Convolutional neural networks (CNNs) are widely used in medical image analysis, especially for breast ultrasound (BUS) image segmentation. Automatically encoding deep features is one of the most important reasons leading to the success of deep convolutional neural networks. There are a lot of studies on obtaining better convolutional features; how-ever, they do not discuss the higher-order information in the features. In this research, we propose a novel convolutional operator, a shape-adaptive convolutional operator, which can select pixels for calculating convolution rather than in the Euclidean space. The proposed operator is combined with the original convolutional operator to extract higher-order convolutional features. We conduct extensive experiments to evaluate the performance of the proposed operator for image segmentation using three datasets: two public BUS image datasets and one multi-category BUS image dataset. The proposed approach achieves state-of-the-art performance.

Fully convolutional network is a powerful tool for per-pixel semantic segmentation/detection. However, it is problematic when coping with crack detection using partially accurate ground truths (GTs): the network may easily converge to the status that treats all the pixels as background (BG) and still achieves a very good loss, named “All Black” phenomenon, due to the unavailability of accurate GTs and the data imbalance. To tackle this problem, we propose crack-patch-only (CPO) supervised generative adversarial learning for end-to-end training, which forces the network to always produce crack-GT images while reserves both crack and BG-image translation abilities by feeding a larger-size crack image into an asymmetric U-shape generator to overcome the “All Black” issue. The proposed approach is validated using four crack datasets; and achieves state-of-the-art performance comparing with that of the recently published works in efficiency and accuracy.

Deep learning approaches have achieved impressive results in breast ultrasound (BUS) image segmentation. However, these methods did not solve uncertainty and noise in BUS images well. Meanwhile, they did not involve the context information of BUS images, either. To address this issue, we present a novel deep learning structure for BUS image semantic segmentation by analyzing the uncertainty using a pyramid fuzzy block and generating a novel feature based on connectedness. There are three major contributions in this paper: (1) the structure of pyramid fuzzy block; (2) a novel membership function based on multi-convolution layers; and (3) a novel context feature based on connectedness. The proposed methods are applied to two datasets: a BUS image benchmark with two categories (background and tumor) and a five-category BUS image dataset with fat layer, mammary layer, muscle layer, background, and tumor. The proposed method achieves the best results on both datasets compared with eight state-of-the-art deep learning-based approaches.

Breast cancer investigation is of great significance, and developing tumor detection methodologies is a critical need. However, it is challenging for breast cancer detection using breast ultrasound (BUS) images due to the complicated breast structure and poor quality of the images. This paper proposes a novel tumor saliency estimation (TSE) model guided by enriched breast anatomy knowledge to localize the tumor. First, the breast anatomy layers are generated by a deep neural network. Then we refine the layers by integrating a non-semantic breast anatomy model to solve the problems of incomplete mammary layers. Meanwhile, a new background map generation method weighted by the semantic probability and spatial distance is proposed to improve the performance. The experiment demonstrates that the proposed method with the new background map outperforms four state-of-the-art TSE models with an increasing 10% of Fmeasure on the public BUS dataset.

Computer-aided diagnosis (CAD) can help doctors in diagnosing breast cancer. Breast ultrasound (BUS) imaging is harmless, effective, portable, and is the most popular modality for breast cancer detection/diagnosis. Many researchers work on improving the performance of CAD systems. However, there are two main shortcomings: (1) Most of the existing methods are based on prerequisites that there is one and only one tumor in the image. (2) The results depend on the datasets, i.e., an algorithm using different datasets may obtain different performances. It implies that the performance of traditional methods is dataset-dependent. In this paper, we propose an effective approach: (1) using information extended images to train a fully convolutional network (FCN) to semantically segment BUS image into 3 categories: mammary layer, tumor, and background; and (2) applying layer structure information - the breast cancers are located inside the mammary layer - to the conditional random field (CRF) for conducting breast cancer segmentation and making the segmentation result more accurate. The proposed method is evaluated utilizing BUS images of 325 cases, and the result is the best comparing with that of the existing methods by achieving true positive rate 92.80%, false positive rate 9%, and Intersection over Union 82.11%. The proposed approach has solved the above mentioned two shortcomings of the existing methods.

