Search

In recent days, the major concern for diabetic patients is foot ulcers. According to the survey, among 15 people among 100 are suffering from this foot ulcer. The wound or ulcer found which is found in diabetic patients consumes more time to heal, also required more conscious treatment. Foot ulcers may lead to deleterious danger condition and also may be the cause for loss of limb. By understanding this grim condition, this paper proposes Fractional-Order Darwinian Particle Swarm Optimization (FO-DPSO) technique for analyzing foot ulcer 2D color images. This paper deals with standard image processing, i.e. efficient segmentation using FO-DPSO algorithm and extracting textural features using Gray Level Co-occurrence Matrix (GLCM) technique. The whole effort projected results as accuracy of 91.2%, sensitivity of 100% and specificity as 96.7% for Naïve Bayes classifier and accuracy of 91.2%, sensitivity of 100% and sensitivity of 79.6% for Hoeffding tree classifier. [ABSTRACT FROM AUTHOR]

As an infrastructure of biochemical laboratories, EP tube label plays a significant role in information extraction to meet the limitations of computing power in offline devices and solve the problem that the EP tube label cannot be accurately identified before identification because the label belongs to multi-angle random placement. This paper proposes a light-weight neural network YOLOv4-tiny-ECA to position tubes and a tilt correction method based on Hough transform. First, the EP tube rack is roughly positioned based on the diffuse filling algorithm combined with digital morphological corrosion, and then the EP tubes in the rack are precisely positioned using the light-weight YOLO target detection algorithm combined with the attention mechanism. Next, the baseline is added to the label as the basis for determining the tilt angle. For the valid target, the baseline is extracted using the Hough transform and the tilt angle is calculated by vector fork multiplication. Finally, baseline is removed using image processing algorithm for better recognition results. Our results show that the light-weight YOLO algorithm reduces the network parameters by 56% and computation by 55% while keeping the accuracy rate largely unchanged, the offline positioning tilt correction method can achieve 98.8% accuracy and 0.076 s processing speed for a single test tube on average, which meets the real-time requirement. [ABSTRACT FROM AUTHOR]

Face recognition (FR) is a hotspot in pattern recognition and image processing for its wide applications in real life. One of the most challenging problems in FR is single sample face recognition (SSFR). In this paper, we proposed a novel algorithm based on nonnegative sparse representation, collaborative presentation, and probabilistic graph estimation to address SSFR. The proposed algorithm is named as Nonnegative Sparse Probabilistic Estimation (NNSPE). To extract the variation information from the generic training set, we first select some neighbor samples from the generic training set for each sample in the gallery set and the generic training set can be partitioned into some reference subsets. To make more meaningful reconstruction, the proposed method adopts nonnegative sparse representation to reconstruct training samples, and according to the reconstruction coefficients, NNSPE computes the probabilistic label estimation for the samples of the generic training set. Then, for a given test sample, collaborative representation (CR) is used to acquire an adaptive variation subset. Finally, the NNSPE classifies the test sample with the adaptive variation subset and probabilistic label estimation. The experiments on the AR and PIE verify the effectiveness of the proposed method both in recognition rates and time cost. [ABSTRACT FROM AUTHOR]

Modified Gram–Schmidt (MGS) algorithm is one of the most-known forms of QR decomposition (QRD) algorithms. It has been used in many signal and image processing applications to solve least square problem and linear equations or to invert matrices. However, QRD is well-thought-out as a computationally expensive technique, and its sequential implementation fails to meet the requirements of many real-time applications. In this paper, we suggest a new parallel version of MGS algorithm that uses VLIW (Very Long Instruction Word) resources in an efficient way to get more performance. The presented parallel MGS is based on compact VLIW kernels that have been designed for each algorithm step taking into account architectural and algorithmic constraints. Based on instruction scheduling and software pipelining techniques, the proposed kernels exploit efficiently data, instruction and loop levels parallelism. Additionally, cache memory properties were used efficiently to enhance parallel memory access and to avoid cache misses. The robustness, accuracy and rapidity of the introduced parallel MGS implementation on VLIW enhance significantly the performance of systems under severe rea-time and low power constraints. Experimental results show great improvements over the optimized vendor QRD implementation and the state of art. [ABSTRACT FROM AUTHOR]

