Search

During recent years, blind image quality assessment (BIQA) has been intensively studied with different machine learning tools. Existing BIQA metrics, however, do not design for stereoscopic images. We believe this problem can be resolved by separating 3D images and capturing the essential attributes of images via deep neural network. In this paper, we propose a blind deep quality evaluator (DQE) for stereoscopic images (denoted by 3D-DQE) based on monocular and binocular interactions. The key technical steps in the proposed 3D-DQE are to train two separate 2D deep neural networks (2D-DNNs) from 2D monocular images and cyclopean images to model the process of monocular and binocular quality predictions, and combine the measured 2D monocular and cyclopean quality scores using different weighting schemes. Experimental results on four public 3D image quality assessment databases demonstrate that in comparison with the existing methods, the devised algorithm achieves high consistent alignment with subjective assessment. [ABSTRACT FROM AUTHOR]

This paper presents a new Bayesian model and algorithm used for depth and reflectivity profiling using full waveforms from the time-correlated single-photon counting measurement in the limit of very low photon counts. The proposed model represents each Lidar waveform as a combination of a known impulse response, weighted by the target reflectivity, and an unknown constant background, corrupted by Poisson noise. Prior knowledge about the problem is embedded through prior distributions that account for the different parameter constraints and their spatial correlation among the image pixels. In particular, a gamma Markov random field (MRF) is used to model the joint distribution of the target reflectivity, and a second MRF is used to model the distribution of the target depth, which are both expected to exhibit significant spatial correlations. An adaptive Markov chain Monte Carlo algorithm is then proposed to perform Bayesian inference. This algorithm is equipped with a stochastic optimization adaptation mechanism that automatically adjusts the parameters of the MRFs by maximum marginal likelihood estimation. Finally, the benefits of the proposed methodology are demonstrated through a series of experiments using real data. [ABSTRACT FROM AUTHOR]

In this paper, we propose an extremely efficient algorithm for visual re-ranking. By considering the original pairwise distance in the contextual space, we develop a feature vector called sparse contextual activation (SCA) that encodes the local distribution of an image. Hence, re-ranking task can be simply accomplished by vector comparison under the generalized Jaccard metric, which has its theoretical meaning in the fuzzy set theory. In order to improve the time efficiency of re-ranking procedure, inverted index is successfully introduced to speed up the computation of generalized Jaccard metric. As a result, the average time cost of re-ranking for a certain query can be controlled within 1 ms. Furthermore, inspired by query expansion, we also develop an additional method called local consistency enhancement on the proposed SCA to improve the retrieval performance in an unsupervised manner. On the other hand, the retrieval performance using a single feature may not be satisfactory enough, which inspires us to fuse multiple complementary features for accurate retrieval. Based on SCA, a robust feature fusion algorithm is exploited that also preserves the characteristic of high time efficiency. We assess our proposed method in various visual re-ranking tasks. Experimental results on Princeton shape benchmark (3D object), WM-SRHEC07 (3D competition), YAEL data set B (face), MPEG-7 data set (shape), and Ukbench data set (image) manifest the effectiveness and efficiency of SCA. [ABSTRACT FROM AUTHOR]

There exist a significant number of benchmarks for evaluating the performance of boundary detection algorithms, most of them relying on some sort of comparison of the automatically-generated boundaries with human-labeled ones. Such benchmarks are composed of a representative image data set, as well as a comparison measure on the universe of boundary images. Despite many such data sets and measures have been proposed, there is no clear way of knowing which combinations of them are the most suitable for the task. In this paper, we introduce four criteria that allow for a sensible evaluation of the performance of a comparison measure on a given data set. The criteria mimic the way in which humans understand boundary images, as well as their ability to recognize the underlying scenes. These criteria can, as a final goal, quantify the ability of the boundary detection benchmarks to evaluate the performance of boundary detection methods, either edge-based or segmentation-based. [ABSTRACT FROM AUTHOR]

