Most of the classification models are built for closed set environments, where the model is trained to assign samples to a set of predefined categories. This assumption cannot be hold for models built for UAV aerial videos, where novel videos are likely to be encountered in the test phase. Dealing with unknown videos is fundamental for a reliable classification model. Therefore, in this work, we propose a model for recognizing events acquired using UAV platforms with the non-event detection property. Our model utilized the power of the attention-based model to extract discriminative spatiotemporal features from the video clips. Then, the model is trained with IsoMax loss to detect out-of-distribution videos. The proposed model is evaluated on UAV Events Recognition Dataset (ERA), and the results show that our model is able to detect non-event videos with 70.87% precision. Moreover, non-event detection has increased the accuracy of recognizing known events to 68.44%, which outperforms the accuracy of other state-of-the-art models.

Most scene classification applications in remote sensing images are addressed from a closed set-setting perspective where both the training and testing sets have the same classes. In some applications, the testing set may encounter images belonging to classes not seen during training. In this case, the classifier will face the negative transfer problem, and assign these images to one of the known classes This raises the attention to develop specific open-set methods with unknown image rejection ability. In this paper, we propose an open-set classification method based on vision transformers. An energy-based model is used to learn the density of the training data by reinterpreting the logits of the token classification head of the transformer. At test time, we reject the images with low log-likelihood scores from classification and classify all other images to their labels. The method is evaluated on Optimal-31 a remote sensing dataset, showing comparable results to the state-of-art methods.

In this letter, we propose a continual learning approach for a set of sequential scene classification tasks, where each task contains a group of land-cover classes. Our aim is to learn new tasks in a continual way without significantly degrading the performances of the old ones, due to the tricky catastrophic forgetting problem inherent to neural networks. To this end, we propose a neural architecture composed of two trainable modules. The first module learns its weights by discriminating between the land-cover classes within the new task while keeping trace of the old ones. On the other side, the second module tries to maximize the separation between the tasks by learning on task-prototypes stored in a linear memory (one prototype per task). The experimental results on two scene data sets (Merced and Optimal31) confirm the promising capability of the proposed method.

In this work, we introduce a neural architecture to unsupervised domain from multiple source domains. This architecture uses an EfficientNet as a feature extractor coupled with a set of Softmax classifiers equal to the number of source domains followed by an opportune fusion layer. To reduce the domain discrepancy between each source and target domain, we adopt a Minmax entropy approach that is based on the idea of optimizing in an adversarial manner the conditional entropy of the target samples with respect to each source classifier and minimizes it with respect to the feature extractor. As for the fusion module, we propose a weighted average fusion layer with learnable weights for aggregating the outputs of the different Softmax classifiers. Experiments on a multisource data set composed of images acquired by manned and unmanned aerial vehicles (MAVs/UAVs) over different locations are reported and discussed.

In this study, we propose an electrocardiogram (ECG) system for the simultaneous and remote monitoring of multiple heart patients. It consists of three main components: patient, sever, and monitoring units. The patient unit uses a wearable miniature sensor that continuously measures ECG signals and sends them to a smart mobile phone via a Bluetooth connection. In the mobile device, the ECG signals can be stored, displayed on screen, and automatically transmitted to a distant server unit over the internet; the server stores ECG data from several patients. Health care stakeholders use a monitoring unit to retrieve the ECG signals of multiple patients at any time from the server for display and real-time automatic analysis. The analysis includes segmentation of the ECG signal into separate heartbeats followed by arrhythmia detection and classification. When compared to existing real-time ECG systems, where the detection of abnormalities is usually performed using simple rules, the proposed system implements a real-time classification module that is based on a support vector machine (SVM) classifier. Extensive experimental results on ECG data obtained from a TechPatientTMsimulator, a real person, and 20 records from the MIT arrhythmia database are reported and discussed.

Multiple-criteria decision problems involve selecting an alternative that best satisfies a collection of criteria as quantified by a scalar corresponding to an aggregation of the alternatives satisfaction to the individual criteria. A fundamental issue is the formulation of decision maker's aggregation function based upon the decision maker's perceived relationship between the criteria. Here, we allow the decision maker to express their perceived relationship between the criteria in terms of information about the criteria importances by providing a fuzzy measure over the criteria such that the measure of any subset of criteria is its importance. With the aid of the Choquet integral, we use this fuzzy measure of importances to construct an aggregation function. As the Choquet integral requires an ordering of an alternatives individual criteria satisfactions, special handling is required in the case when criteria satisfactions are interval valued rather then scalar. Here we use the golden rule representative value in the case of interval values.