In recent years, with the growth of China's economy and the development of the automobile manufacturing industry, the number of various vehicles has continuously increased, and the incidence of traffic accidents has also increased. Especially in traffic blind areas, right-turning areas of vehicles, etc., traffic accidents such as vehicle collisions are extremely easy to occur, which poses a serious threat to people's lives and property, and is extremely harmful. Therefore, related research on collision detection of people and vehicles has been traffic-safe and has received extensive attention from field researchers. At present, the research on human-vehicle collision detection is to detect human-vehicle collision accidents by tracking the track of vehicles and pedestrians, but there are problems such as poor tracking effect, low accuracy of collision discrimination and complex algorithms. Aiming at these problems, this paper studies the human-vehicle collision detection algorithm based on image processing. Through the image processing of traffic monitoring video, the vehicle and pedestrian contour information is extracted. Based on this, a mathematical model for collision detection is constructed to realize human-vehicle collision detection. The results show that the proposed method can effectively distinguish the collision between pedestrians and vehicles, and the algorithm for image processing is simpler than the traditional tracking algorithm, and the time is shorter. The results show that the image-based collision detection algorithm based on image processing can effectively and quickly identify the traffic accidents in which people and vehicles collide, and then can issue alarm signals in time, shortening the accident processing time and reducing the accident time. The possibility of a secondary accident has a high practicability in the detection of traffic accidents in which people and vehicles collide. [ABSTRACT FROM AUTHOR]

This paper presents the modification of a previously developed algorithm using fractional order calculus and its implementation on mobile-embedded devices such as smartphones. The system performs enhancement on three categories of images such as those exhibiting uneven illumination, faded features/colors and hazy appearance. The key contributions include the simplified scheme for illumination correction, contrast enhancement and de-hazing using fractional derivative-based spatial filter kernels. These are achieved without resorting to logarithmic image processing, histogram-based statistics and complex de-hazing techniques employed by conventional algorithms. The simplified structure enables ease of implementation of the algorithm on mobile devices as an image processing application. Results indicate that the fractional order version of the algorithm yields good results relative to the integer order version and other algorithms from the literature. [ABSTRACT FROM AUTHOR]

This paper presents a novel method for video-based face recognition (VFR) based on M-estimator and image set collaborative representation. Since a video is essentially an image set, the VFR problem can be cast as a special case of the image set-based face recognition (FR) problem. To measure the distance between the query image set and the gallery image set, we develop an M-estimator-based image set collaborative representation (MISCR) model. To implement MISCR, we devise an efficient half-quadratic-based optimization algorithm to tackle the complicated optimization problem. We also establish the convergence property of the devised algorithm. Our other contribution is to propose an MISCR-based classifier for the general image set classification problem, including VFR as a special case. The experiments using real-world benchmark databases demonstrate the efficacy and robustness of the proposed method for VFR. [ABSTRACT FROM AUTHOR]

The recognition rate of SIFT algorithm in single hand vein database has been as high as 99.5%. But with the development of Internet-plus technology, the demand for distributed systems becomes more and more significant. However, the problem of picture quality caused by cross-device makes the intraclass variations larger. For example, when gathering the dorsal hand vein images, subtle changes in relative distance and orientation among the imaging camera, the illumination LED arrays and the different location of users' hand, as well as shielding by the external housing box from ambient light sources and so on, these will make large difference to one person's hand images. So, including the contrast, the lightness, the shifting, the angle of rotation, the size and so on, these differences make it possible to use some traditional methods to recognize dorsal hand vein with a low recognition rate of less than 50%. Therefore, based on the traditional SIFT, this paper optimized the scale factor , extreme searching neighborhood structure and matching threshold . It can be seen that the cross-device hand vein feature is more robust, and the recognition rate reached an average of 88.5%. [ABSTRACT FROM AUTHOR]

The multi-task learning (MTL) methods consider learning a problem together with other related problems simultaneously. The major challenge of MTL is how to selectively screen the shared information. The information of each task must be related to the others, but when sharing information between two unrelated tasks it degenerates the performance of both tasks. To ensure the related problems are related to the main task is the most important point in MTL. In this paper, we will design a novel algorithm to calculate the degrees of relationship among tasks by using a semantical space of features in each task and then build semantical tree to achieve better learning performance. We propose an MTL method under this algorithm which achieves good experimental performance. Our experiments are taken on both image classification and video action recognition, compared with the state-of-the-art MTL methods. Our method proposes good performance in the four public datasets. [ABSTRACT FROM AUTHOR]

Image enhancement processing is a very important operation during image preprocessing. Compared with to enhancc the overall contrast level of image, enhancing the local contrast of image can improve the level of such contrast directly as well as the quality and effect of image enhancement. In this paper, the gray prediction model is applied to the process of enhancing image local contrast, so as to measure the change range of image local contrast and adaptively adjust the scale of enhancing image local contrast. The simulation results show that, in addition to enhancing the contrast of gray level on the edge of image, the proposed algorithm can inhibit roughened nonedge region and improve the quality of local enhancement processing, which create a more favorable condition for the further image edge detection. [ABSTRACT FROM AUTHOR]

