Search

Cross-modality face image synthesis such as sketch-to-photo, NIR-to-RGB, and RGB-to-depth has wide applications in face recognition, face animation, and digital entertainment. Conventional cross-modality synthesis methods usually require paired training data, i.e., each subject has images of both modalities. However, paired data can be difficult to acquire, while unpaired data commonly exist. In this paper, we propose a novel semi-supervised cross-modality synthesis method (namely CMOS-GAN), which can leverage both paired and unpaired face images to learn a robust cross-modality synthesis model. Specifically, CMOS-GAN uses a generator of encoder-decoder architecture for new modality synthesis. We leverage pixel-wise loss, adversarial loss, classification loss, and face feature loss to exploit the information from both paired multi-modality face images and unpaired face images for model learning. In addition, since we expect the synthetic new modality can also be helpful for improving face recognition accuracy, we further use a modified triplet loss to retain the discriminative features of the subject in the synthetic modality. Experiments on three cross-modality face synthesis tasks (NIR-to-VIS, RGB-to-depth, and sketch-to-photo) show the effectiveness of the proposed approach compared with the state-of-the-art. In addition, we also collect a large-scale RGB-D dataset (VIPL-MumoFace-3K) for the RGB-to-depth synthesis task. We plan to open-source our code and VIPL-MumoFace-3K dataset to the community (https://github.com/skgyu/CMOS-GAN). [ABSTRACT FROM AUTHOR]

In this paper, we focus on improving the proposal classification stage in the object detection task and present implicit negative sub-categorization and sink diversion to lift the performance by strengthening loss function in this stage. First, based on the observation that the “background” class is generally very diverse and thus challenging to be handled as a single indiscriminative class in existing state-of-the-art methods, we propose to divide the background category into multiple implicit sub-categories to explicitly differentiate diverse patterns within it. Second, since the ground truth class inevitably has low-value probability scores for certain images, we propose to add a “sink” class and divert the probabilities of wrong classes to this class when necessary, such that the ground truth label will still have a higher probability than other wrong classes even though it has low probability output. Additionally, we propose to use dilated convolution, which is widely used in the semantic segmentation task, for efficient and valuable context information extraction. Extensive experiments on PASCAL VOC 2007 and 2012 data sets show that our proposed methods based on faster R-CNN implementation can achieve state-of-the-art mAPs, i.e., 84.1%, 82.6%, respectively, and obtain 2.5% improvement on ILSVRC DET compared with that of ResNet. [ABSTRACT FROM PUBLISHER]

As human visual attention is naturally biased toward foreground objects in a scene, it can be used to extract salient objects in video clips. In this paper, we proposed a weakly supervised learning-based video saliency detection algorithm utilizing eye fixations information from multiple subjects. Our main idea is to extend eye fixations to saliency regions step by step. First, visual seeds are collected using multiple color space geodesic distance-based seed region mapping with filtered and extended eye fixations. This operation helps raw fixation points spread to the most likely salient regions, namely, visual seed regions. Second, in order to seize the essential scene structure from video sequences, we introduce the total variance-based pairwise interaction model to learn the potential pairwise relationship between foreground and background within a frame or across video frames. In this vein, visual seed regions eventually grow into salient regions. Compared with previous approaches the generated saliency maps have two most outstanding properties: $integrity$ and $purity$ , which are conductive to segment the foreground and significant to the follow-up tasks. Extensive quantitative and qualitative experiments on various video sequences demonstrate that the proposed method outperforms the state-of-the-art image and video saliency detection algorithms. [ABSTRACT FROM AUTHOR]

A popular way to restore images comprising edges is to minimize a cost function combining a quadratic data-fidelity term and an edge-preserving (possibly nonconvex) regularization term. Mainly because of the latter term, the calculation of the solution is slow and cumbersome. Half-quadratic (HQ) minimization (multiplicative form) was pioneered by Geman and Reynolds (1992) in order to alleviate the computational task in the context of image reconstruction with nonconvex regularization. By promoting the idea of locally homogeneous image models with a continuous-valued line process, they reformulated the optimization problem in terms of an augmented cost function which is quadratic with respect to the image and separable with respect to the line process, hence the name "half quadratic." Since then, a large amount of papers were dedicated to HQ minimization and important results—including edge-preservation along with convex regularization and convergence—have been obtained. In this paper, we show that HQ minimization (multiplicative form) is equivalent to the most simple and basic method where the gradient of the cost function is linearized at each iteration step. In fact, both methods give exactly the same iterations. Furthermore, connections of HQ minimization with other methods, such as the quasi-Newton method and the generalized Weiszfeld's method, are straightforward. [ABSTRACT FROM AUTHOR]

The Fourier transform is one of the most important transformations in image processing. A major component of this influence comes from the ability to implement it efficiently on a digital computer. This paper describes a new methodology to perform a fast Fourier transform (FFT). This methodology emerges from considerations of the natural physical constraints imposed by image capture devices (camera/eye). The novel aspects of the specific FFT method described include: 1) a bit-wise reversal re-grouping operation of the conventional FFT is replaced by the use of lossless image rotation and scaling and 2) the usual arithmetic operations of complex multiplication are replaced with integer addition. The significance of the FFT presented in this paper is introduced by extending a discrete and finite image algebra, named Spiral Honeycomb image Algebra (SHIA), to a continuous version, named SHIAC. [ABSTRACT FROM AUTHOR]