In this paper, we present a novel method for cross-scene classification in remote sensing images based on generative adversarial networks (GANs). To this end, we train in an adversarial manner an encoder-decoder network coupled with a discriminator network on labeled and unlabeled data coming from two different domains. The encoder-decoder network aims to reduce the discrepancy between the distributions of the two domains, while the discriminator tries to discriminate between them. At the end of the optimization process, we train an extra network on the obtained encoded labeled data and then classify the encoded unlabeled data. Experimental results on two datasets acquired over the cities of Potsdam and Vaihingen with spatial resolutions of 5cm and 9cm, respectively, confirm the promising capability of the proposed method.

We introduce the idea of orthopair membership grades and the related idea of general orthopair fuzzy sets. It is noted that these generalize the intuitionistic and Pythagorean fuzzy sets by allowing the support for and against membership to be almost anywhere in [0, 1] × [0, 1], giving systems modelers great freedom in capturing human knowledge. The aggregation of generalized orthopair fuzzy sets is considered with particular concern for the OWA and Choquet aggregation. The concepts of possibility and certainty as well as plausibility and belief are investigated in this general orthopair environment. We study arithmetic operations on general orthopair fuzzy sets. We show how to obtain associated interval valued fuzzy sets from general orthopair fuzzy sets.

The accurate reconstruction of areas obscured by clouds is among the most challenging topics for the remote sensing community since a significant percentage of images archived throughout the world are affected by cloud covers which make them not fully exploitable. The purpose of this paper is to propose new methods to recover missing data in multispectral images due to the presence of clouds by relying on a formulation based on an autoencoder (AE) neural network. We suppose that clouds are opaque and their detection is performed by dedicated algorithms. The AE in our methods aims at modeling the relationship between a given cloud-free image (source image) and a cloud-contaminated image (target image). In particular, two strategies are developed: the first one performs the mapping at a pixel level while the second one at a patch level to take profit from spatial contextual information. Moreover, in order to fix the problem of the hidden layer size, a new solution combining the minimum descriptive length criterion and a Pareto-like selection procedure is introduced. The results of experiments conducted on three different data sets are reported and discussed together with a comparison with reference techniques.

We introduce the idea of maxitive belief structures, MBS, as a framework for modeling imprecise possibility distributions in a manner analogous to the way Dempster-Shafer belief structures allows the modeling of imprecise probability distributions. We study various properties of these MBS. We consider the problem of obtaining possibility distributions compatible with these belief structures. We consider the problem of fusing multiple MBS and the performance of various arithmetic operations with these objects.

In this paper, we present a domain adaptation network to deal with classification scenarios subjected to the data shift problem (i.e., labeled and unlabeled images acquired with different sensors and over completely different geographical areas). We rely on the power of pretrained convolutional neural networks (CNNs) to generate an initial feature representation of the labeled and unlabeled images under analysis, referred as source and target domains, respectively. Then we feed the resulting features to an extra network placed on the top of the pretrained CNN for further learning. During the fine-tuning phase, we learn the weights of this network by jointly minimizing three regularization terms, which are: 1) the cross-entropy error on the labeled source data; 2) the maximum mean discrepancy between the source and target data distributions; and 3) the geometrical structure of the target data. Furthermore, to obtain robust hidden representations we propose a mini-batch gradient-based optimization method with a dynamic sample size for the local alignment of the source and target distributions. To validate the method, in the experiments we use the University of California Merced data set and a new multisensor data set acquired over several regions of the Kingdom of Saudi Arabia. The experiments show that: 1) pretrained CNNs offer an interesting solution for image classification compared to state-of-the-art methods; 2) their performances can be degraded when dealing with data sets subjected to the data shift problem; and 3) how the proposed approach represents a promising solution for effectively handling this issue.

We introduce the Sugeno integral and describe how it can be used to provide a weighted mean-like aggregation of a collection of values drawn from the unit interval. We explain that the underlying measure provides information about the weights associated with the arguments. We provide an alternative view of the Sugeno integral that enables us to extend its use to situations in which the arguments in the aggregation are possibility distributions. We look at the application of the Sugeno integral to the formulation of decision functions in the case of multi-criteria decision making. We focus on the situation where there exists some possibilistic uncertainty in our knowledge of criteria satisfactions by an alternative. We provide operational formulations for the calculation of some notable decision functions in the case of possibilistically uncertain criteria satisfactions.