Region of interest (ROI) is the most important part of an image that expresses the effective content of the image. Extracting regions of interest from images accurately and efficiently can reduce computational complexity and is essential for image analysis and understanding. In order to achieve the automatic extraction of regions of interest and obtain more accurate regions of interest, this paper proposes Optimized Automatic Seeded Region Growing (OASRG) algorithm. The algorithm uses the affinity propagation (AP) clustering algorithm to extract the seeds automatically, and optimizes the traditional region growing algorithm by regrowing strategy to obtain the regions of interest where target objects are contained. Experimental results show that our algorithm can automatically locate seeds and produce results as good as traditional region growing with seeds selected manually. Furthermore, the precision is improved and the extraction effect is better after the optimization with regrowing strategy. [ABSTRACT FROM AUTHOR]

Full rank principal component analysis (FR-PCA) is a special form of principal component analysis (PCA) which retains all nonzero components of PCA. Generally speaking, it is hard to estimate how the accuracy of a classifier will change after data are compressed by PCA. However, this paper reveals an interesting fact that the transformation by FR-PCA does not change the accuracy of many well-known classification algorithms. It predicates that people can safely use FR-PCA as a preprocessing tool to compress high-dimensional data without deteriorating the accuracies of these classifiers. The main contribution of the paper is that it theoretically proves that the transformation by FR-PCA does not change accuracies of the k nearest neighbor, the minimum distance, support vector machine, large margin linear projection, and maximum scatter difference classifiers. In addition, through extensive experimental studies conducted on several benchmark face image databases, this paper demonstrates that FR-PCA can greatly promote the efficiencies of above-mentioned five classification algorithms in appearance-based face recognition. [ABSTRACT FROM AUTHOR]

Self-organizing feature maps (SOFM) can learn both the distribution and topology of the input vectors they are trained on. According to this characteristic, we construct neural networks with a family of self-organizing feature maps to cluster the input data space. The proposed algorithm in this paper defines a novel similarity measure, topological similarity, and employs some new concepts, such as SOFM family, UsageFactor. The clustering algorithm handles the clusters with arbitrary shapes and avoid the limitations of the conventional clustering algorithms. We conclude our paper by several experiments with synthetic and standard data set of different characteristics, which show good performance of the proposed algorithm. [ABSTRACT FROM AUTHOR]

This paper focuses on image filtering using weighted median (WM) filters, a nonlinear filter class taking advantages of the robust order-statistic theory and capability to adapt a filter behavior for a variety of statistics related to the desired signals and the noise distributions. The main contribution of the paper is the analysis of the four WM optimization schemes, namely genetic WM optimization, non-adaptive WM optimization algorithm and adaptive WM filtering utilizing the linear and the sigmoidal approximation of the sign function. The analysis is done by extensive simulations, in which several features such as noise reduction, edge preservation, error estimation and dependence of error criteria on the degree of the impulse noise corruption, are examined. [ABSTRACT FROM AUTHOR]

This paper presents a dynamical solution of camera registration problem for on-road navigation applications via a 3D-2D parameterized model matching algorithm. The traditional camera'fs three dimensional (3D) position and pose estimation algorithms have always employed fixed and known-structure models as well as the depth information to obtain the 3D-2D correlations, which is however unavailable for on-road navigation applications since there are no fixed models in the general road scene. With the constraints of road structure and on-road navigation features, this paper presents a 2D digital road-based road shape modeling algorithm. Dynamically generated multi-lane road shape models are used to match real road scenes to estimate the camera 3D position and pose data. Our algorithms have successfully simplified the 3D-2D correlation problem to the 2D-2D road model matching on the projective image. The algorithms proposed in this paper are validated with the experimental results of real road tests under different conditions and types of road. [ABSTRACT FROM AUTHOR]

Accurate segmentation of human brain image is an essential step for clinical study of magnetic resonance imaging (MRI) images. However, vagueness and other ambiguity present between the brain tissues boundaries can lead to improper segmentation. Possibilistic fuzzy c-means (PFCM) algorithm is the hybridization of fuzzy c-means (FCM) and possibilistic c-means (PCM) algorithms which overcomes the problem of noise in the FCM algorithm and coincident clusters problem in the PCM algorithm. A major challenge posed in the PFCM algorithm for segmentation of ill-defined MRI image with noise is to take into account the ambiguity in the final localization of the feature vectors due to lack of qualitative information. This may lead to improper assignment of membership (typicality) value to their desired cluster. In this paper, we have proposed the possibilistic intuitionistic fuzzy c-means (PIFCM) algorithm for Atanassov's intuitionistic fuzzy sets (A-IFS) which includes the advantages of the PCM, FCM algorithms and A-IFS. Real and simulated MRI brain images are segmented to show the superiority of the proposed PIFCM algorithm. The experimental results demonstrate that the proposed algorithm yields better result. [ABSTRACT FROM AUTHOR]

