In this paper, based on second-order cross-partial derivative (CPD), we propose an efficient blind image deblurring algorithm for uniform blur. The proposed method consists of two stages. We first apply a novel blur kernel estimation method to quickly estimate the blur kernel. Then, we use the estimated kernel to perform non-blind deconvolution to restore the image. A key discovery of the proposed kernel estimation method is that the blur kernel information is usually embedded in the cross-partial-derivative (CPD) image of the blurred image. By exploiting this property, we propose a pipeline to extract a set of kernel candidates directly from the CPD image and then select the most suitable kernel as the estimated blur kernel. Since our kernel estimation method can obtain a fairly accurate blur kernel, we can achieve effective image restoration using a relatively simple Tikhonov regularization in the subsequent non-blind deconvolution process. To improve the quality of the restored image, we further adopt an efficient filtering technique to suppress periodic artifacts that may appear in the restored images. Experimental results demonstrate that our algorithm can efficiently restore high-quality sharp images on standard CPUs without relying on GPU acceleration or parallel computation. For blurred images of approximately $800\times 800$ resolution, the proposed method can complete image deblurring within 1 to 5 seconds, which is significantly faster than most state-of-the-art methods. Our MATLAB codes are available at https://github.com/e11tkcee06-a11y/CPD-Deblur.git.

In a multiagent competitive environment, it is important for an agent to detect the opponent's policy and adopt a suitable policy to exploit the opponent. Conventionally, most methods, e.g., Bayesian policy reuse (BPR) variants, assume that the opponent adopts a fixed policy or a randomly changing policy. In this article, we make a more realistic and reasonable assumption that the opponent may select its policy based on the previous observation. Here, we define the term “strategy” as the mapping from the previous observation to the opponent's selected policy, and we propose the Bayesian strategy inference (BSI) framework to infer the opponent's strategy. Furthermore, to deal with opponents who may randomly select their policies, the BSI framework is combined with an intraepisode policy tracking mechanism to construct the Bayesian strategy inference plus policy tracking (BSI-PT) algorithm. In our experiments, we design anExtended Batter versus Pitchergame (EBvPG) for the evaluation of the proposed BSI-PT framework. The experimental results demonstrate that BSI-PT obtains higher policy prediction accuracy and winning percentage than three other BPR variants against the opponents with a specific policy selection strategy, with a random selection strategy, or with a partially random strategy.

In a multi-agent competitive domain, the agent needs to anticipate the opponent’s behavior and select a suitable policy to exploit the opponent. In this work, based on the BPR (Bayesian Policy Reuse) framework, we further assume the opponent may determine its policy depending on its previous observation. To deal with opponents of this kind, we discuss three different approaches for the agent, including learning from scratch, reasoning from experience, and reasoning accompanied by learning. The “reasoning accompanied by learning” approach turns out to be the most favorable method, in which the agent executes an iterative process that alternates between “updating the belief of each pre-collected model” and “progressively learning the opponent’s policy selection pattern” based on the observed data. In our experiments, we simulate a simplified batter vs. pitcher game. The experimental results show that the “reasoning accompanied by learning” approach does receive a larger averaged utility value than the learn-from-scratch approach and the reason-from-experience approach.

The state-of-the-art models for semantic image segmentation usually contain a convolutional neural network (CNN) and a conditional random field (CRF). As a predictor, existing CNN techniques can generate a dense prediction result but may generate obvious boundary errors at the same time. As a refinement model, CRF improves the CNN outcomes by forcing the consistency of local labels. However, the use of CRF may cause fragmentation effect around object boundaries. In this paper, we propose the use of a so-called iterative contraction and merging (ICM) process to facilitate the semantic segmentation process. Guided by the high-level information from CNN, the ICM process is used as a tool to grow image segments in a bottom-up way and to produce more accurate outcomes in an iterative way. The ICM process can faithfully preserve the boundary information and maintain the consistency of local labels. Our experimental results demonstrate that the performance of the proposed approach is comparable to the state-of-the-art models but with more accurate boundaries.