In this letter, we propose a novel three-layer convex network termed as 3CN for domain adaptation in multitemporal very high resolution (VHR) remote sensing images. 3CN is composed of three main layers: 1) mapping source training samples to the target domain via a special single-layer feedforward neural network called extreme learning machine (ELM); 2) target image classification via ELM too; and 3) spatial regularization via the random-walker algorithm, which models the target image as a lattice graph and then minimizes an energy functional. This network is convex because all three layers have closed-form solutions. In the preprocessing step, we use scale-invariant feature transform to extract a set of matching key points called inliers from source and target images. Then, these inliers are used by layer 1 of 3CN to spectrally map the source training samples to the target domain. Next, in layer 2, we use the mapped training set to classify the target image. In layer 3, we exploit the spatial contextual information in the target image to reduce noise and generate an improved classification map. In the final step, we iteratively fine-tune the network to increase its discrimination ability and reduce the shift between the target and source domains. In the experiments, we report and discuss the results of the proposed method on two data sets of VHR image pairs acquired by IKONOS-2 and GeoEye-1.

We describe the basic properties of the Dempster-Shafer belief structure and introduce the associated measures of plausibility and belief. We look at the role of these structures for providing a model of imprecise probabilistic information. We next consider the problem of calculating the satisfaction of target values by a variable V whose value is expressed by a belief structure. We first look at the simplest case when the target is expressed as subset of the domain of V . We then look at the situation when the target is expressed by more complex uncertain structures. Among those considered are a probability distribution, another belief structure, measure, and possibility distribution. At a formal level this paper involves the extension of the concepts of plausibility and belief associated with D-S structures from being mappings of subsets of the underlying domain of V into unit interval to be mappings of these more complex structures into the unit interval.

In this paper, we propose a forensic technique that is able to detect the application of a median filter to 1D data. The method relies on deterministic mathematical properties of the median filter, which lead to the identification of specific relationships among the sample values that cannot be found in the filtered sequences. Hence, their presence in the analyzed 1D sequence allows excluding the application of the median filter. Owing to its deterministic nature, the method ensures 0% false negatives, and although false positives (sequences not filtered classified as filtered) are theoretically possible, experimental results show that the false alarm rate is null for sufficiently long sequences. Furthermore, the proposed technique has the capability to locate with good precision a median filtered part of 1-D data and provides a good estimate of the window size used.

In this paper, we present a new semi-supervised method for the classification of hyperspectral and VHR remote sensing images. The method is based on a hierarchical learning paradigm which is composed of multiple layers feeding into each other: 1) feature extraction layer, 2) classification layer, and 3) spatial regularization layer. In the feature extraction layer, the method employs morphological operators. In case of hyperspectral images, a dimensionality reduction step is first applied using an algorithm such PCA. In layer 2, the Extreme Learning Machine is trained and used to build an initial classification map of the image. Finally, in layer 3, a regularization step is applied to exploit spatial information between all pixels in the image. The Random Walker (RW) algorithm is used for this purpose, which uses the output results of layer 2, such as the class map and the posterior probabilities, as inputs. Initial results are obtained using the PAVIA dataset, which outperform the state-of-the-art methods in terms of accuracy and execution times.

In this paper, we propose a novel deep convex network method for domain adaptation in multitemporal remote sensing imagery. We fuse the capabilities of the extreme learning machine (ELM) classifier and local feature descriptor techniques to boost the classification accuracy. We use the Affine Scale Invariant Feature Transform (ASIFT) to extract the key points from the image pair, i.e. source and target domain images. The neural network consist of two layers, one layer uses the keypoints extracted by ASIFT to map the training points of the source image to the target image, while layer 2 is used for the purpose of classification. Experimental results obtained on multitemporal VHR images acquired by the IKONOS2 confirm the promising capability of the proposed method.