Automatic tumor segmentation of breast ultrasound (BUS) image is quite challenging due to the complicated anatomic structure of breast and poor image quality. Most tumor segmentation approaches achieve good performance on BUS images collected in controlled settings; however, the performance degrades greatly with BUS images from different sources. Tumor saliency estimation (TSE) has attracted increasing attention to solve the problem by modeling radiologists' attention mechanism. In this paper, we propose a novel hybrid framework for TSE, which integrates both high-level domain-knowledge and robust low-level saliency assumptions and can overcome drawbacks caused by direct mapping in traditional TSE approaches. The new framework integrated the Neutro-Connectedness (NC) map, the adaptive-center, the correlation and the layer structure-based weighted map. The experimental results demonstrate that the proposed approach outperforms state-of-the-art TSE methods.

This paper proposes individualized cleaning for diverse imbalanced data sets. Existing techniques for data cleaning have difficulties with rare cases and outliers in minority class, especially, in highly unbalanced data. The drawback leads incomplete and imprecise examples to removal. In order to enhance the robustness and perform thorough data cleaning, we propose a weighted edited nearest neighbor (WENN), which detects and removes noisy examples from both classes intelligently. It considers individual characteristics of each imbalanced data, involving global class imbalance and local distribution. The main idea of the proposed method is to carefully put more focus on the majority class than the minority class during data cleaning. Extensive experiments over synthetic and real data clearly validate the superiority of our approach against other data cleaning methods.

Interactive image segmentation is a popular and challenging task. User interactions, e.g., setting seeds or specifying bounding box, play a critical role in determining the performance of all interactive segmentation approaches. However, most methods focus on improving segmentation performance by integrating higher level information; and to the best of our knowledge, no work has been done to improve the effectiveness of user interactions yet. In this paper, we propose the effective interactive segmentation (EISeg) method based on Neutro-Connectedness, which provides user with objective visual clues for guiding interactions. The experiments demonstrate that the proposed EISeg method guides interaction effectively, and achieves better results with much less user interaction (averagely 2.3 foreground and 1.8 background seeds/image) than state-of-the-art approaches.

Visual saliency estimation based on optimization models is gaining increasing popularity recently. In this paper, we formulate saliency estimation as a quadratic program (QP) problem based on robust hypotheses. First, we propose an adaptive center-based bias hypothesis to replace the most common image center-based center-bias. It calculates the weighted center by utilizing local contrast which is much more robust when the objects are far away from the image center. Second, we model smoothness term on saliency statistics of each color. It forces the pixels with similar colors to have similar saliency statistics. The proposed smoothness term is more robust than the smoothness term based on region dissimilarity when the image has complicated background or low contrast. The primal-dual interior point method is applied to optimize the proposed QP in polynomial time. Extensive experiments demonstrate that the proposed method can outperform 10 state-of-the-art methods on three public benchmark datasets.

Interactive image segmentation is a challenging task and receives increasing attention recently; however, two major drawbacks exist in interactive segmentation approaches. First, the segmentation performance of region of interest (ROI)-based methods is sensitive to the initial ROI: different ROIs may produce results with great difference. Second, most seed-based methods need intense interactions, and are not applicable in many cases. In this paper, we generalize the neutro-connectedness (NC) to be independent of top-down priors of objects and to model image topology with indeterminacy measurement on image regions, propose a novel method for determining object and background regions, which is applied to exclude isolated background regions and enforce label consistency, and put forward a hybrid interactive segmentation method, NC Cut (NC-Cut), which can overcome the above two problems by utilizing both pixelwise appearance information and region-based NC properties. We evaluate the proposed NC-Cut by employing two image data sets (265 images), and demonstrate that the proposed approach outperforms the state-of-the-art interactive image segmentation methods (Grabcut, MILCut, One-Cut, MGCmaxsum, and pPBC).

Transesophageal echocardiography (TEE) is widely used to detect left atrium (LA)/left atrial appendage (LAA) thrombi. In this paper, the local binary pattern variance (LBPV) features are extracted from region of interest (ROI). And the dynamic features are formed by using the information of its neighbor frames in the sequence. The sequence is viewed as a bag, and the ROIs in the sequence are considered as the instances. Multiple-instance learning (MIL) method is employed to solve the LAA thrombi detection. The experimental results show that the proposed method can achieve better performance than that by using other methods.

Tumor detection is the key issue of computer-aided diagnosis (CAD) systems using breast ultrasound (BUS) images. However, accurately and automatically locating the suspicious lesions in BUS images is still a very challenging job. In this paper, we propose a saliency model to describe the radiologists' visual (RV) attention. The main contributions of the paper are: (1) The saliency model is built based on biological hypotheses instead of using inflexible assumptions which are more robust, adaptive and objective. (2) Background based attention cue is also proposed. Before, the background information was either ignored or only used for excluding non-target areas. However, we find that the background information is very useful for establishing the anatomy constrains. The proposed method is evaluated using real breast ultrasound images and the result demonstrates a significantly improved performance comparing with that of the state-of-the-art methods.