Measurement of visual quality is of fundamental importance for numerous image and video processing applications, where the goal of quality assessment (QA) algorithms is to automatically assess the quality of images or videos in agreement with human quality judgments. Over the years, many researchers have taken different approaches to the problem and have contributed significant research in this area and claim to have made progress in their respective domains. It is important to evaluate the performance of these algorithms in a comparative setting and analyze the strengths and weaknesses of these methods. In this paper, we present results of an extensive subjective quality assessment study in which a total of 779 distorted images were evaluated by about two dozen human subjects. The "ground truth" image quality data obtained from about 25000 individual human quality judgments is used to evaluate the performance of several prominent full-reference image quality assessment algorithms. To the best of our knowledge, apart from video quality studies conducted by the Video Quality Experts Group, the study presented in this paper is the largest subjective image quality study in the literature in terms of number of images, distortion types, and number of human judgments per image. Moreover, we have made the data from the study freely available to the research community [1]. This would allow other researchers to easily report comparative results in the future. [ABSTRACT FROM AUTHOR]

In this paper, we investigate the problem of facial kinship verification by learning hierarchical reasoning graph networks. Conventional methods usually focus on learning discriminative features for each facial image of a paired sample and neglect how to fuse the obtained two facial image features and reason about the relations between them. To address this, we propose a Star-shaped Reasoning Graph Network (S-RGN). Our S-RGN first constructs a star-shaped graph where each surrounding node encodes the information of comparisons in a feature dimension and the central node is employed as the bridge for the interaction of surrounding nodes. Then we perform relational reasoning on this star graph with iterative message passing. The proposed S-RGN uses only one central node to analyze and process information from all surrounding nodes, which limits its reasoning capacity. We further develop a Hierarchical Reasoning Graph Network (H-RGN) to exploit more powerful and flexible capacity. More specifically, our H-RGN introduces a set of latent reasoning nodes and constructs a hierarchical graph with them. Then bottom-up comparative information abstraction and top-down comprehensive signal propagation are iteratively performed on the hierarchical graph to update the node features. Extensive experimental results on four widely used kinship databases show that the proposed methods achieve very competitive results. [ABSTRACT FROM AUTHOR]

The generalization performance for semantic segmentation remains a major challenge when the data distributions between the source and target domain mismatch. Unsupervised domain adaptation (UDA) approaches are proposed to mitigate the problem above, among which entropy-minimization-based methods have gained more and more attention. However, the methods merely follow the cluster assumption sharpening the prediction distribution, thus have limited performance improvement. Without additional priors, the entropy loss can easily over-sharpen the prediction distribution, which brings noisy information into the learning process. On the other hand, the gradient of the entropy loss is strongly biased toward easy samples, also leading to limited generalization advances. In this paper, we firstly propose a pixel-level consistency regularization method, which introduces the smoothness prior to the UDA problem. Furthermore, we propose the neutral cross-entropy loss based on the consistency regularization, and reveal that its internal neutralization mechanism mitigates the over-sharpness of entropy minimization via the flatness effect of consistency regularization. We also demonstrate that the gradient bias toward easy samples is inherently tackled via the neutral cross-entropy loss. The experiments show that the proposed method has outperformed state-of-the-art methods in two synthetic-to-real experiments, only using the lightweight network. [ABSTRACT FROM AUTHOR]

Images are conventionally sampled on a rectangular lattice. Thus, traditional image processing is carried out on the rectangular lattice. The hexagonal lattice was proposed more than four decades ago as an alternative method for sampling. Compared with the rectangular lattice, the hexagonal lattice has certain advantages which include that it needs less sampling points; it has better consistent connectivity and higher symmetry; the hexagonal structure is also pertinent to the vision process. In this paper, we investigate the construction of symmetric FIR hexagonal filter banks for multiresolution hexagonal image processing. We obtain block structures of FIR hexagonal filter banks with 3-fold rotational symmetry and 3-fold axial symmetry. These block structures yield families of orthogonal and biorthogonal FIR hexagonal filter banks with 3-fold rotational symmetry and 3-fold axial symmetry. In this paper, we also discuss the construction of orthogonal and biorthogonal FIR filter banks with scaling functions and wavelets having optimal smoothness. In addition, we present a few of such orthogonal and biorthogonal FIR filters banks. [ABSTRACT FROM AUTHOR]

Sparse representations of signals have drawn considerable interest in recent years. The assumption that natural signals, such as images, admit a sparse decomposition over a redundant dictionary leads to efficient algorithms for handling such sources of data. In particular, the design of well adapted dictionaries for images has been a major challenge. The K-SVD has been recently proposed for this task [1] and shown to perform very well for various grayscale image processing tasks. In this paper, we address the problem of learning dictionaries for color images and extend the K-SVD-based grayscale image denoising algorithm that appears in [21. This work puts forward ways for handling nonhomogeneous noise and missing information, paving the way to state-of-the-art results in applications such as color image denoising, demosaicing, and inpainting, as demonstrated in this paper. [ABSTRACT FROM AUTHOR]

Image moments have been extensively used as feature descriptors. However, the quantization error introduced in discrete signals presents problems, especially when dealing with small-size images. This results in the fact that the invariant properties of moments are compromised. In this paper, we present a technique suitable for the calculation of moments from a continuous signal, derived by piecewise polynomial interpolation of the corresponding discrete one. The computed moments exhibit significantly increased accuracy while requiring trivial computational effort. Zernike moments are then computed using the proposed scheme and are shown to display increased stability to geometrical transformations. [ABSTRACT FROM AUTHOR]

Motion trajectories provide rich spatiotemporal information about an object's activity. This paper presents novel classification algorithms for recognizing object activity using object motion trajectory. In the proposed classification system, trajectories are segmented at points of change in curvature, and the subtrajectories are represented by their principal component analysis (PCA) coefficients. We first present a framework to robustly estimate the multivariate probability density function based on PCA coefficients of the subtrajectories using Gaussian mixture models (GMMs). We show that GMM-based modeling alone cannot capture the temporal relations and ordering between underlying entities. To address this issue, we use hidden Markov models (HMMs) with a data-driven design in terms of number of states and topology (e.g., left-right versus ergodic). Experiments using a database of over 5700 complex trajectories (obtained from UCI-KDD data archives and Columbia University Multimedia Group) subdivided into 85 different classes demonstrate the superiority of our proposed 11MM-based scheme using PCA coefficients of subtrajectories in comparison with other techniques in the literature. [ABSTRACT FROM AUTHOR]