In this paper, we propose a new framework for hierarchical image segmentation based on iterative contraction and merging. In the proposed framework, we treat the hierarchical image segmentation problem as a sequel of optimization problems, with each optimization process being realized by a contraction-and-merging process to identify and merge the most similar data pairs at the current resolution. At the beginning, we perform pixel-based contraction and merging to quickly combine image pixels into initial region-elements with visually indistinguishable intra-region color difference. After that, we iteratively perform region-based contraction and merging to group adjacent regions into larger ones to progressively form a segmentation dendrogram for hierarchical segmentation. Comparing with the state-of-the-art techniques, the proposed algorithm can not only produce high-quality segmentation results in a more efficient way, but also keep a lot of boundary details in the segmentation results.

In this paper, we present an unsupervised hierarchical image segmentation algorithm based on a split-and-merge scheme. In the split phase, we propose an efficient partition algorithm, called Just-Noticeable-Difference Bayesian Sequential Partitioning (JND-BSP), to partition image pixels into a few regions, within which the color variations are perceived to be smoothly changing without apparent color differences. In the merge phase, we propose a simple but effective merging criterion to sequentially construct a hierarchical structure that represents the relative similarity among these partitioned regions. Instead of generating a segmentation result with a fixed number of segments, the new algorithm produces an entire hierarchical representation of the given image in a single run. This hierarchical representation is informative and can be very useful for subsequent processing, like object recognition and scene analysis. To demonstrate the effectiveness and efficiency of our method, we compare our new segmentation algorithm with several existing algorithms. Experiment results show that our new algorithm can not only offers a more flexible way to segment images but also provides segmented results close to human's visual perception.

This paper presents a maximum a posteriori (MAP) framework to incorporate a spatial consistency prior model for depth reconstruction in the shape-from-focus (SFF) process. Existing SFF techniques, which reconstruct a dense 3-D depth from multifocus image frames, usually have poor performance over low-contrast regions and usually need a large number of frames to achieve satisfactory results. To overcome these problems, a new depth reconstruction process is proposed to estimate the depth values by solving an MAP estimation problem with the inclusion of a spatial consistency model. This consistency model assumes that within a local region, the depth value of each pixel can be roughly predicted by an affine transformation of the image features at that pixel. A local learning process is proposed to construct the consistency model directly from the multifocus image sequence. By adopting this model, the depth values can be inferred in a more robust way, especially over low-contrast regions. In addition, to improve the computational efficiency, a cell-based version of the MAP framework is proposed. Experimental results demonstrate the effective improvement in accuracy and robustness as compared with existing approaches over real and synthesized image data. In addition, experimental results also demonstrate that the proposed method can achieve quite impressive performance, even with only the use of a few image frames.

Automatically extracting foreground objects from a natural image remains a challenging task. This paper presents a learning-based hierarchical graph for unsupervised matting. The proposed hierarchical framework progressively condenses image data from pixels into cells, from cells into components, and finally from components into matting layers. First, in the proposed framework, a graph-based contraction process is proposed to condense image pixels into cells in order to reduce the computational loads in the subsequent processes. Cells are further mapped into matting components using spectral clustering over a learning based graph. The graph affinity is efficiently learnt from image patches of different resolutions and the inclusion of multiscale information can effectively improve the performance of spectral clustering. In the final stage of the hierarchical scheme, we propose a multilayer foreground estimation process to assemble matting components into a set of matting layers. Unlike conventional approaches, which typically address binary foreground/background partitioning, the proposed method provides a set of multilayer interpretations for unsupervised matting. Experimental results show that the proposed approach can generate more consistent and accurate results as compared with state-of-the-art techniques.

In this paper, we focus on recovering a 3-D depth map from a single image. Given an image of urban scene, we extract linear perspective information to establish the 3-D scene model. Unlike approaches which use only occlusion relationship between objects to estimate the relative depth of the image, we further combine the perspective geometry information with the occlusion relationship between objects. Besides, we propose the construction of depth gradient maps to represent the depth variation trend along the vertical and horizontal directions. The image is first partitioned into geometric components and initial depth gradient maps are generated based on the relative position between the vanishing point and the classified components. Incorporating main directions of vanishing lines and occlusion boundaries in the initial depth gradient maps, a refined depth map is obtained by using a CRF (conditional random field) model. We demonstrate that our approach can produce realistic relative depth maps for images of urban scenes.