In this paper, we introduce a novel approach to automatically detect salient regions in an image. Our approach consists of global and local features, which complement each other to compute a saliency map. The first key idea of our work is to create a saliency map of an image by using a linear combination of colors in a high-dimensional color space. This is based on an observation that salient regions often have distinctive colors compared with backgrounds in human perception, however, human perception is complicated and highly nonlinear. By mapping the low-dimensional red, green, and blue color to a feature vector in a high-dimensional color space, we show that we can composite an accurate saliency map by finding the optimal linear combination of color coefficients in the high-dimensional color space. To further improve the performance of our saliency estimation, our second key idea is to utilize relative location and color contrast between superpixels as features and to resolve the saliency estimation from a trimap via a learning-based algorithm. The additional local features and learning-based algorithm complement the global estimation from the high-dimensional color transform-based algorithm. The experimental results on three benchmark datasets show that our approach is effective in comparison with the previous state-of-the-art saliency estimation methods. [ABSTRACT FROM PUBLISHER]

Hashing has attracted increasing research attention in recent years due to its high efficiency of computation and storage in image retrieval. Recent works have demonstrated the superiority of simultaneous feature representations and hash functions learning with deep neural networks. However, most existing deep hashing methods directly learn the hash functions by encoding the global semantic information, while ignoring the local spatial information of images. The loss of local spatial structure makes the performance bottleneck of hash functions, therefore limiting its application for accurate similarity retrieval. In this paper, we propose a novel deep ordinal hashing (DOH) method, which learns ordinal representations to generate ranking-based hash codes by leveraging the ranking structure of feature space from both local and global views. In particular, to effectively build the ranking structure, we propose to learn the rank correlation space by exploiting the local spatial information from fully convolutional network and the global semantic information from the convolutional neural network simultaneously. More specifically, an effective spatial attention model is designed to capture the local spatial information by selectively learning well-specified locations closely related to target objects. In such hashing framework, the local spatial and global semantic nature of images is captured in an end-to-end ranking-to-hashing manner. Experimental results conducted on three widely used datasets demonstrate that the proposed DOH method significantly outperforms the state-of-the-art hashing methods. [ABSTRACT FROM AUTHOR]

As one of the most widely used clustering techniques, the fuzzy $k$ -means (FKM) assigns every data point to each cluster with a certain degree of membership. However, conventional FKM approach relies on the square data fitting term, which is sensitive to the outliers with ignoring the prior information. In this paper, we develop a novel and robust fuzzy $k$ -means clustering algorithm, namely, joint learning of fuzzy $k$ -means and nonnegative spectral clustering with side information. The proposed method combines fuzzy $k$ -means and nonnegative spectral clustering into a unified model, which can further exploit the prior knowledge of data pairs such that both the quality of affinity graph and the clustering performance can be improved. In addition, for the purpose of enhancing the robustness, the adaptive loss function is adopted in the objective function, since it smoothly interpolates between $\ell _{1}$ -norm and $\ell _{2}$ -norm. Finally, experimental results on benchmark datasets verify the effectiveness and the superiority of our clustering method. [ABSTRACT FROM AUTHOR]

Fractional interpolation is used to provide sub-pixel level references for motion compensation in the interprediction of video coding, which attempts to remove temporal redundancy in video sequences. Traditional handcrafted fractional interpolation filters face the challenge of modeling discontinuous regions in videos, while existing deep learning-based methods are either designed for a single quantization parameter (QP), only generating half-pixel samples, or need to train a model for each sub-pixel position. In this paper, we present a one-for-all fractional interpolation method based on a grouped variation convolutional neural network (GVCNN). Our method can deal with video frames coded using different QPs and is capable of generating all sub-pixel positions at one sub-pixel level. Also, by predicting variations between integer-position pixels and sub-pixels, our network offers more expressive power. Moreover, we perform specific measurements in training data generation to simulate practical situations in video coding, including blurring the down-sampled sub-pixel samples to avoid aliasing effects and coding integer pixels to simulate reconstruction errors. In addition, we analyze the impact of the size of blur kernels theoretically. Experimental results verify the efficiency of GVCNN. Compared with HEVC, our method achieves 2.2% in bit saving on average and up to 5.2% under low-delay P configuration. [ABSTRACT FROM AUTHOR]