The shape-adaptive discrete cosine transform (SA-DCT) transform can be computed on a support of arbitrary shape, but retains a computational complexity comparable to that of the usual separable block-DCT (B-DCT). Despite the near-optimal decorrelation and energy compaction properties, application of the SA-DCT has been rather limited, targeted nearly exclusively to video compression. In this paper, we present a novel approach to image filtering based on the SA-DCT. We use the SA-DCT in conjunction with the Anisotropic Local Polynomial Approximation—Intersection of Confidence Intervals technique, which defines the shape of the transform's support in a pointwise adaptive manner. The thresholded or attenuated SA-DCT coefficients are used to reconstruct a local estimate of the signal within the adaptive-shape support. Since supports corresponding to different points are in general overlapping, the local estimates are averaged together using adaptive weights that depend on the region's statistics. This approach can be used for various image-processing tasks. In this paper, we consider, in particular, image denoising and image deblocking and deringing from block-DCT compression. A special structural constraint in luminance-chrominance space is also proposed to enable an accurate filtering of color images. Simulation experiments show a state-of-the-art quality of the final estimate, both in terms of objective criteria and visual appearance. Thanks to the adaptive support, reconstructed edges are clean, and no unpleasant ringing artifacts are introduced by the fitted transform. [ABSTRACT FROM AUTHOR]

Contrast enhancement has an important role in image processing applications. Conventional contrast enhancement techniques either often fail to produce satisfactory results for a broad variety of low-contrast images, or cannot be automatically applied to different images, because their parameters must be specified manually to produce a satisfactory result for a given image. This paper describes a new automatic method for contrast enhancement. The basic procedure is to first group the histogram components of a low-contrast image into a proper number of bins according to a selected criterion, then redistribute these bins uniformly over the grayscale, and finally ungroup the previously grouped gray-levels. Accordingly, this new technique is named gray-level grouping (GLG). GLG not only produces results superior to conventional contrast enhancement techniques, but is also fully automatic in most circumstances, and is applicable to a broad variety of images. An extension of GLG, selective GLG (SGLG), and its variations will be discussed in Part II of this paper. SGLG selectively groups and ungroups histogram components to achieve specific application purposes, such as eliminating background noise, enhancing a specific segment of the histogram, and so on. The extension of GLG to color images will also be discussed in Part II. [ABSTRACT FROM AUTHOR]

In this paper, a new method for generating different texture images is presented. This method involves a simple transform from a certain one-dimensional (1-D) signal to an expected two-dimensional (2-D) image. Unlike traditional methods, the input signal is generated by a simple 1-D function in our work instead of a sample texture. We first transform the 1-D input signal into frequency domain using fast Fourier transform. Based on the sufficient analysis in 2-D discrete cosine transform (DCT) domain, where each of the coefficients expresses a texture feature in a certain direction, the 2-D pseudo-DCT coefficients are then constructed by appropriately rearranging the Fourier coefficients in terms of their frequency components. Finally, the corresponding texture image can be produced by 2-D inverse DCT algorithm. We applied the proposed method to generate several stochastic textures (i.e., cloud, illumination, and sand), and several structural texture images. Experimental results indicate the good performance of the proposed method. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

This paper advances a new framework for chromatic filtering of color images. The chromatic content of a color image is encoded in the CIE u' v' chromaticity coordinates whereas the achromatic content is encoded as CIE Y tristimulus value. Within the u' v' chromaticity diagram, colors are added according to the well-known center of gravity law of additive color mixtures, which is generalized here into a nonlinear filtering scheme for processing the two chromatic signals u' and v'. The achromatic channel Y can be processed with traditional filtering schemes, either linear or nonlinear, depending on the specific task at hand. The most interesting characteristics of the new filtering scheme are: 1) the elimination of color smearing effects along edges between bright and dark areas; 2) the possibility of processing chromatic components in a noniterative fashion through linear convolution operations; and 3) the consequent amenability to computationailly efficient implementations with fast Fourier transform. The paper includes several examples with both synthetic and real images where the performance of the new filtering method is compared with that of other color image processing algorithms. [ABSTRACT FROM AUTHOR]

This paper introduces a new transmission protocol that uses a joint lossless-source and channel coding scheme (JARQ). This protocol utilizes the self-synchronization property of lossless compression to generate indications of errors in the received data. This approach assures the reconstruction of images that were compressed in a lossless fashion and transmitted over a packet switched network, regardless of the error pattern that occurred during transmission. This new protocol is referred to as Go-Back-(N, M) JARQ. In this paper, we evaluate the protocol by analyzing its throughput and present simulation results that compare the throughput achieved with this protocol with that of conventional ARQ protocols. Using still images, we found significant gain in throughput performance for our Go-Back-(N, M) protocol, especially in moderate to low BERs, compared with that of the conventional Go-Back-N protocol. Moreover, by including packet combining, we found large throughput gains at low BERS, as well. This gain is realized for both random and burst errors. This approach provides an increase in the code rate; a clear indication of error propagation; and insensitivity to the type of error pattern-random or burst. [ABSTRACT FROM AUTHOR]