Breast tumor segmentation is an important step of breast ultrasound (BUS) computer-aided diagnosis (CAD) systems. However, because of the poor quality of BUS images, it's a challenging task to develop a robust and accurate segmentation algorithm. Much progress has been made on applying fuzzy connectedness to segment objects from low quality images. However, the fuzzy connectedness method still has difficulty in segmenting objects with weak boundaries. The neutrosophic set theory has been widely applied to image processing, and shows more strengths in modeling uncertainty and indeterminacy. In this paper, two new concepts of neutrosophic subset and neutrosophic connectedness (neutro-connectedness) were defined to generalize the fuzzy subset and fuzzy connectedness. The newly proposed neutro-connectedness models the inherent uncertainty and indeterminacy of the spatial topological properties of the image. The proposed method is applied to a breast ultrasound database with 131 cases, and its performance is evaluated by similarity ratio (SIR), false positive ratio (FPR) and average Hausdroff error (AHE). In comparison with the fuzzy connectedness segmentation method, the proposed method is more accurate and robust in segmenting tumors in BUS images.

In this study, the authors propose a novel and effective short track speed skating tracking system. Aimed at several challenging tracking problems of short track skating: long‐time occlusion and complex group situations, size variations, similar or identical uniforms, fast motion speed, quick orientation changes etc.; a novel fuzzy model is proposed to initialise contours of skaters even they wear the same kind of uniform. Then, a novel approach for multiple object tracking is developed to track skaters reliably. The experimental results demonstrate that the proposed system can solve the above challenging problems very effectively. The information provided by the proposed system, including trajectories, velocity analysis and two‐dimensional reconstruction animations, is valuable to broadcasters, athletes and coaches alike. The proposed tracking algorithm can obtain better results than that by the other eight state‐of‐the‐art trackers in short track speed skating tracking.

Human pose tracking is among the most popular hotspots in the field of computer vision. In this paper, we propose a novel game theory based method for tracking two dimensional articulated human poses in monocular video sequences. A new probability scheme of game theory is introduced into human pose tracking to find optimal solutions of human poses. The possible limb positions are modeled as strategies of agents who play normal form game with adjacent agents. Likelihood measurements and distance constraints are applied to calculate the payoffs of each of the strategies. Finally, the Nash equilibria are found for each normal form game and the human poses are estimated based on them. In the experiments, the effectiveness and efficiency of the proposed algorithm is fully exhibited.

To improve the diagnostic accuracy of breast ultrasound classification, a novel computer-aided diagnosis (CAD) system based on B-Mode and color Doppler flow imaging is proposed. Several new features are modeled and extracted from the static images and color Doppler image sequences to study blood flow characteristics. Moreover, we proposed a novel classifier ensemble strategy for obtaining the benefit of mutual compensation of classifiers with different characteristics. Experimental results demonstrate that the proposed CAD system can improve the true-positive and decrease the false positive detection rate, which is useful for reducing the unnecessary biopsy and death rate.

Over-enhancement is the major problem of image contrast enhancement algorithms which could induce the loss of edges, change the important texture, impair the fine details, and make the images look unnatural. Over-enhancement has traditionally been assessed by visual inspection due to the fact that there is no an effective objective criterion for over-enhancement yet. In this paper, we propose a novel approach for the detection of over-enhancement. The main contributions of the paper are as follows. (1) The reasons for generating over-enhancement are investigated and analyzed deeply. (2) An objective criterion for detecting over-enhancement is proposed. The experimental results demonstrate that the proposed approach can locate the over enhanced areas accurately and effectively, and provide a quantitative criterion to assess the over-enhancement levels well. The proposed approach will be useful for dynamically monitoring the quality of the enhanced image, and optimizing the parameter settings of the contrast enhancement algorithms.

In recent years, most action recognition researches focus on isolated action analysis for short videos, but ignore the issue of continuous action recognition for a long video sequence in real time. This paper proposes a novel approach for human action recognition in a video sequence with whatever length, which, unlike previous works,requires no annotations and no pre-temporal-segmentations.Based on the bag of words representation and the probabilistic Latent Semantic Analysis (pLSA) model, there cognition process goes frame by frame and the decision updates from time to time. Experimental results show that this approach is effective to recognize both isolated actions and continuous actions no matter how long a video sequence is. This is very useful for real time applications like video surveillance. Besides, we also test our approach for real time temporal video segmentation and real time keyframe extraction.

