. Finally, The experimental results on ORL face database indicate that the proposed methods are more efficient than KFDA while retaining the same recognition accuracy.

In cross-country navigation, autonomous land vehicles (ALVs) must traverse harsh natural terrains, which are uneven, rough, and sloping. One of challenges is to evaluate the terrain's characteristics quantitatively so as to prepare for smooth and stable trajectory planning subsequently. In this paper, we proposed a separate-and-integrate model to analysis rugged terrains, and developed a more universal and robust untraversable regions detection method on elevation maps. When separate, we extract the necessary and sufficient terrain characteristics such as slope, roll variance and roughness from elevation maps respectively and when integrate, the fuzzy inference is applied to combine the above terrain features in order to obtain its traversability assessment and local quantitative evaluations. Experimental results show the method can accurately evaluate terrains' characters and properly classify rugged terrains, and the classification results are robust to the uncertainty and imprecision of the terrain information. And because it's based on terrains' geometry clues, the method provides a more generic framework for rugged terrain analysis.

The performance of a novel binary linear classifier named as minimum norm minimum squared-error (MNMSE), which is based on a refined minimum squared-error discriminant criterion is evaluated in this paper. Experimental results show that MNMSE is very effective and efficient for many pattern recognition problems. In most cases it can compete with support vector machines in recognition rate and be more efficient than the methods.

In Chinese, thousands of bankchecks are validated due to manual processing every day to find out the bankchecks, which are invalidate to the bank's rules or contain error input information. It is necessary to relieve people from these intensive and tedious works. This paper presents a technique, which is the preprocess stage in our auto-validating system, for extracting the user-entered courtesy amount item from Chinese bankcheck images. Seal imprints in different types and positions cause the main difficulty in the extracting procedure. Instead of removing lines in bi-level images, we proposed a line removal algorithm based on crossing shape analysis in gray-level image. The handwritten information is extracted by a new recursive thresholding algorithm, which can continue removing the brighter background until only the darkest object is left. The proposed methods have been evaluated on real-life Chinese checks. And the results demonstrate the effectiveness of the proposed preprocessing techniques.

For infrared vehicle verification we propose a novel feature extraction technique based on Gabor filters which consists two main steps: feature extraction and feature weighting. It weights the raw features derived from 2D Gabor filters according to their own degree of dispersion which can enhance the effect of the features whose degree of dispersion is relatively small but also can widely used the statistical information of sample images. Infrared vehicle verification results on the four different videos suggest that the proposed method is superior (in terms of robustness and discrimination ability) to conventional ones. This technique holds good for visual sequences as well.

In this paper, a novel image projection analysis method (UIPDA) is first developed for image feature extraction. In contrast to Liu's projection discriminant method, UIPDA has the desirable property that the projected feature vectors are mutually uncorrelated. Also, a new LDA technique called EULDA is presented for further feature extraction. The proposed methods are tested on the ORL and the NUST603 face databases. The experimental results demonstrate that: (i) UIPDA is superior to Liu's projection discriminant method and more efficient than Eigenfaces and Fisherfaces; (ii) EULDA outperforms the existing PCA plus LDA strategy; (iii) UIPDA plus EULDA is a very effective two-stage strategy for image feature extraction.