Existing video coders anchor motion fields at frames that are to be predicted. In this paper, we demonstrate how changing the anchoring of motion fields to reference frames has some important advantages over conventional anchoring. We work with piecewise-smooth motion fields, and use breakpoints to signal discontinuities at moving object boundaries. We show how discontinuity information can be used to resolve double mappings arising when motion is warped from reference to target frames. We present an analytical model that allows to determine weights for texture, motion, and breakpoints to guide the rate-allocation for scalable encoding. Compared with the conventional way of anchoring motion fields, the proposed scheme requires fewer bits for the coding of motion; furthermore, the reconstructed video frames contain fewer ghosting artefacts. The experimental results show the superior performance compared with the traditional anchoring, and demonstrate the high scalability attributes of the proposed method. [ABSTRACT FROM PUBLISHER]

Face recognition methods, which usually represent face images using holistic or local facial features, rely heavily on alignment. Their performances also suffer a severe degradation under variations in expressions or poses, especially when there is one gallery per subject only. With the easy access to high-resolution (HR) face images nowadays, some HR face databases have recently been developed. However, few studies have tackled the use of HR information for face recognition or verification. In this paper, we propose a pose-invariant face-verification method, which is robust to alignment errors, using the HR information based on pore-scale facial features. A new keypoint descriptor, namely, pore-Principal Component Analysis (PCA)-Scale Invariant Feature Transform (PPCASIFT)—adapted from PCA-SIFT—is devised for the extraction of a compact set of distinctive pore-scale facial features. Having matched the pore-scale features of two-face regions, an effective robust-fitting scheme is proposed for the face-verification task. Experiments show that, with one frontal-view gallery only per subject, our proposed method outperforms a number of standard verification methods, and can achieve excellent accuracy even the faces are under large variations in expression and pose. [ABSTRACT FROM AUTHOR]

This paper advocates a novel multiscale, structure-sensitive saliency detection method, which can distinguish multilevel, reliable saliency from various natural pictures in a robust and versatile way. One key challenge for saliency detection is to guarantee the entire salient object being characterized differently from nonsalient background. To tackle this, our strategy is to design a structure-aware descriptor based on the intrinsic biharmonic distance metric. One benefit of introducing this descriptor is its ability to simultaneously integrate local and global structure information, which is extremely valuable for separating the salient object from nonsalient background in a multiscale sense. Upon devising such powerful shape descriptor, the remaining challenge is to capture the saliency to make sure that salient subparts actually stand out among all possible candidates. Toward this goal, we conduct multilevel low-rank and sparse analysis in the intrinsic feature space spanned by the shape descriptors defined on over-segmented super-pixels. Since the low-rank property emphasizes much more on stronger similarities among super-pixels, we naturally obtain a scale space along the rank dimension in this way. Multiscale saliency can be obtained by simply computing differences among the low-rank components across the rank scale. We conduct extensive experiments on some public benchmarks, and make comprehensive, quantitative evaluation between our method and existing state-of-the-art techniques. All the results demonstrate the superiority of our method in accuracy, reliability, robustness, and versatility. [ABSTRACT FROM AUTHOR]

This paper adapts the least-squares luma-chroma demultiplexing (LSLCD) demosaicking method to noisy Bayer color filter array (CFA) images. A model is presented for the noise in white-balanced gamma-corrected CFA images. A method to estimate the noise level in each of the red, green, and blue color channels is then developed. Based on the estimated noise parameters, one of a finite set of configurations adapted to a particular level of noise is selected to demosaic the noisy data. The noise-adaptive demosaicking scheme is called LSLCD with noise estimation (LSLCD-NE). Experimental results demonstrate state-of-the-art performance over a wide range of noise levels, with low computational complexity. Many results with several algorithms, noise levels, and images are presented on our companion web site along with software to allow reproduction of our results. [ABSTRACT FROM AUTHOR]

In this paper, a new fuzzy filter for the removal of random impulse noise in color video is presented. By working with different successive filtering steps, a very good tradeoff between detail preservation and noise removal is obtained. One strong filtering step that should remove all noise at once would inevitably also remove a considerable amount of detail. Therefore, the noise is filtered step by step. In each step, noisy pixels are detected by the help of fuzzy rules, which are very useful for the processing of human knowledge where linguistic variables are used. Pixels that are detected as noisy are filtered, the others remain unchanged. Filtering of detected pixels is done by blockmatching based on a noise adaptive mean absolute difference. The experiments show that the proposed method outperforms other state-of-the-art filters both visually and in terms of objective quality measures such as the mean absolute error (MAE), the peak-signal-to-noise ratio (PSNR) and the normalized color difference (NCD). [ABSTRACT FROM PUBLISHER]

Software realizations of computationally-demanding image processing tasks (e.g., image transforms and convolution) do not currently provide graceful degradation when their clock-cycles budgets are reduced, e.g., when delay deadlines are imposed in a multitasking environment to meet throughput requirements. This is an important obstacle in the quest for full utilization of modern programmable platforms' capabilities since worst-case considerations must be in place for reasonable quality of results. In this paper, we propose (and make available online) platform-independent software designs performing bitplane-based computation combined with an incremental packing framework in order to realize block transforms, 2-D convolution and frame-by-frame block matching. The proposed framework realizes incremental computation: progressive processing of input-source increments improves the output quality monotonically. Comparisons with the equivalent nonincremental software realization of each algorithm reveal that, for the same precision of the result, the proposed approach can lead to comparable or faster execution, while it can be arbitrarily terminated and provide the result up to the computed precision. Application examples with region-of-interest based incremental computation, task scheduling per frame, and energy-distortion scalability verify that our proposal provides significant performance scalability with graceful degradation. [ABSTRACT FROM AUTHOR]