In this paper, we propose a vacant parking space detection system that operates day and night. In the daytime, the major challenges of the system include dramatic lighting variations, shadow effect, inter-object occlusion, and perspective distortion. In the nighttime, the major challenges include insufficient illumination and complicated lighting conditions. To overcome these problems, we propose a plane-based method which adopts a structural 3-D parking lot model consisting of plentiful planar surfaces. The plane-based 3-D scene model plays a key part in handling inter-object occlusion and perspective distortion. On the other hand, to alleviate the interference of unpredictable lighting changes and shadows, we propose a plane-based classification process. Moreover, by introducing a Bayesian hierarchical framework to integrate the 3-D model with the plane-based classification process, we systematically infer the parking status. Last, to overcome the insufficient illumination in the nighttime, we also introduce a preprocessing step to enhance image quality. The experimental results show that the proposed framework can achieve robust detection of vacant parking spaces in both daytime and nighttime.

Global spatial coherence is an important criterion in the performance evaluation of many image applications, such as image segmentation, image enhancement, depth estimation, motion estimation, and many others. In this paper, we treat the recovery of spatial coherence as a Maximum-A-Posteriori (MAP) estimation problem, with a generalized spatial-coherence prior model based on Matting Laplacian (ML) matrix. Besides, to enhance computational efficiency, a cell-based Matting-Laplacian (CML) framework is further proposed. In our experiments, we demonstrate that the proposed approach can greatly improve the spatial coherence of the output results in variant applications, like the shape-from-focus process and the SIFT-flow refinement process.

While various kinds of local tone mapping approaches have been proposed for contrast enhancement, how to automatically recovering overly bright and/or overly dark regions in an image without introducing extra artifacts still remains a challenging problem. Conventional approaches usually apply a translation-invariant filter to decompose the contrast information of an image into a global component and a detailed component and then adjust the contrast components according to some preselected criteria. However, the use of translation-invariant filter makes it hard to adaptively decompose the contrast information based on local image contents. To overcome this problem, we derive a global optimization approach with the use of cell-based matting Laplacian matrix to obtain more accurate decomposition. Besides, for the adjustment of contrast component, we present a spatially varying gamma adjustment approach that can locally recover poorly exposed regions and properly enhance contrast detail. This translation-varying approach can successfully suppress the halo artifacts without the loss of image details.

In this paper, we focus on recovering a 3-D depth map from a single image via ground-vertical boundary analysis. First, we generate a ground map from the input image based on the spectral matting method, followed by a spatial geometric inference. After that, we derive the depth information for the ground-vertical boundaries. Unlike conventional approaches which generally use plane models to reconstruct a 3-D structure that fits the estimated boundaries, we infer a dense depth map by solving a Maximum-A-Posteriori (MAP) estimation problem. In this MAP problem, we use a generalized spatial-coherence prior model based on the Matting Laplacian (ML) matrix in order to provide a more robust solution for depth inference. We demonstrate that this approach can produce more pleasant depth maps for cluttered scenes.

In this paper, the main purpose is to locate, label, and correspond multiple targets with the capability of ghost suppression over a multicamera surveillance system. In practice, the challenges come from the unknown target number, the interocclusion among targets, and the ghost effect caused by geometric ambiguity. Instead of directly corresponding objects among different camera views, the proposed framework adopts a fusion-inference strategy. In the fusion stage, we formulate a posterior distribution to indicate the likelihood of having some moving targets at certain ground locations. Based on this distribution, a systematic approach is proposed to construct a rough scene model of the moving targets. In the inference stage, the scene model is inputted into a proposed Bayesian hierarchical detection framework, where the target labeling, target correspondence, and ghost removal are regarded as a unified optimization problem subject to 3-D scene priors, target priors, and foreground detection results. Moreover, some target priors, such as target height, target width, and the labeling results are iteratively refined based on an expectation-maximization (EM) mechanism to further boost system performance. Experiments over real videos verify that the proposed system can systematically determine the target number, efficiently label moving targets, precisely locate their 3-D locations, and effectively tackle the ghost problem.