A strong assumption to derive generalization guarantees in the standard PAC framework is that training (or source) data and test (or target) data are drawn according to the same distribution. Because of the presence of possibly outdated data in the training set, or the use of biased collections, this assumption is often violated in real-world applications leading to different source and target distributions. To go around this problem, a new research area known as Domain Adaptation (DA) has recently been introduced giving rise to many adaptation algorithms and theoretical results in the form of generalization bounds. This paper deals with self-labeling DA whose goal is to iteratively incorporate semi-labeled target data in the learning set to progressively adapt the classifier from the source to the target domain. The contribution of this work is three-fold: First, we provide the minimum and necessary theoretical conditions for a self-labeling DA algorithm to perform an actual domain adaptation. Second, following these theoretical recommendations, we design a new iterative DA algorithm, called GESIDA, able to deal with structured data. This algorithm makes use of the new theory of learning with (ε,γ,τ)-good similarity functions introduced by Balcan et al., which does not require the use of a valid kernel to learn well and allows us to induce sparse models. Finally, we apply our algorithm on a structured image classification task and show that self-labeling domain adaptation is a new original way to deal with scaling and rotation problems. [ABSTRACT FROM AUTHOR]

The main goal of this present paper is to develop color detection, and counting algorithm for tangerine flowers under natural lighting conditions to estimate better yield of tangerine from orchards, and each tree picture was taken from four sides. As a result, total of 1340 subimages of tangerine flowers were detected by the newly introduced algorithm from a sample of 21 tangerine trees during blooming season. A Gaussian filter was used to reduce noise and illumination adjustment as much as possible for better clarity to identify exactly the tangerine flowers. The proposed algorithm gives accurate output of tangerine flower detection by including partially/semipartially occluded tangerine flowers and its clusters. Finally, the output of yield estimation reveals that about 10% of all total tangerine flowers turned out to be tangerine. [ABSTRACT FROM AUTHOR]

The paper sets forth an improved edge-directed image interpolation algorithm with low time complexity. The algorithm partitions images into homogeneous and edge areas by setting the preset threshold value based on the local structure characteristics. Specified algorithms are assigned to interpolate each classified areas respectively. The proposed method implements strategy in three steps to interpolate after setting the preset threshold value. In this way, it can achieve the goals of real-time interpolation and good subjective quality. Furthermore, the interpolated images have much more explicit edge regions and better visual effects using our proposed method than that of using other algorithms. Experimental results demonstrate that the method proposed by the authors is high-performed in image interpolation. [ABSTRACT FROM AUTHOR]

Image inpainting is an active research area in the image processing field. The essential idea of image inpainting algorithm is to fill in the missing or damaged regions with available information from their surroundings. In this paper, we propose two image inpainting models based on the variational method. We show that the diffusion performance of the proposed models for image inpainting are superior to classical total variation (TV) inpainting model according to the physical characteristics in local coordinates. To show the effective performance of the proposed models, we apply it to restoring of scratched photos, text removal and even removal of entire objects from images. [ABSTRACT FROM AUTHOR]

The task of face recognition has been actively researched in recent years because of its many applications in various domains. This paper presents a robust face recognition system using curvelet-based two-dimensional principle component analysis (2D PCA) to address the problem of human face recognition from still images. 2D PCA has advantages over PCA in evaluating the covariance matrix accurately and time complexity. Inspired by the attractive attributes of curvelets in catching the edge singularities with very few coefficients in a non-adaptive manner, we introduce the scheme of decomposing images into curvelet subbands and applying 2D PCA to create a representative feature set. Experiments were designed with different implementations of each module using standard testing database. We experimented with changing the illumination normalization procedure; comparing the baseline PCA-based method with the proposed scheme; studying effects on algorithm performance of k-nearest neighbor (kNN) classifier and Support Vector Machine (SVM) classifier in the classification process; also we experimented with different databases such as FERET, etc. High accuracy rate were achieved by the proposed scheme through a comparative study. [ABSTRACT FROM AUTHOR]

The increased demand for clustering objects of unlabeled data into similarity group lies in determining a number of clusters. In addition, the performance of the cluster should be analyzed to provide the precise clustering of objects. Available clustering algorithm depends on the number of clusters C to search with threshold. The proposed method of this paper is Enhanced Visual Assessment of Cluster Tendency, which robotically identifies the number of object groups or clusters in unlabeled datasets. The proposed algorithm relies on visual assessment of cluster tendency (VAT) that intermingles Euclidean, Mahalanobis distance measures, and common image processing techniques. Enhanced VAT produces a binary image, which can be visually assessed for the cluster tendency. However, VAT becomes disrupting for huge datasets. Enhanced VAT reduces the amount of computation and performs dissimilarities with different measures of metrics that are used for an effective visual evaluation process. Validation of our algorithm is performed on several UCI datasets and HIV real world datasets. [ABSTRACT FROM AUTHOR]

In this paper, a novel image fusion algorithm based on framelet transform is presented. The core idea is to decompose all the images to be fused into low and high-frequency bands using framelet transform. For fusion, two different selection strategies are developed and used for low and high-frequency bands. The first strategy is adaptive weighted average based on local energy and is applied to fuse the low-frequency bands. In order to fuse high-frequency bands, a new strategy is developed based on texture while exploiting the human visual system characteristics, which can preserve more details in source images and further improve the quality of fused image. Experimental results demonstrate the efficiency and better performance than existing image fusion methods both in visual inspection and objective evaluation criteria. [ABSTRACT FROM AUTHOR]