The distance between a straight line and a straight line segment in the image space is proposed in this paper. Based on this distance, the neighborhood of a straight line segment is defined and mapped into the parameter space to obtain the parameter space neighborhood of the straight line segment. The neighborhood mapping between the image space and parameter space is a one to one reversible map. The mapped region in the parameter space is analytically derived and it is proved that it can be effi- ciently approximated by a quadrangle. The proposed straight line segment neighborhood technique for the HT outperforms conventional straight line neighborhood methods currently used with existing HT variations. In contrast to the straight line neighborhoods used in existing HT variations, the proposed straight line segment neighborhood has several advantages including: 1) the detection error of the proposed neighborhood is not affected by the length of the straight line segments; 2) a precision requirement in the image space described using the proposed distance can be explicitly resolved using the proposed formulation; 3) the proposed neighborhood has the ability to distinguish between segments belonging to the same straight line. A variety of experiments are executed to demonstrate that the proposed neighborhood has a variety of interesting properties of high practical value. [ABSTRACT FROM AUTHOR]

Face recognition is one of the most intensively studied topics in computer vision and pattern recognition, but few are focused on how to robustly recognize faces with expressions under the restriction of one single training sample per class. A constrained optical flow algorithm, which combines the advantages of the unambiguous correspondence of feature point labeling and the flexible representation of optical flow computation, has been developed for face recognition from expressional face images. In this paper, we propose an integrated face recognition system that is robust against facial expressions by combining information from the computed intraperson optical flow and the synthesized face image in a probabilistic framework. Our experimental results show that the proposed system improves the accuracy of face recognition from expressional face images. [ABSTRACT FROM AUTHOR]

In this paper, we propose an algorithm to compose a geometrically dewarped and visually enhanced image from two document images taken by a digital camera at different angles. Unlike the conventional works that require special equipments or assumptions on the contents of books or complicated image acquisition steps, we estimate the unfolded book or document surface from the corresponding points between two images. For this purpose, the surface and camera matrices are estimated using structure reconstruction, 3-D projection analysis, and random sample consensus-based curve fitting with the cylindrical surface model. Because we do not need any assumption on the contents of books, the proposed method can be applied not only to optical character recognition (OCR), but also to the high-quality digitization of pictures in documents. In addition to the dewarping for a structurally better image, image mosaic is also performed for further improving the visual quality. By finding better parts of images (with less out of focus blur and/or without specular reflections) from either of views, we compose a better image by stitching and blending. them. These processes are formulated as energy minimization problems that can be solved using a graph cut method. Experiments on many kinds of book or document images show that the proposed algorithm robustly works and yields visually pleasing results. Also, the OCR rate of the resulting image is comparable to that of document images from a flatbed scanner. [ABSTRACT FROM AUTHOR]

This paper presents a consistent framework for continuous stereo self-calibration. Based on a practical analysis of the sensitivity of stereo reconstruction to camera calibration uncertainties, we identify important parameters for self-calibration. We evaluate different geometric constraints for estimation and tracking of these parameters: bundle adjustment with reduced structure representation relating corresponding points in image sequences, the epipolar constraint between stereo image pairs, and trilinear constraints between image triplets. Continuous, recursive calibration refinement is obtained with a robust, adapted iterated extended Kalman filter. To achieve high accuracy, physically relevant geometric optimization criteria are formulated in a Gauss-Helmert type model. The self-calibration framework is tested on an active stereo system. Experiments with synthetic data as well as on natural indoor and outdoor imagery indicate that the different constraints are complementing each other and thus a method combining two of the above constraints is proposed: While reduced order bundle adjustment gives by far the most accurate results (and might suffice on its own in some environments), the epipolar constraint yields instantaneous calibration that is not affected by independently moving objects in the scene. Hence, it expedites and stabilizes the calibration process. [ABSTRACT FROM AUTHOR]

This paper develops a distinctive class of color error diffusion algorithm, called hierarchical error diffusion (HED). It aims to achieve perceptually pleasing color halftone through neither conventional joint quantization nor interchannel error diffusion. Instead, it explicitly controls three critical factors sequentially to yield high-quality color halftone: dot-overlapping control, dot-positioning control, and dot-coloring control. A specific implementation of HED is presented with the objective of minimum brightness variation rendering (MBVR). First, an optimal color transform is derived for dot-overlapping control to achieve minimum brightness variation color density (MBVCD). Then, the embedded monochrome error diffusion is employed in dot-positioning control. By sequentially thresholding the elements in partial density sum vector, better dot-positioning is encouraged for more visible color dots. The "blue noise" characteristics of dot-positioning from the monochrome error diffusion are inherited by the color halftone. The simple density priority strategy is applied in dot-coloring control. The pixel color error is diffused channel-independently with a single error filter in halftone dot color space. A comparison with the state-of-the-art color error diffusion algorithms demonstrates excellent halftone quality of HED, while without the typical artifacts of vector error diffusion. Evidence also shows that HED is closer to achieve MBVR than the minimum brightness variation quantization (MBVQ) color diffusion algorithm proposed in [32]. [ABSTRACT FROM AUTHOR]

This paper proposes a novel approach to extract image features for texture classification. The proposed features are robust to image rotation, less sensitive to histogram equalization and noise. It comprises of two sets of features: dominant local binary patterns (DLBP) in a texture image and the supplementary features extracted by using the circularly symmetric Gabor filter responses. The dominant local binary pattern method makes use of the most frequently occurred patterns to capture descriptive textural information, while the Gabor-based features aim at supplying additional global textural information to the DLBP features. Through experiments, the proposed approach has been intensively evaluated by applying a large number of classification tests to histogram-equalized, randomly rotated and noise corrupted images in Outex, Brodatz, Meastex, and CUReT texture image databases. Our method has also been compared with six published texture features in the experiments. It is experimentally demonstrated that the proposed method achieves the highest classification accuracy in various texture databases and image conditions. [ABSTRACT FROM AUTHOR]