In this paper, an efficient Bayesian framework is proposed for image contrast enhancement. Based on the image acquisition pipeline, we model the image enhancement problem as a maximum a posteriori (MAP) estimation problem, where the posteriori probability is formulated based on the local information of the given image. In our framework, we express the likelihood model as a local image structure preserving constraint, where the overall effect of the shutter speed and camera response function is approximated as a linear transformation. On the other hand, we design the prior model based on the observed image and some statistical property of natural images. With the proposed framework, we can effectively enhance the contrast of the image in a natural-looking way, while with fewer artifacts at the same time. Moreover, in order to apply the proposed MAP formulation to typical enhancement problems, like image editing, we further convert the estimation process into an intensity mapping process, which can achieve comparable enhancement performance with a much lower computational complexity. Simulation results have demonstrated the feasibility of the proposed framework in providing flexible and effective contrast enhancement.

In this paper we propose a cascaded hierarchical framework for object detection and tracking. We claim that, by integrating both detection and tracking into a unified framework, the detection and tracking of multiple moving objects in a complicated environment become more robust. Under the proposed architecture, detection and tracking cooperate with each other. Based on the result of moving object detection, a dynamic model is adaptively maintained for object tracking. On the other hand, the updated dynamic model is used for both temporal prior propagation of object labels and the update of foreground/background models, which step further to help the detection of moving objects. The experiments show accurate results can be obtained under situations with foreground/background appearance ambiguity, camera shaking, and object occlusion.

In this paper, a Bayesian framework is proposed for image enhancement. We model the image enhancement problem as a maximum a posteriori (MAP) estimation problem and the posteriori distribution function is formulated based on the local structures and local gradients of the given image. By solving the MAP estimation problem, image contrast gets properly enhanced while image noise gets suppressed at the same time. Moreover, since directly solving an MAP estimation problem is impractical for real-time applications, we further simplify the process to generate an intensity mapping function that achieves comparable performance in image enhancement. Simulation results have demonstrated the applicability of the proposed method in providing a flexible and efficient way for image enhancement.

In this paper, we propose a probabilistic method to model the dynamic traffic flow across non-overlapping camera views. By assuming the transition time of object movement follows a certain global model, we may infer the time-varying traffic status in the unseen region without performing explicit object correspondence between camera views. In this paper, we model object correspondence and parameter estimation as a unified problem under the proposed Expectation-Maximization (EM) based framework. By treating object correspondence as a latent random variable, the proposed framework can iteratively search for the optimal model parameters with the implicit consideration of object correspondence.

In this paper, from the viewpoint of scene under standing, a three-layer Bayesian hierarchical framework (BHF) is proposed for robust vacant parking space detection. In practice, the challenges of vacant parking space inference come from dramatic luminance variations, shadow effect, perspective distortion, and the inter-occlusion among vehicles. By using a hidden labeling layer between an observation layer and a scene layer, the BHF provides a systematic generative structure to model these variations. In the proposed BHF, the problem of luminance variations is treated as a color classification problem and is tack led via a classification process from the observation layer to the labeling layer, while the occlusion pattern, perspective distortion, and shadow effect are well modeled by the relationships between the scene layer and the labeling layer. With the BHF scheme, the detection of vacant parking spaces and the labeling of scene status are regarded as a unified Bayesian optimization problem subject to a shadow generation model, an occlusion generation model, and an object classification model. The system accuracy was evaluated by using outdoor parking lot videos captured from morning to evening. Experimental results showed that the proposed framework can systematically determine the vacant space number, efficiently label ground and car regions, precisely locate the shadowed regions, and effectively tackle the problem of luminance variations.

In this paper, we proposed a dynamic ordered subcarrier selection algorithm (DOSSA) for OFDM based video transmission system. The proposed scheme is shown to achieve lower bit error rate (BER) than the previously proposed OSSA by first selecting a fraction of the subcarriers with highest channel gain. The content information is then exploited in order to extend the OSSA to achieve unequal error protection (UEP) for packets of different importance. Simulation results show that system that utilizes the proposed scheme can achieve higher PSNR, especially at low SNR, compared to those that use the equal error protection (EEP) OSSA.