Human recognition with heartbeat signal is useful for different applications such as information security, user identification and remote patient monitoring. In this paper, we propose a model-based method for the alignment of heartbeat morphology to enhance the recognition capability. The scale change of different heartbeats of the same individual due to heart rate variability is estimated and inversed to yield better alignment. Recognition capabilities of different alignment methods are analyzed and measured by intra-individual and inter-individual distances of aligned heartbeats. A framework for heartbeat recognition incorporating the model-based alignment method is also presented. We tested the recognition capability of heartbeat morphology by using two different databases. It was found that model-based alignment method was useful to boost the recognition capability of heartbeat morphology. A statistical t-test revealed that the improvement was significant with respect to recognition capabilities of other existing alignment methods. We also used the aligned morphology as a feature, tested the recognition accuracy on both databases and compared the recognition performance to those of four other state-of-the-art features. A large increase in recognition accuracy was obtained especially for a multisession database of heartbeat signals captured from fingers using a handheld ECG device.

We introduce Jeffrey's rule of conditioning. We explain how it enables us to determine the current probability of an event using a collection of conditional probabilities of the event determined from past experiences and the current probabilities of the conditioning events. We note the importance of the joint probabilities of the event of interest and the conditioning events in obtaining the required conditional probabilities. We investigate the use of copula's to help obtain these required joint probabilities. We then apply our results to a problem of financial decision making in which the success of the stock issue of a new company depends on the quality of management of company. Here, past history tells information about the success of a typical company based on its quality of management and our own observations provides information about the quality of the current companies management.

In this letter, we propose an efficient multiclass active learning (AL) method for remote sensing image classification. We fuse the capabilities of an extreme learning machine (ELM) classifier and graph-based optimization methods to boost the classification accuracy while minimizing the user interaction. First, we use the ELM to generate an initial label estimation of the unlabeled image pixels. Then, we optimize a graph-based functional energy that integrates the ELM outputs as an initial estimation of the image structure. As for the ELM, the solution to this multiclass optimization problem leads to a system of linear equations. Due to the sparse Laplacian matrix built from the lattice graph defined on the image pixels, the optimization problem is solved in a linear time. In the experiments, we report and discuss the results of the proposed AL method on two very high resolution images acquired by IKONOS-2 and GoeEye-1, as well as the well-known Pavia University hyperspectral image.

In this letter, we formulate a land-use (LU) classification problem within a compressive sensing (CS) fusion framework. CS aims at providing a compact representation form after a given query image has been processed with an opportune feature extraction type. In particular, residuals are generated from the image reconstruction with dictionaries associated with the available set of possible LUs and gathered to form a single-feature image pattern. The patterns obtained from different types of features are then fused to provide the final LU estimate. Two simple fusion strategies are adopted for such purpose. As demonstrated by experiments ran on the basis of a public benchmark database, the proposed method can achieve substantial classification accuracy gains over reference methods.

This paper introduces a new portable camera-based method for helping blind people to recognize indoor objects. Unlike state-of-the-art techniques, which typically perform the recognition task by limiting it to a single predefined class of objects, we propose here a completely different alternative scheme, defined as coarse description. It aims at expanding the recognition task to multiple objects and, at the same time, keeping the processing time under control by sacrificing some information details. The benefit is to increment the awareness and the perception of a blind person to his direct contextual environment. The coarse description issue is addressed via two image multilabeling strategies which differ in the way image similarity is computed. The first one makes use of the Euclidean distance measure, while the second one relies on a semantic similarity measure modeled by means of Gaussian process estimation. To achieve fast computation capability, both strategies rely on a compact image representation based on compressive sensing. The proposed methodology was assessed on two indoor datasets representing different indoor environments. Encouraging results were achieved in terms of both accuracy and processing time.

This paper presents a novel method to “coarsely” describe extremely high-resolution (EHR) images acquired by means of unmanned aerial vehicles (UAVs) over urban areas. Standard image analysis approaches cannot be directly exploited for the automatic description of UAV images due to their EHR. For this reason, we propose an alternative approach that consists first in the subdivision of the original UAV image in a grid of tiles. Then, each tile is compared with a library of training tiles to inherit the binary multilabel vector of the most similar training tile. This vector conveys a list of classes likely present in the considered tile. Our multiclass tile-based approach needs the definition of two main ingredients: 1) a suitable tile-representation strategy; and 2) a tile-to-tile matching operation. Various tile-representation and matching strategies are investigated. In particular, we present three global representation strategies, which process each tile as a whole and two point-based strategies that exploit points of interest within the considered tile. Regarding the matching strategies, two simple measures of distance, namely, the Euclidean and the chi-squared histogram distances, are explored. Interesting experimental results conducted on a rich set of real UAV images acquired over an urban area are reported and discussed.