This paper discusses the task of human action detection in crowded videos. First, we propose a novel mask based shape matching method for action recognition. Our method does not need human detection or segmentation, and it can be used in both clean and crowed backgrounds. Next, shape and flow based features are combined due to their complementary nature. For each action, a binary sequence is used as the template for both shape and flow matching. For a testing sequence and a template sequence, dynamic time warping technique is first applied for time alignment, then shape and flow matching distances are computed between matched frames. We test our algorithm on the CMU dataset and achieve an encouraging performance.

Human motion capture typically requires synchronization hardware and specialized cameras, which makes the system expensive and technically complex. Instead, in this paper, we propose a novel approach for markerless motion capture with multiple unsynchronized cameras. Cameras synchronization is achieved using sharp illumination changes produced while recording the videos. To estimate poses with the presence of sharp illumination changes, we also propose a pose estimation method based on a bilayer Gaussian Mixture Model (GMM) and graph-cut, which can handle sharp illumination changes. And we demonstrate our video synchronization and markerless motion capture methods by the experiments on real human motion videos.

Because of ultrasound images' low quality, fully automated segmentation of breast ultrasound (BUS) image is a challenging task. In this paper, a novel segmentation method for BUS images which is fully automatic without any human intervention is proposed. By incorporating empirical knowledge and characteristics of breast structure, a ROI is generated automatically. Then two newly proposed lesion features: phase in max-energy orientation (PMO) and radial distance (RD), combined with the commonly used intensity and texture feature, are extracted. Then the new feature set is used to distinguish lesion region from the background by a trained ANN. The proposed segmentation method was tested on a BUS database composed of 60 cases. We use the manually outlined lesions by an experienced radiologist as the golden standard and evaluated the performance by both area error metrics and boundary error metrics. Quantitative results demonstrate the efficiency of the proposed fully automatic BUS segmentation method.

Two major problems of ultrasound imaging are low-contrast and speckle noise. Traditionally, before speckle reduction, an enhancement algorithm is employed to improve the quality of the image. However, the noise is enhanced as well. To overcome this drawback, we introduce a novel fuzzy anisotropic diffusion approach for speckle reduction and contrast enhancement. Maximum fuzzy entropy principle is used to map the image from space domain to fuzzy domain. Then, fractional-order partial differential equation is used to remove noise and to preserve edges. Finally, the subpixel operator is utilized as a tuning parameter to achieve the optimal result. We test the proposed method on synthetic and real breast ultrasound (BUS) images. The experimental results demonstrate that the proposed method can preserve the edges and enhance the structural details of the BUS images well while removing speckle noise.

Region growing is a frequently used segmentation method for medical ultrasound images processing. The first step of region growing is selecting the seed point which is inside the breast lesion. Most of the region growing methods require manually selecting the seed point which needs human interaction. To make the segmentation completely automatic, we propose a new automatic seed point selecting method for region growing algorithm. The method is validated on our database with 105 ultrasound images with breast masses and it is compared with other automatic seed point selecting method on the same database. Quantitative experiment results show that our proposed method can successfully find the proper seed points for 95.2% of the US images in the database which is much more robust than other automatic seed point selection methods.

Vehicle detection and classification are invaluable in many transportation systems, such as traffic flow analysis, abnormal events detection, automotive driver assistant systems and so on. Many vehicle detection systems have been proposed so far. However, there are still some problems not well solved yet. One of the crucial problems is how to eliminate shadows cast by moving vehicles. In this paper, we propose a novel method based on combination of HMM and background subtraction. A public database of shadow: http://cvrr.ucsd.edu/aton/shadow is employed to test the performance of the new algorithm. Result shows that the proposed method is much better than other old methods.

In this paper, we present an effective, flexible and completely automated camera calibration approach using only one pair of concentric circles. This approach utilizes the characteristics of concentric circles' tangent lines to locate the center of these circles, and finds the geometric constraints for calibration based on the orthogonality formed by a point on the circle and the two intersected points of the circle with the line through the center of the circle. The entire process requires no conic equation fitting and no metric measurement of the test pattern, which is very flexible to implement.