The logarithmic image processing (LIP) model is a mathematical theory that provides new operations for image processing. The contrast definition has been shown to be consistent with some important physical laws and characteristics of human visual system. In this paper, we establish an information-theoretic interpretation of the contrast definition. We show that it can be expressed as a combination of the relative entropy and Shannon's information content. Based on this new interpretation, we propose an adaptive algorithm for enhancing the contrast and sharpness of noisy images. [ABSTRACT FROM AUTHOR]

In this paper, we present two related multigrid algorithms for multiphase image segmentation. Algorithm I solves the model by Vese-Chan. We first generalize our recently developed multigrid method to this multiphase segmentation model (MG1); we also give a local Fourier analysis for the local smoother which leads to a new and more effective smoother. Although MG1 is found many magnitudes faster than the fast method of additive operator splitting (AOS), both algorithms are not robust with regard to the initial guess. To overcome this dependence on the initial guess, we consider a hierarchical segmentation model which achieves multiphase segmentation by repeated use of the Chan-Vese two-phase model; our Algorithm II solves this model by a multigrid algorithm (MG2). Numerical experiments show that both algorithms are efficient and in particular MG2 is more robust than MG1 with respect to initial guesses. AMS subject classifications: 68U10, 65F10, 65K10. [ABSTRACT FROM AUTHOR]

One of the fastest methods of localizing edges in images is based on small gradient kernels, such as Sobel, Prewitt, and Roberts. Although small gradient kernels provide a fast way of computing the gradients, they have little control over noise, edge location, and edge orientation. They are known to be only sensitive to step edges and fail to detect smooth boundaries, On the other hand, large kernels provide superior noise suppression characteristics, but they suffer from wide response area around edges. They cause edges of neighboring objects to merge due to their wide support. Problems associated with large gradient kernels prevent their widespread usage. This paper presents a fuzzy topology-based method to facilitate the use of larger gradient kernels. The new method effectively limits the response area around the edge and prevents neighboring objects to affect each other. Synthetic images are used to show the superior noise suppression properties and response characteristics to both step and ramp edges. Natural images are also used to assess the performance of the newly proposed topological gradient estimation qualitatively. [ABSTRACT FROM AUTHOR]

This paper discusses the use of Binary Partition Trees (BPTs) for object detection. BPTs are hierarchical region-based representations of images. They define a reduced set of regions that covers the image support and that spans various levels of resolution. They are attractive for object detection as they tremendously reduce the search space. In this paper, several issues related to the use of BPT for object detection are studied. Concerning the tree construction, we analyze the compromise between computational complexity reduction and accuracy. This will lead us to define two parts in the BPT: one providing accuracy and one representing the search space for the object detection task. Then we analyze and objectively compare various similarity measures for the tree construction. We conclude that different similarity criteria should be used for the part providing accuracy in the BPT and for the part defining the search space and specific criteria are proposed for each case. Then we discuss the object detection strategy based on BPT. The notion of node extension is proposed and discussed. Finally, several object detection examples illustrating the generality of the approach and its efficiency are reported. [ABSTRACT FROM AUTHOR]

Due to the sequential-readout structure of complementary metal-oxide semiconductor image sensor array, each scanline of the acquired image is exposed at a different time, resulting in the so-called electronic rolling shutter that induces geometric image distortion when the object or the video camera moves during image capture. In this paper, we propose an image processing technique using a planar motion model to address the problem. Unlike previous methods that involve complex 3-D feature correspondences, a simple approach to the analysis of inter- and intraframe distortions is presented. The high-resolution velocity estimates used for restoring the image are obtained by global motion estimation, Bézier curve fitting, and local motion estimation without resort to correspondence identification. Experimental results demonstrate the effectiveness of the algorithm. [ABSTRACT FROM AUTHOR]

In this paper, a level-set-based geometric regularization method is proposed which has the ability to estimate the local orientation of the evolving front and utilize it as shape induced information for anisotropic propagation. We show that preserving anisotropic fronts can improve elongations of the extracted structures, while minimizing the risk of leakage. To that end, for an evolving front using its shape-offset level-set representation, a novel energy functional is defined. It is shown that constrained optimization of this functional results in an anisotropic expansion flow which is usefull for vessel segmentation. We have validated our method using synthetic data sets, 2-D retinal angiogram images and magnetic resonance angiography volumetric data sets. A comparison has been made with two state-of-the-art vessel segmentation methods. Quantitative results, as well as qualitative comparisons of segmentations, indicate that our regularization method is a promissing tool to improve the efficiency of both techniques. [ABSTRACT FROM AUTHOR]

In this paper, we propose a maximum-entropy expectation- maximization (MEEM) algorithm. We use the proposed algorithm for density estimation. The maximum-entropy constraint is imposed for smoothness of the estimated density function. The derivation of the MEEM algorithm requires determination of the covariance matrix in the framework of the maximum-entropy likelihood function, which is difficult to solve analytically. We, therefore, derive the MEEM algorithm by optimizing a lower-bound of the maximum-entropy likelihood function. We note that the classical expectation-maximization (EM) algorithm has been employed previously for 2-D density estimation. We propose to extend the use of the classical EM algorithm for image recovery from randomly sampled data and sensor field estimation from randomly scattered sensor networks. We further propose to use our approach in density estimation, image recovery and sensor field estimation. Computer simulation experiments are used to demonstrate the superior performance of the proposed MEEM algorithm in comparison to existing methods. [ABSTRACT FROM AUTHOR]