In this paper, we develop an automatic method for counting palm trees in UAV images. First we extract a set of keypoints using the Scale Invariant Feature Transform (SIFT). Then, we analyze these keypoints with an Extreme Learning Machine (ELM) classifier a priori trained on a set of palm and no-palm keypoints. As output, the ELM classifier will mark each detected palm tree by several keypoints. Then, in order to capture the shape of each tree, we propose to merge these keypoints with an active contour method based on level-sets (LS). Finally, we further analyze the texture of the regions obtained by LS with local binary patterns (LBPs) to distinguish palm trees from other vegetations. Experimental results obtained on a UAV image acquired over a palm farm are reported and discussed.

In this letter, we show how active learning can be particularly promising for classifying remote sensing images at large scales. The classification model constructed on samples extracted from a limited region of the image, called source domain, exhibits generally poor accuracies when used to predict the samples of a different region, called target domain, due to possible changes in class distributions throughout the image. To alleviate this problem, we suggest selecting and labeling additional samples from the new domain in order to improve generalization capabilities of the model. We propose to implement an initialization strategy based on clustering before applying the traditional active learning method in order to cope with distribution changes and better explore the feature space of the target domain. Experiments on a MODIS dataset for the generation of a land-cover map at European scale show good capabilities of the proposed approach for this purpose.

Recently, a new machine learning approach that is termed as the extreme learning machine (ELM) has been introduced in the literature. This approach is characterized by a unified formulation for regression, binary, and multiclass classification problems, and the related solution is given in an analytical compact form. In this letter, we propose an efficient classification method for hyperspectral images based on this machine learning approach. To address the model selection issue that is associated with the ELM, we develop an automatic-solution-based differential evolution (DE). This simple yet powerful evolutionary optimization algorithm uses cross-validation accuracy as a performance indicator for determining the optimal ELM parameters. Experimental results obtained from four benchmark hyperspectral data sets confirm the attractive properties of the proposed DE-ELM method in terms of classification accuracy and computation time.

In decision-making under uncertainty we have a collection of alternatives from which we must choose one. Associated with each alternative is an uncertainty profile consisting of the set of possible outcomes that can occur if we choose this alternative along with some indication of the uncertainty associated with the outcomes. Since it is difficult to compare these uncertainty profiles one commonly used approach is to obtain a representative value, an aggregation of the information in the uncertainty profile, and use these to compare the alternatives. The method that we use to aggregate the information in the uncertainty profile must reflect aspects of the decision attitude of the decision maker. Here we look at the role that the ordered weighted averaging (OWA) can play in the aggregation process used to obtain these representative values. Since an uncertainty profile can involve a discrete set of possible outcomes or an interval of possible outcomes we provide the OWA operator with the capability to perform aggregations in either of these environments. In addition we provide the OWA operator with the ability to perform aggregations in situations where the arguments being aggregated, the potential outcomes, have an associated uncertainty, probability of occurrence. Particularly notable is the extension the OWA operator to perform aggregation with arguments consisting of a continuum of values with an associated probability density function. We also look at the cases where the uncertainty is modeled with a belief structure as well a possibility distribution.

Our interest here is in multicriteria decision-making when we use a fuzzy measure to capture information about the importances and relationships between the criteria. We describe the use of an integral, such as the Choquet or Sugeno integral, to evaluate the overall satisfaction of each of the available alternatives. We discuss three measures particularly useful for these multicriteria decision problems, the additive, cardinality-based, and possibility measures. We note that the usefulness of these measures is a result of the fact that for each of these, the measure's values for any subset just depends on a small number of parameters. We then consider the situation in which we have some imprecision in these underlying parameters. We show how to represent this imprecision in the underlying parameters using a Dempster-Shafer belief structure. We then consider the evaluation of alternatives under this kind of imprecision using the Choquet, Sugeno, and median type aggregations. As a result of the imprecision in the parameters our overall evaluation for the alternatives, rather than being simple scalar values are imprecise, they are intervals. We discuss some methods for associating a scalar value with an interval. One notable method here is what we refer to as Golden Rule aggregation.