This paper presents a novel fuzzy neural network (FNN) approach to detect malignant mass lesions on mammograms. The mammograms were obtained from the digital database for screening mammography (DDSM) at the University of South Florida. Six-hundred-seventy regions of interest (ROIs) were extracted from 100 mammograms and are randomly divided into two groups: training and testing sets. Entropy, uniformity, contrast, and maximum co-occurrence matrix elements are calculated at sizes of 256/spl times/256 and 768/spl times/768, respectively. The differences of these features (feature differences) from these two image sets with the above mentioned sizes are computed for each feature, and they are discriminant in differentiating between malignant masses and normal tissues regardless of lesion shape, size, and subtlety. After training, the FNN can correctly detect all malignant masses on mammograms in the testing group. The true positive fraction (TPF) is 0.92 when the number of false positives (FP) is 1.33 per mammogram; and 1.0 when the FP is 2.15 per mammogram.

Breast cancer is one of the leading causes of female mortality. Since the causes are unknown, breast cancer cannot be prevented. Microcalcifications and masses are the earliest signs of breast carcinomas and their detection is one of the key issues for breast cancer control. It is difficult for radiologists to provide accurate and uniform evaluations of the enormous number of mammograms generated in widespread screening. Computer-aided detection of microcalcifications and masses is an important and challenging task. The paper presents a novel approach for detecting microcalcification clusters (MCCs). First, mammograms are normalized. Then, fuzzy set theory and the fuzzy entropy principle are used to fuzzify the mammograms and the fuzzified images are enhanced. Finally, scale-space and Laplacian-of-a-Gaussian filter techniques are used to determine the sizes and locations of microcalcifications. A free-response operating characteristic (FROC) curve is used to evaluate the performance. The major advantage of the proposed system is its ability to detect microcalcifications even in mammograms of very dense breasts. A data set of 40 mammograms (Nijmegen database) containing 105 clusters of microcalcifications was studied. Microcalcifications can be accurately and efficiently detected using the proposed approach.

This paper presents a thresholding approach by performing fuzzy partition on a two-dimensional (2-D) histogram based on fuzzy relation and maximum fuzzy entropy principle. The experiments with various gray level and color images have demonstrated that the proposed approach outperforms the 2-D nonfuzzy approach and the one dimensional (1-D) fuzzy partition approach.

In this paper, a novel hierarchical approach to color image segmentation is studied. We extend the general idea of a histogram to the homogeneity domain. In the first phase of the segmentation, uniform regions are identified via multilevel thresholding on a homogeneity histogram. While we process the homogeneity histogram, both local and global information is taken into consideration. This is particularly helpful in taking care of small objects and local variation of color images. An efficient peak-finding algorithm is employed to identify the most significant peaks of the histogram. In the second phase, we perform histogram analysis on the color feature hue for each uniform region obtained in the first phase. We successfully remove about 99.7% singularity off the original images by redefining the hue values for the unstable points according to the local information. After the hierarchical segmentation is performed, a region merging process is employed to avoid over-segmentation. CIE(L*a*b*) color space is used to measure the color difference. Experimental results have demonstrated the effectiveness and superiority of the proposed method after an extensive set of color images was tested.

The method of moments is one of the most powerful techniques for image analysis. However, real-time applications of this method have been prohibited due to the computational intensity in calculating the moments. This paper presents a novel configurable hardware accelerator for expediting the moment computation. The fundamental building block of the proposed accelerator is a custom-designed floating-point moment processing element (MPE). Running at 75 MHz, the MPE can provide a 12X speedup over a 166 MHz TMS320C6701 digital signal processor. On top of this, a linear performance boost can be obtained by connecting up to eight MPEs into a one-dimensional (1-D) array.

Thresholding is an important topic of image processing. This paper proposes a thresholding approach by performing a fuzzy partition on a 2D histogram of the image. The 2D fuzzy partition method and membership assignment are based on fuzzy relation of two fuzzy sets, which is characterized by a set of parameters (a, b, c). The proposed approach has been tested on various images, and the results have demonstrated that the proposed 2D fuzzy approach outperforms the 2D nonfuzzy approach and the 1D fuzzy approach.

Commonly used techniques for contrast enhancement fall into two categories: (1) indirect methods and (2) direct methods. In this paper, we propose a novel, fuzzy, adaptive, direct contrast enhancement method based on the fuzzy entropy principle and fuzzy set theory. The proposed approach has much better adaptability and can determine the enhancement parameters automatically according to the nature of the image. The experimental results demonstrate that the proposed algorithm is very effective in contrast enhancement as well as in preventing over-enhancement.