In this paper, we propose a new re-coloring algorithm to enhance the accessibility for the color vision deficient (or colorblind). Compared to people with normal color vision, people with color vision deficiency (CVD) have difficulty in distinguishing between certain combinations of colors. This may hinder visual communication owing to the increasing use of colors in recent years. To address this problem, we re-color the image to preserve visual detail when perceived by people with CVD. We first extract the representing colors in an image. Then we find the optimal mapping to maintain the contrast between each pair of these representing colors. The proposed algorithm is image content dependent and completely automatic. Experimental results on natural images are illustrated to demonstrate the effectiveness of the proposed re-coloring algorithm.

In this paper, we propose an efficient way to simultaneously label and map targets over a multi-camera surveillance system. In the system, we first fuse the detection results from multiple cameras into a posterior distribution. This distribution indicates the likelihood of having some moving targets on the ground plane. Based on the distribution, isolated targets, together with their 3-D positions, are identified in a sample-based manner, which combines Markov Chain Monte Carlo (MCMC), and mean-shift clustering. The induced 3-D scene information is further inputted into a 3-layer Bayesian hierarchical framework (BHF), which adopts a Markov network to deal with the object labeling and correspondence problems. In principle, labeling and correspondence are regarded as a unified optimal problem subject to 3-D scene prior, image color similarity, and detection results. The experiments show that accurate results can be gotten even under situations with severe occlusion.

In this paper, we propose a new algorithm for dynamic calibration of multiple cameras. Based on the mapping between a horizontal plane in the 3-D space and the 2-D image plane on a panned and tilted camera, we utilize the displacement of feature points and the epipolar-plane constraint among multiple cameras to infer the changes of pan and tilt angles for each camera. This algorithm does not require a complicated correspondence of feature points. It can be applied to surveillance systems with wide-range coverage. It also allows the presence of moving objects in the captured scenes while performing dynamic calibration. The sensitivity analysis of our algorithm with respect to measurement errors and fluctuations in previous estimations is also discussed. The efficiency and feasibility of this approach has been demonstrated in some experiments over real scenery.

In this paper, a 3-layer Bayesian hierarchical detection framework (BHDF) is proposed for robust parking space detection. In practice, the challenges of the parking space detection problem come from luminance variations, inter- occlusions among cars, and occlusions caused by environmental obstacles. Instead of determining the status of parking spaces one by one, the proposed BHDF framework models the inter-occluded patterns as semantic knowledge and couple local classifiers with adjacency constraints to determine the status of parking spaces in a row-by-row manner. By applying the BHDF to the parking space detection problem, the available parking spaces and the labeling of parked cars can be achieved in a robust and efficient manner. Furthermore, this BHDF framework is generic enough to be used for various kinds of detection and segmentation applications.

In this paper, a simple but efficient image enhancement algorithm is proposed. We model the image enhancement problem as a quadratic programming problem, and the cost function of the optimization problem is formulated based on local gradients of an image. By adjusting the definitions of gain function and weighting function in the cost function, we can derive various kinds of intensity transfer functions to fit for different applications. Simulation results for contrast enhancement and shadow enhancement have demonstrated the feasibility of this approach in providing a flexible and efficient mechanism for image enhancement.

In this letter, we proposed a new recoloring method for people with protanopic and deuteranopic color deficiencies. We present a color transformation that aims to preserve the color information in the original images while maintaining the recolored images as natural as possible. Two error functions are introduced and combined together to form an objective function using the Lagrange multiplier with a user-specified parameter$\lambda$. This objective function is then minimized to obtain the optimal settings. Experimental results show that the proposed method can yield more comprehensible images for color-deficient viewers while maintaining the naturalness of the recolored images for standard viewers.