Our focus is on decision making in uncertain environments. We first introduce the Dempster–Shafer framework to model the uncertainty associated with possible outcomes. We then describe an approach for decision making when our uncertainty is captured using the Dempster–Shafer model and where the payoffs are numeric values. An important part of this approach is the role of the decision attitude as well as the aggregation of the possible payoffs. We then look at the situation where the payoffs, rather than being numbers, are values drawn from an ordinal scale. This requires us to provide appropriate operations for combining payoffs drawn from an ordinal scale.

Mathematical morphology has shown to be an effective tool to extract spatial information for remote-sensing image classification. Its application is performed by means of a structuring element (SE), whose shape and size play a fundamental role for appropriately extracting structures in complex regions such as urban areas. In this letter, we propose a novel method, which automatically tailors both the shape and the size of the SE according to the considered classification task. For this purpose, the SE design is formulated as an optimization problem within a particle swarm optimization framework. The experiments conducted on two real images suggest that better accuracies can be achieved with respect to the common procedure for finding the best regular SE, which, so far, is heuristically done.

In this letter, we propose to solve the change detection (CD) problem in multitemporal remote-sensing images using interactive segmentation methods. The user needs to input markers related to change and no-change classes in the difference image. Then, the pixels under these markers are used by the support vector machine classifier to generate a spectral-change map. To enhance further the result, we include the spatial contextual information in the decision process using two different solutions based on Markov random field and level-set methods. While the former is a region-driven method, the latter exploits both region and contour for performing the segmentation task. Experiments conducted on a set of four real remote-sensing images acquired by low as well as very high spatial resolution sensors and referring to different kinds of changes confirm the attractive capabilities of the proposed methods in generating accurate CD maps with simple and minimal interaction.

In the remote sensing field, ground-truth design for collecting training samples represents a tricky and critical problem since it has a direct impact on most of the subsequent image processing and analysis steps. In this paper, we propose a novel framework for assisting a human user in designing ground-truth by photointerpretation for optical remote sensing image classification. The proposed approach is (almost) completely automatic and comprehensive since it aims at assisting the human user from the first to the last step of the process. It is based on unsupervised methods of segmentation and clustering, in order to investigate both the spatial and the spectral information in the process of ground-truth design. The resulting ground-truth is classifier-free and can be further improved by making it classifier-driven through an active learning process. To validate the proposed framework, an experimental study was conducted on very high spatial resolution and hyperspectral images acquired by the IKONOS and the Reflective Optics System Imaging Spectrometer sensors, respectively. The obtained results show the usefulness and effectiveness of the proposed approach.

In this paper, we propose to improve the classification accuracy of hyperspectral images by fusing the capabilities of the support vector machine (SVM) classifier and the fuzzy C-means (FCM) clustering algorithm. While the former is used to generate a spectral-based classification map, the latter is adopted to provide an ensemble of clustering maps. To reduce the computation complexity, the most representative spectral channels identified by the Markov Fisher Selector (MFS) algorithm are used during the clustering process. Then, these maps are successively labeled via a pairwise relabeling procedure with respect to the SVM-based classification map using voting rules. To generate the final classification result, we propose to aggregate the obtained set of spectro-spatial maps through two different fusion methods based on voting rules and Markov Random Field (MRF) theory.

This paper proposes an interactive change detection method in multitemporal remote sensing images. The user needs to input markers related to change and no-change classes in the Difference image. Then this information is used by a support vector machine classifier to generate a spectral-change map. Then two different solutions based on Markov Random Field or Level-Set methods are used to incorporate the spatial contextual information in the decision process. While the Markov Random Field method is region driven, the level-set method exploits both region and contour for performing the segmentation task. Experiments conducted on two real remote-sensing images confirm the promising capabilities of the proposed method.

This paper proposes a novel semisupervised regression framework for estimating chlorophyll concentrations in subsurface waters from remotely sensed imagery. This framework integrates multiobjective optimization and Gaussian processes (GPs) for boosting the accuracy of the estimation process when conditioned by limited labeled-sample availability. To this end, the labeled samples are exploited in conjunction with unlabeled ones (available at zero cost from the image under analysis) for learning the regression model. The estimation of the target of these unlabeled samples is handled by the simultaneous optimization of two different criteria expressing the generalization capabilities of the GP estimator. The first is the empirical risk quantified in terms of the mean square error measure, and the second is the log marginal likelihood, which merges two terms expressing the model complexity and the data fit capability, respectively. In order to alleviate the computational burden and, possibly, to improve the estimation process accuracy, two different selection strategies of unlabeled samples are compared to the simple random-sampling procedure. They are based on the estimated variance provided by the GP estimator and the differential entropy measure, respectively. Experimental results obtained on simulated and real data sets are reported and discussed.