In this paper, we develop a new unified approach for laser radar range anomaly suppression, range profiling, and segmentation. This approach combines an object-based hybrid scene model for representing the range distribution of the field and a statistical mixture model for the range data measurement noise. The image segmentation problem is formulated as a minimization problem which jointly estimates the target boundary together with the target region range variation and background range variation directly from the noisy and anomaly-filled range data. This formulation allows direct incorporation of prior information concerning the target boundary, target ranges, and background ranges into an optimal reconstruction process. Curve evolution techniques and a generalized expectation-maximization algorithm are jointly employed as an efficient solver for minimizing the objective energy, resulting in a coupled pair of object and intensity optimization tasks. The method directly and optimally extracts the target boundary, avoiding a suboptimal two-step process involving image smoothing followed by boundary extraction. Experiments are presented demonstrating that the proposed approach is robust to anomalous pixels (missing data) and capable of producing accurate estimation of the target boundary and range values from noisy data. [ABSTRACT FROM AUTHOR]

Kernel regression is an effective tool for a variety of image processing tasks such as denoising and interpolation [1]. In this paper, we extend the use of kernel regression for deblurring applications. In some earlier examples in the literature, such nonparametric deblurring was suboptimally performed in two sequential steps, namely denoising followed by deblurring. In contrast, our optimal solution jointly denoises and deblurs images. The proposed algorithm takes advantage of an effective and novel image prior that generalizes some of the most popular regularization techniques in the literature. Experimental results demonstrate the effectiveness of our method. [ABSTRACT FROM AUTHOR]

This paper presents a unified solution to three unsolved problems existing in face verification with subspace learning techniques: selection of verification threshold, automatic determination of subspace dimension, and deducing feature fusing weights. In contrast to previous algorithms which search for the projection matrix directly, our new algorithm investigates a similarity metric matrix (SMM). With a certain verification threshold, this matrix is learned by a semidefinite programming approach, along with the constraints of the kindred pairs with similarity larger than the threshold, and inhomogeneous pairs with similarity smaller than the threshold. Then, the subspace dimension and the feature fusing weights are simultaneously inferred from the singular value decomposition of the derived SMM. In addition, the weighted and tensor extensions are proposed to further improve the algorithmic effectiveness and efficiency, respectively. Essentially, the verification is conducted within an affine subspace in this new algorithm and is, hence, called the affine subspace for verification (ASV). Extensive experiments show that the ASV can achieve encouraging face verification accuracy in comparison to other subspace algorithms, even without the need to explore any parameters. [ABSTRACT FROM AUTHOR]

This paper studies image deblurring problems using a total variation-based model, with a non-negativity constraint. The addition of the non-negativity constraint improves the quality of the solutions, but makes the solution process a difficult one. The contribution of our work is a fast and robust numerical algorithm to solve the non-negatively constrained problem. To overcome the nondifferentiability of the total variation norm, we formulate the constrained deblurring problem as a primal-dual program which is a variant of the formulation proposed by Chan, Golub, and Mulet for unconstrained problems. Here, dual refers to a combination of the Lagrangian and Fenchel duals. To solve the constrained primal-dual program, we use a semi-smooth Newton's method. We exploit the relationship between the semi-smooth Newton's method and the primal-dual active set method to achieve considerable simplification of the computations. The main advantages of our proposed scheme are: no parameters need significant adjustment, a standard inverse preconditioner works very well, quadratic rate of local convergence (theoretical and numerical), numerical evidence of global convergence, and high accuracy of solving the optimality system. The scheme shows robustness of performance over a wide range of parameters. A comprehensive set of numerical comparisons are provided against other methods to solve the same problem which show the speed and accuracy advantages of our scheme. [ABSTRACT FROM AUTHOR]

This paper addresses the problem of image segmentation by means of active contours, whose evolution is driven by the gradient flow derived from an energy functional that is based on the Bhattacharyya distance. In particular, given the values of a photo- metric variable (or of a set thereof), which is to be used for classifying the image pixels, the active contours are designed to converge to the shape that results in maximal discrepancy between the empirical distributions of the photometric variable inside and outside of the contours. The above discrepancy is measured by means of the Bhattacharyya distance that proves to be an extremely useful tool for solving the problem at hand. The proposed methodology can be viewed as a generalization of the segmentation methods, in which active contours maximize the difference between a finite number of empirical moments of the ‘inside’ and ‘outside’ distributions. Furthermore, it is shown that the proposed methodology is very versatile and flexible in the sense that it allows one to easily accommodate a diversity of the image features based on which the segmentation should be performed. As an additional contribution, a method for automatically adjusting the smoothness properties of the empirical distributions is proposed. Such a procedure is crucial in situations when the number of data samples (supporting a certain segmentation class) varies considerably in the course of the evolution of the active contour. In this case, the smoothness properties of the empirical distributions have to be properly adjusted to avoid either over-or underestimation artifacts. Finally, a number of relevant segmentation results are demonstrated and some further research directions are discussed. [ABSTRACT FROM AUTHOR]

This paper presents a new algorithm based on the Mumford-Shah model for simultaneously detecting the edge features of two images and jointly estimating a consistent set of transformations to match them. Compared to the current asymmetric methods in the literature, this fully symmetric method allows one to determine one-to-one correspondences between the edge features of two images. The entire variational model is realized in a multiscale framework of the finite element approximation. The optimization process is guided by an estimation minimization-type algorithm and an adaptive generalized gradient flow to guarantee a fast and smooth relaxation. The algorithm is tested on Ti and T2 magnetic resonance image data to study the parameter setting. We also present promising results of four applications of the proposed algorithm: interobject monomodal registration, retinal image registration, matching digital photographs of neurosurgery with its volume data, and motion estimation for frame interpolation. [ABSTRACT FROM AUTHOR]