This paper presents a development of the post-compression rate-distortion optimization (PCRD-opt) algorithm in JPEG2000 used for optimal truncation (OT) rate control. The proposed treatment of PCRD-opt differs from the treatment given in the JPEG2000 standard and what is given in a number of publications. The proposed algorithm is implemented in a complete JPEG2000 compression engine as well as the algorithm published in the JPEG2000 standard. The proposed algorithm gives a substantial performance gain, outperforming the implementation given in the standard by 0.25-1 dB in PSNR on average, demonstrating an improvement from the method for PCRD-opt given in the standard. The proposed algorithm is also compared to the JPEG2000 reference implementation, JasPer, and the popular Kakadu JPEG2000 compressor. The proposed algorithm provides equivalent performance results to both JasPer and Kakadu, indicating that the proposed PCRD-opt treatment provides correct OT of JPEG2000 compressed imagery. [ABSTRACT FROM AUTHOR]

In this paper, we describe an algorithm for computing biorthogonal compactly supported dyadic wavelets related to the Walsh functions on the positive half-line ℝ+. It is noted that a similar technique can be applied in very general situations, e.g., in the case of Cantor and Vilenkin groups. Using the feedback-based approach, some numerical experiments comparing orthogonal and biorthogonal dyadic wavelets with the Haar, Daubechies, and biorthogonal 9/7 wavelets are prepared. [ABSTRACT FROM AUTHOR]

This paper presents a run- and label-equivalence-based one-and-a-half-scan algorithm for labeling connected components in a binary image. Major differences between our algorithm and conventional label-equivalence-based algorithms are: (1) all conventional label-equivalence-based algorithms scan all pixels in the given image at least twice, whereas our algorithm scans background pixels once and object pixels twice; (2) all conventional label-equivalence-based algorithms assign a provisional label to each object pixel in the first scan and relabel the pixel in the later scan(s), whereas our algorithm assigns a provisional label to each run in the first scan, and after resolving label equivalences between runs, by using the recorded run data, it assigns each object pixel a final label directly. That is, in our algorithm, relabeling of object pixels is not necessary any more. Experimental results demonstrated that our algorithm is highly efficient on images with many long runs and/or a small number of object pixels. Moreover, our algorithm is directly applicable to run-length-encoded images, and we can obtain contours of connected components efficiently. [ABSTRACT FROM AUTHOR]

In this paper, we design a cellular automaton and a discrete-time cellular neural network (DTCNN) using nonlinear passive memristors. They can perform a number of applications, such as logical operations, image processing operations, complex behaviors, higher brain functions, RSA algorithm, etc. By modifying the characteristics of nonlinear memristors, the memristor DTCNN can perform almost all functions of memristor cellular automaton. Furthermore, it can perform more than one function at the same time, that is, it allows multitasking. [ABSTRACT FROM AUTHOR]

Iris localization is a key component of practical iris recognition system. Previous algorithms show good localization performances for iris images captured in the ideal conditions. However, in practice, the quality of iris image is greatly influenced by luminance, eyelashes, hair or glasses frame, which will cause mislocalization. In order to improve the robustness of iris localization, this paper proposes a new localization algorithm based on the radial symmetry transform, in which the radial symmetry characteristic of the pupil is utilized to realize iris localization. Experimental results show that the proposed algorithm can efficiently avoid the interference of luminance and other bad conditions, and realize robust precise localization in a real-time system. [ABSTRACT FROM AUTHOR]

This paper describes an innovative aerial images segmentation algorithm. The algorithm is based upon the knowledge of image multiscale geometric analysis using contourlet transform, which can extract the image's intrinsic geometrical structure efficiently. The contourlet transform is introduced to represent the most distinguished and the rotation invariant features of the image. A modified Mumford–Shah model is applied to segment the aerial image by a multifeature level set evolution. To avoid possible local minima in the level set evolution, we adjust the weighting coefficients of the multiscale features in different evolution periods, i.e. the global features have bigger weighting coefficients at the beginning stages which roughly define the shape of the contour, then bigger weighting coefficients are assigned to the detailed features for segmenting the precise shape. When the algorithm is applied to segment the aerial images with several classes, satisfied experimental results are achieved by the proposed method. [ABSTRACT FROM AUTHOR]