In this paper, we propose an efficient approach to infer the relative positioning and orientation among multiple pan-tilt-zoom (PTZ) cameras. In this approach, the tilt angle and altitude of each PTZ camera are estimated first based on the observation of some simple objects lying on a horizontal plane. With the estimated tilt angles and altitudes, the calibration of multiple cameras can be easily accomplished by comparing the back-projected world coordinates of some common vectors in 3-D space. This calibration method does not require particular system setup or specific calibration patterns. The sensitivity analysis with respect to parameter fluctuations and measurement errors is also discussed. Experiment results over real images have demonstrated the efficiency and feasibility of this approach. Note to Practitioners-This paper was motivated by the problem that pan-tilt-zoom (PTZ) cameras may change their poses from time to time to achieve better monitoring results. Whenever there is a change, we need to recalibrate the extrinsic parameters again. In this paper, we demonstrate a new and efficient approach to calibrate multiple PTZ cameras. The concept of our approach originated from the observation that people could usually make a rough estimate about the tilt angle of the camera simply based on some clues revealed in the captured images. Based on our approach, we can simply use some A4 papers on a table to calibrate multiple PTZ cameras. In our approach, there is no need to calculate the commonly used homography matrix. For real cases, once a set of PTZ cameras is settled, we can simply place a few simple patterns on a horizontal plane. These patterns can be A4 papers, books, boxes, etc.; and the horizontal plane can be a tabletop or the ground plane. The whole procedure does not need specially designed calibration patterns and requires only a light computational load. In the near future, we will work on the extension of the proposed approach so that we will be able to perform dynamic calibration when the PTZ cameras are under movement

Histogram equalization (HE) and its variations have been widely used in image enhancement. Even though these approaches may enhance image contrast in an effective and efficient way, they usually face some undesired drawbacks, like loss of image details, noise amplification and over-enhancement. In this paper, we propose a generalized histogram equalization technique based on localized image analysis. Starting from designing two measures f1and f2to measure local characteristics around each pixel, the global statistics of these two local measures are then recorded into an extended histogram. Based on this extended histogram, we develop a procedure to generate suitable intensity transfer functions for various applications, like contrast enhancement and shadow enhancement. Experimental results show that the proposed algorithm provides a flexible and efficient way for image enhancement.

Surveillance systems with multiple cameras have become increasingly important. The space relationship between cameras offers useful information for surveillance applications, such as object tracking or 3- D positioning. In this paper, we propose a visionbased approach to infer the relative positioning and orientation among multiple PTZ cameras. The relationship between the tilt angle of a PTZ camera and the 3D-to-2D coordinate transformation is built first. Then, the tilt angles and the altitudes of PTZ cameras are estimated based on the observation of some simple objects lying on a horizontal plane, with known intrinsic parameters of these PTZ cameras. With the estimated tilt angles and altitudes, the calibration of multiple cameras can be accomplished by comparing the back-projected world coordinates of a common vector in the 3-D space. The whole procedure does not need a huge amount of data and the computational load is light. Experimental results over real images have demonstrated the efficiency and feasibility of this approach.

This paper presents a feature-based scheme for image compression. In the proposed method, the features in an image are recorded by three-dimensional verge points, which are defined as high curvature points on the image surface. The verge point representation can be further condensed using B-spline control point approximation. By encoding and transmitting these control points, the features in an image could be revealed at the decoder side. Furthermore, by selecting different coding modes, the proposed method can offer diversified scalabilities, including SNR scalability, spatial scalability, and shape scalability. In addition, this coding technique is suitable for region of interest selection and transmission. Experimental results are provided to present the scalability and interactivity of the proposed method.

This paper presents a scheme for feature-based image editing. In the proposed method, an image is decomposed into a skeleton component and a residual component. The skeleton component is obtained by performing iterative linear interpolation based on high-curvature points, which are extracted from the image surface using a Hessian tensor. The residual component is obtained by subtracting the skeleton component from the original image. By manipulating the skeleton component and the residual component, several applications, such as adaptive contrast enhancement, sharpness enhancement, and shape editing, can be achieved. Experimental results are provided to verify the versatility and flexibility of this proposed architecture.

Current contrast enhancement algorithms sometimes come with undesired drawbacks, like the loss of tiny details, enhancement of image noise, occasional over-enhancement, and unnatural look of the processed images. In this paper, we propose a new approach for contrast enhancement based on the use of a so-called intensity-pair distribution. This distribution possesses both local information and global information of the image content. By analyzing the content of intensity-pair distribution, a set of expansion forces are generated for contrast enhancement while another set of anti-expansion forces are generated to suppress image noise. To avoid over-enhancement and preserve the natural look of the processed images, a magnitude mapping function is also proposed. Experimental results show that the proposed algorithm does provide a flexible and reliable way for contrast enhancement.