This paper introduces a new edge-grouping method to detect perceptually salient structures in noisy images. Specifically, we define a new grouping cost function in a ratio form, where the numerator measures the boundary proximity of the resulting structure and the denominator measures the area of the resulting structure. This area term introduces a preference towards detecting larger-size structures and, therefore, makes the resulting edge grouping more robust to image noise. To find the optimal edge grouping with the minimum grouping cost, we develop a special graph model with two different kinds of edges and then reduce the grouping problem to finding a special kind of cycle in this graph with a minimum cost in ratio form. This optimal cycle-finding problem can be solved in polynomial time by a previously developed graph algorithm. We implement this edge-grouping method, test it on both synthetic data and real images, and compare its performance against several available edge-grouping and edge-linking methods. Furthermore, we discuss several extensions of the proposed method, including the incorporation of the well-known grouping cues of continuity and intensity homogeneity, introducing a factor to balance the contributions from the boundary and region information, and the prevention of detecting self-intersecting boundaries. [ABSTRACT FROM AUTHOR]

Color constancy is the ability to measure colors of objects independent of the color of the light source. A well-known color constancy method is based on the gray-world assumption which assumes that the average reflectance of surfaces in the world is achromatic. In this paper, we propose a new hypothesis for color constancy namely the gray-edge hypothesis, which assumes that the average edge difference in a scene is achromatic. Based on this hypothesis, we propose an algorithm for color constancy. Contrary to existing color constancy algorithms, which are computed from the zero-order structure of images, our method is based on the derivative structure of images. Furthermore, we propose a framework which unifies a variety of known (gray-world, max-RGB, Minkowski norm) and the newly proposed gray-edge and higher order gray-edge algorithms. The quality of the various instantiations of the framework is tested and compared to the state-of-the-art color constancy methods on two large data sets of images recording objects under a large number of different light sources. The experiments show that the proposed color constancy algorithms obtain comparable results as the state-of-the-art color constancy methods with the merit of being computationally more efficient. [ABSTRACT FROM AUTHOR]

Snakes, or active contours, have been widely used in image processing applications. Typical roadblocks to consistent performance include limited capture range, noise sensitivity, and poor convergence to concavities. This paper proposes a new external force for active contours, called vector field convolution (VFC), to address these problems. VFC is calculated by convolving the edge map generated from the image with the user-defined vector field kernel. We propose two structures for the magnitude function of the vector field kernel, and we provide an analytical method to estimate the parameter of the magnitude function. Mixed VFC is introduced to alleviate the possible leakage problem caused by choosing inappropriate parameters. We also demonstrate that the standard external force and the gradient vector flow (GVF) external force are special cases of VFC in certain scenarios. Examples and comparisons with GVF are presented in this paper to show the advantages of this innovation, including superior noise robustness, reduced computational cost, and the flexibility of tailoring the force field. [ABSTRACT FROM AUTHOR]

This paper proposes a novel algorithm for an optimal reduction of object description for object matching purposes. Our aim is to decrease the computation needs by considering simplified objects, thus reducing the number of pixels involved in the matching process. We develop the appropriate theoretical background based on centroidal Voronoi tessellations. Its use within the chamfer matching framework is also discussed. We present experimental results regarding the performance of this approach for 2-D contour and region-like object matching. As a special case, we investigate how the snake based representation of target objects can be employed in chamfer matching. The experimental results concern the use of object part matching for recognizing humans and show how the proposed simplification leads to valid replacements of the original templates. [ABSTRACT FROM AUTHOR]

In this paper, an innovative joint-source channel coding scheme is presented. The proposed approach enables iterative soft decoding of arithmetic codes by means of a soft-in soft-out decoder based on suboptimal search and pruning of a binary tree. An error-resilient arithmetic coder with a forbidden symbol is used in order to improve the performance of the joint source/channel scheme. The performance in the case of transmission across the AWGN channel is evaluated in terms of word error probability and compared to a traditional separated approach. The interleaver gain, the convergence property of the system, and the optimal source/channel rate allocation are investigated. Finally, the practical relevance of the proposed joint decoding approach is demonstrated within the JPEG 2000 coding standard. In particular, an iterative channel and JPEG 2000 decoder is designed and tested in the case of image transmission across the AWGN channel. [ABSTRACT FROM AUTHOR]

This paper presents a novel approach for creation of topographical function and object markers used within watershed segmentation. Typically, marker-driven watershed segmentation extracts seeds indicating the presence of objects or background at specific image locations. The marker locations are then set to be regional minima within the topological surface (typically, the gradient of the original input image), and the watershed algorithm is applied. In contrast, our approach uses two classifiers, one trained to produce markers, the other trained to produce object boundaries. As a result of using machine-learned pixel classification, the proposed algorithm is directly applicable to both single channel and multichannel image data. Additionally, rather than flooding the gradient image, we use the inverted probability map produced by the second aforementioned classifier as input to the watershed algorithm. Experimental results demonstrate the superior performance of the classification-driven watershed segmentation algorithm for the tasks of 1) image-based granulometry and 2) remote sensing. [ABSTRACT FROM AUTHOR]

This paper presents a new approach to automatic segmentation of foreground objects from an image sequence by integrating techniques of background subtraction and motion-based foreground segmentation. First, a region-based motion segmentation algorithm is proposed to obtain a set of motion-coherence regions and the correspondence among regions at different time instants. Next, we formulate the classification problem as a graph labeling over a region adjacency graph based on Markov random fields (MRFs) statistical framework. A background model representing the background scene is built and then is used to model a likelihood energy. Besides the background model, a temporal coherence is also maintained by modeling it as the prior energy. On the other hand, color distributions of two neighboring regions are taken into consideration to impose spatial coherence. Then, the a priori energy of MRFs takes both spatial and temporal coherence into account to maintain the continuity of our segmentation. Finally, a labeling is obtained by maximizing the a posteriori energy of the MRFs. Under such formulation, we integrate two different kinds of techniques in an elegant way to make the foreground detection more accurate. Experimental results for several video sequences are provided to demonstrate the effectiveness of the proposed approach. [ABSTRACT FROM AUTHOR]