In a classification problem, quite often the dimension of the measurement vector is large. Some of these measurements may not be important for separating the classes. Removal of these measurement variables not only reduces the computational cost but also leads to better understanding of class separability. There are some methods in the existing literature for reducing the dimensionality of a classification problem without losing much of the separability information. However, these dimension reduction procedures usually work well for linear classifiers. In the case where competing classes are not linearly separable, one has to look for ideal "features" which could be some transformations of one or more measurements. In this paper, we make an attempt to tackle both, the problems of dimension reduction and feature extraction, by considering a projection pursuit regression model. The single hidden layer perceptron model and some other popular models can be viewed as special cases of this model. An iterative algorithm based on backfitting is proposed to select the features dynamically, and cross-validation method is used to select the ideal number of features. We carry out an extensive simulation study to show the effectiveness of this fully automatic method. [ABSTRACT FROM AUTHOR]

We investigate the development of a new analytic approach for 3D PET reconstruction by extension of the chord-based approach for X-ray cone-beam tomography (XCBT). The extension is made possible by recognizing a connection that allows one to reformat 3D PET data into effective cone-beam data so that the chord-based approach can be applied. An important advantage of the new approach is that it can work with general PET system geometries, not limited to the conventional circular geometry. In this paper, we consider a rectangular PET system consisting of four flat-panel detectors. We derive exact analytic reconstruction algorithms for this system and evaluate their performances in numerical studies. Our preliminary results indicate that the derived algorithms can yield accurate reconstructions when applied to noiseless PET data that are generated by assuming the ideal projection model. The algorithms are also observed to respond reasonably well to data noise. Currently, our algorithms do not utilize the entire 3D PET data. Potential modifications to the algorithms for enabling the inclusion of the entire 3D PET data for reconstruction, as well as the theoretical significances and potential practical advantages of this new analytic reconstruction approach, are discussed. [ABSTRACT FROM AUTHOR]

Multiscale image analysis has been used successfully in a number of applications to segment image features according to their relative scale. In this paper, we present a new framework for the hierarchical segmentation of gray level image. The proposed scheme comprises a nonlinear scale-space and morphological gradient watersheds. Our aim is to produce a meaningful hierarchy among the objects in the image. The scale-space is based on morphological anisotropic diffusion that uses reconstruction morphological operators. Furthermore, we introduce the method to reconstruct morphological operators and the principle of the dynamics of contours in scale-space that combines scale and contrast information. The performance of the proposed segmentation scheme is presented via experimental results obtained with a wide range of image including natural scenes. [ABSTRACT FROM AUTHOR]

This paper presents an algorithm for the allocation of on-chip FPGA Block RAMs for the implementation of Real-Time Video Processing Systems. The effectiveness of the algorithm is shown through the implementation of realistic image processing systems. The algorithm, which is based on a heuristic, seeks the most cost-effective way of allocating memory objects to the FPGA Block RAMs. The experimental results obtained, show that this algorithm generates results which are close to the theoretical optimum for most design cases. [ABSTRACT FROM AUTHOR]

This paper proposes a new method for the exact reconstruction of gray-scale images from projections. The image projections construct an accumulator array, which is used afterwards to reconstruct the original grayscale image by applying the proposed decomposition algorithm. The proposed method determines the number of projections and the number of rays in each projection that are required in order to achieve the reconstruction. These two parameters also define the dimensions of the accumulator array. Using an accumulator array with proper dimensions ensures that there is always a unique characteristic sample for each pixel, which is used during the reconstruction process to extract the pixel's grayscale value. During the reconstruction phase, the sinusoidal contribution of each pixel is removed from the accumulator array. At the end of the decomposition process the accumulator array becomes empty and the original image is exactly reconstructed. The experimental results confirm the robustness and efficiency of the proposed method. [ABSTRACT FROM AUTHOR]

A new feature based image mosaic method is presented in this paper. Our main contribution is an improved RANSAC algorithm based on the modified median flow filter to find the inliers and the homography between the images. This algorithm overcomes the limit of local feature detection and thus improves the stability of homography calculation. Except for the RANSAC algorithm, PCA-SIFT is used to detect features because it is more compact, more robust and faster than the standard SIFT. The priority search is also used to match the feature points in a faster way than BBF search. Experiments show that our method is robust for image mosaic. [ABSTRACT FROM AUTHOR]

In this paper, a face recognition system based on the fusion of two well-known appearance-based algorithms, namely Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA), is proposed. Fusion is performed at the decision-level, that is, the outputs of the individual face recognition algorithms are combined. Two main benefits of such fusion are shown. First, the reduction of the dependence on the environmental conditions with respect to the best individual recognizer. Secondly, the overall performance improvement over the best individual recognizer. To this end, fusion is investigated under different environmental conditions, namely, "ideal" conditions, characterized by a very limited variability of environmental parameters, and "real" conditions with large variability of lighting and face expressions. [ABSTRACT FROM AUTHOR]

In this paper we present a new algorithm to track an organ in a sequence of medical images in order to achieve a 3D reconstruction. The automatic method that we propose allows the tracking of the external contour of the anatomical organ in all the sequence from one contour initialized by the user on the first image. The required operations for our tracking method are the region-based active contours segmentation. The objects localization with dynamic prediction of displacements is based on the level-set functions and the definition of the region of interest for the robust local estimation of the image model. An application of this method is the 3D reconstruction of abdominal aorta. [ABSTRACT FROM AUTHOR]