The identification of images irrespective of their location, size and orientation is one of the important tasks in pattern analysis. The use of global moment features has been one of the most popular techniques for this purpose. We present a simple and effective method for gray-level image representation and identification which utilizes fuzzy radial moments of image segments (local moments) as features as opposed to global features. A multilayer perceptron neural network is employed for classification. Fuzzy entropy measure is applied to optimize the parameters of the membership function. The technique does not require translation, scaling or rotation of the image. Furthermore, it is suitable for parallel implementation which is an advantage for real-time applications. The classification capability and robustness of the technique are demonstrated by experiments on scaled, rotated and noisy gray-level images of uppercase and lowercase characters and digits of English alphabet, as well as the images of a set of tools. The proposed approach can handle rotation, scale and translation invariance, noise and fuzziness simultaneously.

The spatial ambiguity among pixels has inherent vagueness rather than randomness, therefore, the conventional methods might not work well. We propose fuzzy homogeneity vectors to handle the greyness and spatial uncertainties among pixels, and to perform multilevel thresholding. The experimental results prove that the proposed approach works better than the histogram-based algorithms.

Breast cancer continues to be a significant public health problem in the United States. Approximately, 182,000 new cases of breast cancer are diagnosed and 46,000 women die of breast cancer each year. Even more disturbing is the fact that one out of eight women in the United States will develop breast cancer at some point during her lifetime. Since the cause of breast cancer remains unknown, primary prevention becomes impossible. Computer-aided mammography is an important and challenging task in automated diagnosis. It has great potential over traditional interpretation of film-screen mammography in terms of efficiency and accuracy. Microcalcifications are the earliest sign of breast carcinomas and their detection is one of the key issues for breast cancer control. In this study, a novel approach to microcalcification detection based on fuzzy logic technique is presented. Microcalcifications are first enhanced based on their brightness and nonuniformity. Then, the irrelevant breast structures are excluded by a curve detector. Finally, microcalcifications are located using an iterative threshold selection method. The shapes of microcalcifications are reconstructed and the isolated pixels are removed by employing the mathematical morphology technique. The essential idea of the proposed approach is to apply a fuzzified image of a mammogram to locate the suspicious regions and to interact the fuzzified image with the original image to preserve fidelity. The major advantage of the proposed method is its ability to detect microcalcifications even in very dense breast mammograms. A series of clinical mammograms are employed to test the proposed algorithm and the performance is evaluated by the free-response receiver operating characteristic curve. The experiments aptly show that the microcalcifications can be accurately detected even in very dense mammograms using the proposed approach.

Previously developed Special Sensor Microwave/Imager (SSM/I) snow classification algorithms have limitations and do not work properly for terrain where forests overlie snow cover. In this study, the authors applied unsupervised cluster analysis to separate SSM/I brightness temperature (T/sub B/) observations into groups. Six desired snow conditions were identified from the clusters; both sparse- and medium-vegetated region scenes were assessed. Typical SSM/I T/sub B/ signatures for each snow condition were determined by calculating the mean T/sub B/ value of observations for each channel in the corresponding cluster. A single-hidden-layer artificial neural network (ANN) classifier was designed to learn the SSM/I T/sub B/ signatures. An error backpropagation training algorithm was applied to train the ANN. After training, a winner-takes-all method was used to determine the snow condition. Results showed that the ANN classifier was able to outline not only the snow extent but also the geographical distribution of snow conditions. This study confirms the potential of using cluster means in ANN supervised learning, and suggests a nonlinear retrieval method for inferring land-surface snow conditions from SSM/I data over varied terrain.

The Special Sensor Microwave/Imager (SSM/I) radiometer is practical in monitoring snow conditions for its sensitive response to the changes in snow properties. A single-hidden-layer artificial neural network (ANN) was employed to accomplish this remote sensing task, with radiometric observations of brightness temperatures (Tbs) as input data, to derive information about snow. Error backpropagation learning was applied to train the ANN. After learning the mapping of SSM/I Tbs to snow classes, the ANN approach showed a significant promise for identifying mountainous snow conditions. Error rates were 3% for snow-free, 5% for dry snow, 9% for wet snow, and 0% for refrozen snow, respectively. This study indicates the potential of ANN supervised learning for the inference of snow conditions from SSM/I observations. Further improvement on the application of ANN for large-scale snow monitoring can be expected by using more training data derived from both plains and mountain regions.