This paper presents a new approach to represent an image by "verge points," which are defined as high-curvature points on the image surface. This representation offers a compact and reversible way to preserve the essence of the original image. Various applications, such as compression, edge detection, image enhancement, and image editing, can be achieved based on this representation. In this paper, the whole procedure for verge point representation is presented. Based on these verge points, image reconstruction can be easily achieved via iterative linear interpolation. These extracted verge points with compatible properties are further linked into verge curves to offer more compact representation. Progressive representation is also developed based on a multiscale extraction scheme. Some potential applications are then presented to demonstrate the versatility of this representation.

In this paper, we propose the use of visible color difference in a new quantitative evaluation scheme for color image segmentation. With visible color difference, two measurements, named intra-region visual error and inter-region visual error, are defined to evaluate the quality of segmentation results. To fit human visual perception, segmentation results with an excessive amount of intra-region error are regarded as under-segmentation, while segmentation results with too many inter-region errors are regarded as over-segmentation. Based on these two measurements, a complete scheme for the evaluation of color image segmentation is proposed. The simulation results demonstrate that this new scheme may provide a reliable and efficient way to automatically select the parameter settings for a given segmentation algorithm and to compare the performance between various segmentation algorithms.

In this letter, we propose a color image segmentation algorithm based on contrast information. Given a color image, we use contrast information, instead of the commonly used derivative information, to detect edges. To fit for human's visual perception, the CIE L/sup */a/sup */b/sup */ color space is used and the /spl Delta/E/sub ab/ color difference is adopted as the measure of color contrast. A subjective experiment is made to demonstrate the weak correlation between the perceived color contrast and the levels of (L/sup */,a/sup */,b/sup */). This experiment implies the feasibility of using a single-threshold scheme to suppress perceptually faint boundaries. A complete segmentation scheme is proposed and the simulation results demonstrate the superiority of this approach in providing reasonable and reliable color image segmentation.

In this paper, we propose a color segmentation algorithm based on contrast information and adaptive thresholds. Given a color image, instead of the commonly used achromatic difference and chromatic difference, we use achromatic contrast and chromatic contrast to represent the significance of boundary. To fit for human visual perception, adaptive thresholds are applied to suppress perceptually faint boundaries. A complete segmentation scheme is proposed and the simulation results demonstrate the superiority of this approach in providing reasonable and reliable color segmentation.

A new scheme, which automatically generates a hierarchical mesh from a real image, is proposed. First, three distinct meshes are generated according to a three-layer image pyramid. By eliminating the duplicated mesh nodes between these three meshes, a hierarchical mesh is formed. Because each hierarchy represents the image in different resolutions, this hierarchical structure can achieve progressive coding. Furthermore, to generate a dynamic mesh for an image sequence, this hierarchical structure can help to reduce the computation complexity through the tracking of mesh nodes in the sequence. A method is also proposed to predict the moving direction of mesh nodes and to facilitate the motion estimation.

The authors present two systolic architectures to speed up the computation of modular multiplication in RSA cryptosystems. In the double-layer architecture, the main operation of Montgomery's algorithm is partitioned into two parallel operations after using the precomputation of the quotient bit. In the non-interlaced architecture, we eliminate the one-clock-cycle gap between iterations by pairing off the double-layer architecture. We compare our architectures with some previously proposed Montgomery-based systolic architectures, on the basis of both modular multiplication and modular exponentiation. The comparisons indicate that our architectures offer the highest speed, lower hardware complexity, and lower power consumption.

In this paper, we present a new 2-D approach to extract brink points in an image. These brink points can efficiently represent the image and can be used for various purposes. These extracted brink points are further linked into brink curves and the B-spline approximation is used to compactly represent these linked curves.

In this paper we present a new approach which represents an intensity profile by using some "pulley" points, which are defined as points of high-curvature. The basic concept and the morphological methods for finding these pulley points are introduced. This representation can faithfully keep the spatial information of a profile and greatly reduce the spatial redundancy. We show some experimental results which demonstrate the promising possibility of using this approach in image compression.