In cases of densely occluded urban scenes, it is useful to determine the visibility of scenes, since only small parts of the scene are visible from a given cell. In this paper, we introduce a new visibility preprocessing method that efficiently computes potentially visible objects for volumetric cells. The proposed method deals with general 3D polygonal models and invisible objects jointly blocked by multiple occluders. The proposed approach decomposes volume visibility into a set of point visibilities, and then computes point visibility using hardware-visibility queries. We carry out experiments on various large-scale scenes, and show the performance of our algorithm. Our performance analysis approach estimates the exact solution of volume visibility. From differences between the estimated solution and the proposed algorithms solution, we show that our algorithm seeks a tight overestimate of the potentially visible set (PVS). [ABSTRACT FROM AUTHOR]

This paper presents a new algorithm for detection and compensation of backlight images. The proposed technique attacks the weakness of the conventional backlight image processing methods such as over-saturation, losing contrast and so on. The proposed algorithm consists of two operation phases: detection and compensation phases. In the detection phase, we use the spatial position characteristic and histogram of backlight image to obtain two image indices, which can determine the backlight degree of an image. Fuzzy logic is then used to integrate these two indices into a final backlight index determining the final backlight degree of an image precisely. Second, in the compensation phase, to solve the over-saturation problem that exists usually in conventional image compensation methods, we propose the adaptive compensation-curve scheme to compensate and enhance the brightness of backlight images. The luminance of a backlight image is adjusted according to the compensation curve, which is adapted dynamically according to the backlight degree indicated by the backlight index estimated in the detection phase. The performance of the proposed technique is tested on 100 backlight images covering various kinds of backlight conditions and degrees. The experimental and comparison results clearly show the superiority of the proposed technique. [ABSTRACT FROM AUTHOR]

Content-based face image retrieval is concerned with computer retrieval of face images (of a given subject) based on the geometric or statistical features automatically derived from these images. It is well known that color spaces provide powerful information for image indexing and retrieval by means of color invariants, color histogram, color texture, etc. This paper assesses comparatively the performance of content-based face image retrieval in different color spaces using a standard algorithm, the Principal Component Analysis (PCA), which has become a popular algorithm in the face recognition community. In particular, we comparatively assess 12 color spaces (RGB, HSV, YUV, YCbCr, XYZ, YIQ, L*a*b*, U*V*W*, L*u*v*, I1I2I3, HSI, and rgb) by evaluating seven color configurations for every single color space. A color configuration is defined by an individual or a combination of color component images. Take the RGB color space as an example, possible color configurations are R, G, B, RG, RB, GB and RGB. Experimental results using 600 FERET color images corresponding to 200 subjects and 456 FRGC (Face Recognition Grand Challenge) color images of 152 subjects show that some color configurations, such as YV in the YUV color space and YI in the YIQ color space, help improve face retrieval performance. [ABSTRACT FROM AUTHOR]

The current paper proposes a font classification method for document images that uses non-negative matrix factorization (NMF), that is able to learn part-based representations of objects. The basic idea of the proposed method is based on the fact that the characteristics of each font are derived from parts of individual characters in each font rather than holistic textures. Spatial localities, parts composing of font images, are automatically extracted using NMF and, then, used as features representing each font. Using hierarchical clustering algorithm, these feature sets are generalized for font classification, resulting in the prototype templates construction. In both the prototype construction and font classification, earth mover's distance (EMD) is used as the distance metric, which is more suitable for the NMF feature space than Cosine or Euclidean distance. In the experimental results, the distribution of features and the appropriateness of the features specifying each font are investigated, and the results are compared with a related algorithm: principal component analysis (PCA). The proposed method is expected to improve the performance of optical character recognition (OCR), document indexing and retrieval systems, when such systems adopt a font classifier as a preprocessor. [ABSTRACT FROM AUTHOR]

In this paper we propose a new algorithm for the skeletonization of handwritten characters. Unlike traditional skeletonization algorithms that relay only on the configuration of a binary image pixel in deciding whether it is deletable or not, Natural Skeletonization (NS) integrates the gray-level information in this process. The underlying principle here, which stems from the elongated properties of the handwritten characters, is that medial pixels of a handwritten stroke are "naturally" darker than its side pixels. NS consists of three steps: (1) the decomposition step; (2) the thinning step; (3) the reconstruction step. The integration of gray-level information is facilitated by the iterative binarization at equally spaced thresholds, which highlights positional differences between the medial and side pixels of a stroke. The advantage of our approach over existing methods is demonstrated by its ability to prevent the "flooding water" and to prevent the boundary noise from developing extraneous branches. One important aspect of the approach is that it relaxes the skeletonization's dependence on the quality and shape of initial binary pattern. The experimental results indicate that the proposed algorithm substantially improves the skeletonization quality compared to experiments with traditional skeletonization methods. [ABSTRACT FROM AUTHOR]