Proposes a novel texture analysis technique based on fuzzy cooccurrence matrix concept, and uses it to deal with early and accurate breast cancer diagnosis by analyzing the microscope-slide biopsy images. A newly proposed feature extraction algorithm is employed to extract the features from the digitized images, then the features are input to a multilayer back-propagation neural network to classify the images into three risk groups. Finally, a resultful comparison of breast cancer diagnosis between the conventional method and the proposed approach is conducted and the conclusion is reached that the proposed method is much superior to the existing methods. The proposed method may have wide applications in the areas of pattern recognition and image processing.

Shape recognition is an important research area in pattern recognition. It also has wide practical applications in many fields. An attribute grammar approach to shape recognition combines both the advantages of syntactic and statistical methods and makes shape recognition more accurate and efficient. However, the time complexity of a sequential shape recognition algorithm using attribute grammar is O(n3) where n is the length of an input string. When the problem size is very large it needs much more computing time, therefore a high speed parallel shape recognition is necessary to meet the demands of some real-time applications. This paper presents a parallel shape recognition algorithm and also discusses the algorithm partition problem as well as its implementation on a fixed-size VLSI architecture. The proposed algorithm has time complexity O(n3/k2) if using k×k processing elements. When k=n, its time complexity is O(n). The experiment has been conducted to verify the performance of the proposed algorithm. The correctness of the algorithm partition and the behavior of the proposed VLSI architecture have also been proved through the experiment. The results indicate that the proposed algorithm and the VLSI architecture could be very useful to imaging processing, pattern recognition and related areas, especially for real-time applications.

Identification of images irrespective of their location, size or orientation is one of the important tasks in pattern analysis. Use of global moment features has been one of the most popular techniques for this purpose. The authors present a simple and effective method for image representation and identification which utilizes local radial moments of segments of image as features as opposed to global features and a simple classifier such as the nearest-neighbor classifier. The technique does not require translation, scaling or rotation of the image itself. Furthermore, it is suitable for parallel implementation and hence is useful for real-time applications. The classification capability of the technique is demonstrated by experiments on scaled, rotated and noisy images of upper and lower case characters and digits of the English alphabet.

The feasible map approach (FMA) to certain motion planning problems in robotics is introduced. This approach is based on the use of a feasible map representation of a configuration space. When a feasible map is constructed, the topology of a configuration space is derived by shrink transformation. Path planning is done at two levels: first, to find a feasible path in a feasible map, and second, to transform the feasible path in the feasible map into the configuration space. When a feasible map is obtained, the feasible path can be obtained according to any starting and desired configurations, at once. A detailed FMA is given on a sphere world and the performance of the proposed algorithm is demonstrated by experiments. The results indicate that the FMA is efficient, useful and widely applicable.

The histogram of an image conveys information about the brightness and contrast of the image, and is used to manipulate these features. Histogram has many applications in image processing and may be needed at different processing stages. In this paper, we propose a parallel algorithm for computing the histogram of limited-width (such as gray-level) values. The essential parallelism and simplicity of the proposed algorithm make it easy to implement by using a VLSI array architecture. Each pixel only needs to perform addition and comparison, and communicate only with its immediate neighbor pixels during the entire computation period. The histograms for pre-load and in-load images can be computed using the proposed architecture. The time complexity for the proposed algorithm is O(N), comparing with O(N2) if using a uniprocessor, where N is the dimension of the image plane. The algorithm partition issue has also been studied.

In this paper, a novel parallel approach called VH2D (Vertical- Horizontal-2 Diagonals) method is proposed. In this method, projections of character images are made from four directions: vertical, horizontal, and two diagonals, which produce four subfeature vectors for each character. The four subfeature vectors are adjusted according to the character's center and combined into a complete feature vector. The feature dictionary consists of 3000 Chinese characters. The experiment has shown that the approach can result in extremely high accuracy of recognition. The techniques of pipelining and parallelism are applied in the proposed approach. The time complexity of the proposed algorithm is 0(N). A simple VLSI architecture composed of four linear arrays of processing elements for the VH2D approach is briefly presented.

This paper presents a fuzzy enhancement algorithm for image enhancement based on a fuzzy membership function and a contrast intensification transformation function using the average fuzzy membership grade with neighbors. Our algorithm has the following features: (1) fully employs the information of neighbors and utilizes the two-step nonlinear transformations, (2) reduces noise by using a smoothing operator in fuzzy singletons, and (3) keeps the edges intact.