In this paper, we face the problem of collecting training samples for regression problems under an active learning perspective. In particular, we propose various active learning strategies specifically developed for regression approaches based on Gaussian processes (GPs) and support vector machines (SVMs). For GP regression, the first two strategies are based on the idea of adding samples that are dissimilar from the current training samples in terms of covariance measure, while the third one uses a pool of regressors in order to select the samples with the greater disagreements between the different regressors. Finally, the last strategy exploits an intrinsic GP regression outcome to pick up the most difficult and hence interesting samples to label. For SVM regression, the method based on the pool of regressors and two additional strategies based on the selection of the samples distant from the current support vectors in the kernel-induced feature space are proposed. The experimental results obtained on simulated and real data sets show that the proposed strategies exhibit a good capability to select samples that are significant for the regression process, thus opening the way to the active learning approach for remote-sensing regression problems.

In this paper, a new feature named heartbeat shape (HBS) is proposed for ECG-based biometrics. HBS is computed from the morphology of segmented heartbeats. Computation of the feature involves three basic steps: 1) resampling and normalization of a heartbeat; 2) reduction of matching error; and 3) shift invariant transformation. In order to construct both gallery and probe templates, a few consecutive heartbeats which could be captured in a reasonably short period of time are required. Thus, the identification and verification methods become efficient. We have tested the proposed feature independently on two publicly available databases with 76 and 26 subjects, respectively, for identification and verification. The second database contains several subjects having clinically proven cardiac irregularities (atrial premature contraction arrhythmia). Experiments on these two databases yielded high identification accuracy (98% and 99.85%, respectively) and low verification equal error rate (1.88% and 0.38%, respectively). These results were obtained by using templates constructed from five consecutive heartbeats only. This feature compresses the original ECG signal significantly to be useful for efficient communication and access of information in telecardiology scenarios.

This paper present a novel ensemble method for clustering very high spatial resolution (VHR) images that is composed of four main steps. Firstly, because of the important role of the spatial component in VHR imagery, a set of morphological features are extracted from the original image using many openings and closings with increasing structural element sizes. Secondly, we construct the ensemble by running the k-means algorithm several times with different initializations. In order to increase the diversity, different subsets of features are randomly selected at each time. Third, an optimal relabeling of the ensemble with respect to a representative partition is made via a pairwise relabeling procedure. Finally, the relabeled maps are fused with a Markov Random Field (MRF) method. The Experimental results obtained on two real VHR images acquired by the sensors IKONOS-2 and GeoEye-1 over urban areas confirmed the promising capabilities of the proposed approach.

In this paper, a geometry-based image retrieval system is developed for multi-object images. We model both shape and topology of image objects using a structured representation called curvature tree (CT). The hierarchy of the CT reflects the inclusion relationships between the image objects. To facilitate shape-based matching, triangle-area representation (TAR) of each object is stored at the corresponding node in the CT. The similarity between two multi-object images is measured based on the maximum similarity subtree isomorphism (MSSI) between their CTs. For this purpose, we adopt a recursive algorithm to solve the MSSI problem and a very effective dynamic programming algorithm to measure the similarity between the attributed nodes. Our matching scheme agrees with many recent findings in psychology about the human perception of multi-object images. Experiments on a database of 13500 real and synthesized medical images and the MPEG-7 CE-1 database of 1400 shape images have shown the effectiveness of the proposed method.

In this paper, a new 2D shape multiscale triangle-area representation (MTAR) is proposed. This representation utilizes a simple geometric principle, the area of a triangle, in obtaining a robust and efficient shape representation. The use of the wavelet transform for decomposing the boundary of the shapes improves the efficiency and robustness of the representation. The MTAR is more robust to the affine transformation, less affected by noise, and more selective than similar methods, e.g., the curvature scale-space CSS. Two tests, using MPEG-7 CE-shape-1 database, show that MTAR achieves better performance than the CSS under affine transformation and in the general shape retrieval.