Image restoration problems can naturally be cast as constrained convex programming problems in which the constraints arise from a priori information and the observation of signals physically related to the image to be recovered. In this paper, the focus is placed on the construction of constraints based on wavelet representations. Using a mix of statistical and convex-analytical tools, we propose a general framework to construct wavelet-based constraints. The resulting optimization problem is then solved with a block-iterative parallel algorithm which offers great flexibility in terms of implementation. Numerical results illustrate an application of the proposed framework. [ABSTRACT FROM AUTHOR]

In this paper we propose a technique that reconstructs high-resolution images with improved super-resolution algorithms, based on Irani and Peleg iterative method, and employs our suggested initial interpolation, robust image registration, automatic image selection and image enhancement post-processing. When the target of reconstruction is a moving object with respect to a stationary camera, high-resolution images can still be reconstructed, whereas previous systems only work well when we move the camera and the displacement of the whole scene is the same. [ABSTRACT FROM AUTHOR]

In this paper, we present a new approach to geometrical modeling which allows the user to easily characterize and control the shape defined to a closed surface. We will focus on dealing with the shape's topological, morphological and geometrical properties separately. To do this, we have based our work on the following observations concerning surfaces defined by control-points, and implicit surfaces with skeleton. They both provide complementary approaches to the surface's deformation, and both have specific advantages and limits. We thus attempted to conceive a model which integrates the local and geometrical characterization induced by the control points, as well as the representation of the morphology given by the skeleton. Knowing that the lattice of control points is close to the surface and that the skeleton is centered in the related shape, we thought of a 3-layer model. The transition layer separates the local geometrical considerations from those linked to the global morphology. We apply our model to shape design in order to modify an object in an interactive and ergonomic way, as well as to reconstruction which allows better shape understanding. To do so, we present the algorithms related to these processes. [ABSTRACT FROM AUTHOR]

This paper presents a new topological structure for use in the context of hierarchical radiosity combined with discontinuity meshing. This is most useful for a new strategy adopted for subdividing the elements of a scene consisting of convex polygons. The subdivision is done in a local optimization manner keeping the aspect ratios of produced polygons low. The generated meshes give high visual accuracy. [ABSTRACT FROM AUTHOR]

Since the BSP tree algorithm was introduced, many extended or applied algorithms for the original BSP tree algorithm have been reported. Most of the previous work dealt with polygons that are components of polyhedra. If a scene consists of many polyhedra and they are allowed to move, the management cost of a BSP tree becomes expensive and the size of the tree becomes large. This paper presents an object-oriented BSP tree algorithm that can more efficiently deal with a large number of moving polyhedra. [ABSTRACT FROM AUTHOR]

The parallel implementation of image processing algorithms implies an important choice of data distribution strategy. In order to handle the specific constraints associated with images, data distribution must take into account not only the locality of the data and its geometrical regularity but also the possible irregular computation costs associated with different image elements. A widely studied field to tackle this problem is the family of methods related to rectilinear partitioning. We introduce two fully parallel heuristics that compute suboptimal partitions, with a better complexity than the best known algorithms that compute optimal partitions. In this paper, we compare our heuristics to an optimal partitioning, both in terms of execution time and accuracy of the partition. We give some theoretical bounds on the quality of these heuristics that are corroborated by results of random numerical experiments and real applications. [ABSTRACT FROM AUTHOR]

Accurate motion estimation algorithms are based on a number of invariant properties that can be inferred from the motion. A large number of calibration algorithms have been proposed over the last two decades mainly based on analytic, perspective, or epipolar geometries. Extending Chasles' screw motion concept to the estimation of motion parameters in computer vision, we have presented an analysis of geometric properties of image correspondence vectors synthesized into a single coordinate frame and developed calibration algorithms using both simulated and real range image data.[sup 15,16] In this paper, we extend that work by defining the relevant geometric properties of image correspondence vectors from the point of view of invariants and by developing two calibration algorithms using the Monte Carlo method and median filtering. The algorithms are applied to real and synthetic image data corrupted by noise and outliers. Experimental results demonstrate that the median filter based algorithm is generally more robust and accurate than the Monte Carlo based algorithm and that the geometric analysis of invariant properties of correspondence vectors is a useful framework to motion parameter estimation. [ABSTRACT FROM AUTHOR]

This paper presents a gray-scale skeletonization algorithm based on the gray weighted distance transformation (GWDT). The proposed algorithm is conceptually simple and could be used to process nonuniformly distributed gray-scale images. The algorithm can detect the hollows on the gray-scale image, a feature that is often ignored in other skeletonization algorithms, and improves the quality of the skeleton. [ABSTRACT FROM AUTHOR]