Shape recognition has wide applications in many fields. An attribute grammar approach to shape recognition combines both advantages of syntactic and statistical methods and makes shape recognition more accurate and efficient. However, the time complexity of a sequential shape recognition algorithm using attribute grammar is O(n/sup 3/) where n is the length of an input string. The paper presents a parallel shape recognition algorithm and its implementation on a fixed-size VLSI architecture. The proposed algorithm has time complexity O(n/sup 3//k/sup 2/). Experiments have also been conducted to verify the performance of the proposed algorithm. The proposed algorithm and architecture could be very useful for image processing, pattern recognition and related areas.>

The size-orientation-invariance characteristic plays an important role in pattern recognition. It has many applications in computer vision, optical character recognition (OCR), office automation, electronic publication, graphics, etc. In this paper, a new method called transformation-ring-projection (TRP) is proposed to achieve this characteristic. In TRP, shape transformation technique is employed to center the pattern image and normalize its size; the ring-projection scheme is used to handle the orientation problem. An experiment was conducted to verify the proposed method in character recognition. The TRP algorithm requires only simple and regular operations, and provides the feasibility or VLSI implementation to speed up computation for real-time processing. A study on VLSI architecture with extensive parallel processing and pipelining capabilities for the proposed TRP algorithm is also presented.

An image transformation method that performs mapping and filling at the same time, while respecting the connectivity of the original image, is proposed. As a result, the transformations become more consistent and accurate. Its VLSI implementation can reduce the time complexity to O(N/sup 2/) using a uniprocessor, where N is the dimension of the image plane. The algorithms can handle all kinds of images including those of long narrow objects that present problems to other algorithms They also reduce the errors introduced by the order in which rotation and scaling are applied. Their application to gray level images is studied. A series of experiments has been conducted to verify the performance of the proposed algorithms.>

Human pulmonary circulation is studied by using a quasi-one-dimensional unsteady nonlinear fluid model. It is applied to 17 generations of blood vessels composed of the branching arterial, capillary, and venous distensible vessel segments which make up the complete pulmonary circulation. An idealized pressure-area relation is introduced describing the varying degrees of vessel collapse. The model gives satisfactory agreement with the experimental data: a dramatic pressure drop occurs in the arterioles and postcapillaries, and a negative transmural pressure is shown in the postcapillary and small venous segments. This model can also be used to study abnormal pulmonary circulation, such as arteriosclerosis, atherosclerosis, vasospasm, hypertension, etc.>

Comparing the hand-written symbol with the set of training symbols (called reference symbols), we can recognize the input hand-written symbol by computing the distances among the input symbol and the reference symbols in the training set. In this paper we propose a VLSI architecture based on the space-time domain expansion which can compute the symbol distance and also give the index-pairs which correspond to the warp function. The time complexity is O(max(m, n)) by using m × n processing elements array, where m is the length of the input symbol and n is the length of the reference symbol. With a uniprocessor the matching process will have the time complexity O(m × n). If there are p reference symbols, using the proposed architecture the recognition problem can be solved in time O(max(m,n,p)). With a uniprocessor the time complexity will be O(m × n × p). The algorithm partition problems are discussed. Verification of the proposed VLSI architecture is also given.

The space-time domain expansion method has recently been used to transform a computational task with a recursive formula into a VLSI architecture. In addition to its simplicity and completeness, an important advantage of this method is that it can easily solve the problem of partitioning an algorithm to fit a fixed size VLSI architecture. We propose a computational model and a partition rule which can be easily used to partition any recursive computation problem suited to the space-time domain expansion method so it can be solved on fixed-size VLSI architectures. Several examples, such as partitioned vector inner product, partitioned comparators in relational database management, partitioned matrix multiplications, and partitioned transitive closure computation, parallel recognition of general context-free languages, string matching and dynamic time-warp pattern-matching are used to illustrate the proposed method.

VLSI technology has recently received increasing attention due to its high performance and high reliability. Designing a VLSI structure systematically for a given task becomes a very important problem to many computer engineers. In this paper, we present a method to transform a recursive computation task into a VLSI structure systematically. The main advantages of this approach are its simplicity and completeness. Several examples, such as vector inner product, matrix multiplication, convolution, comparison operations in relational database and fast Fourier transformation (FFT), are given to demonstrate the transformation procedure. Finally, we apply the proposed method to hierarchical scene matching. Scene matching refers to the process of locating or matching a region of an image with a corresponding region of another view of the same image taken from a different viewing angle or at a different time. We first present a constant threshold estimation for hierarchical scene matching. The VLSI implementation of the hierarchical scene matching is then described in detail.