Deep convolutional neural networks (CNNs) have revolutionized the computer vision research and have seen unprecedented adoption for multiple tasks, such as classification, detection, and caption generation. However, they offer little transparency into their inner workings and are often treated as black boxes that deliver excellent performance. In this paper, we aim at alleviating this opaqueness of CNNs by providing visual explanations for the network’s predictions. Our approach can analyze a variety of CNN-based models trained for computer vision applications, such as object recognition and caption generation. Unlike the existing methods, we achieve this via unraveling the forward pass operation. The proposed method exploits feature dependencies across the layer hierarchy and uncovers the discriminative image locations that guide the network’s predictions. We name these locations CNN fixations, loosely analogous to human eye fixations. Our approach is a generic method that requires no architectural changes, additional training, or gradient computation, and computes the important image locations (CNN fixations). We demonstrate through a variety of applications that our approach is able to localize the discriminative image locations across different network architectures, diverse vision tasks, and data modalities. [ABSTRACT FROM AUTHOR]

To meet the required huge data analysis, organization, and storage demand, the hashing technique has got a lot of attention as it aims to learn an efficient binary representation from the original high-dimensional data. In this paper, we focus on the unsupervised spectral hashing due to its effective manifold embedding. Existing spectral hashing methods mainly suffer from two problems, i.e., the inefficient spectral candidate and intractable binary constraint for spectral analysis. To overcome these two problems, we propose to employ spectral rotation to seek a better spectral solution and adopt the alternating projection algorithm to settle the complex code constraints, which are therefore named as Spectral Hashing with Spectral Rotation and Alternating Discrete Spectral Hashing, respectively. To enjoy the merits of both methods, the spectral rotation technique is finally combined with the original spectral objective, which aims to simultaneously learn better spectral solution and more efficient discrete codes and is called as Discrete Spectral Hashing. Furthermore, the efficient optimization algorithms are also provided, which just take comparable time complexity to existing hashing methods. To evaluate the proposed three methods, extensive comparison experiments and studies are conducted on four large-scale data sets for the image retrieval task, and the noticeable performance beats several state-of-the-art spectral hashing methods on different evaluation metrics. [ABSTRACT FROM AUTHOR]

In this paper, we propose a novel depth restoration algorithm from RGB-D data through combining characteristics of local and non-local manifolds, which provide low-dimensional parameterizations of the local and non-local geometry of depth maps. Specifically, on the one hand, a local manifold model is defined to favor local neighboring relationship of pixels in depth, according to which, manifold regularization is introduced to promote smoothing along the manifold structure. On the other hand, the non-local characteristics of the patch-based manifold can be used to build highly data-adaptive orthogonal bases to extract elongated image patterns, accounting for self-similar structures in the manifold. We further define a manifold thresholding operator in 3D adaptive orthogonal spectral bases—eigenvectors of the discrete Laplacian of local and non-local manifolds—to retain only low graph frequencies for depth maps restoration. Finally, we propose a unified alternating direction method of multipliers optimization framework, which elegantly casts the adaptive manifold regularization and thresholding jointly to regularize the inverse problem of depth maps recovery. Experimental results demonstrate that our method achieves superior performance compared with the state-of-the-art works with respect to both objective and subjective quality evaluations. [ABSTRACT FROM AUTHOR]

Reflection symmetry detection receives increasing attentions in recent years. The state-of-the-art algorithms mainly use the matching of intensity-based features (such as the SIFT) within a single image to find symmetry axes. This paper proposes a novel approach by establishing the correspondence of locally affine invariant edge-based features, which are superior to the intensity based in the aspects that it is insensitive to illumination variations, and applicable to textureless objects. The locally affine invariance is achieved by simple linear algebra for efficient and robust computations, making the algorithm suitable for detections under object distortions like perspective projection. Commonly used edge detectors and a voting process are, respectively, used before and after the edge description and matching steps to form a complete reflection detection pipeline. Experiments are performed using synthetic and real-world images with both multiple and single reflection symmetry axis. The test results are compared with existing algorithms to validate the proposed method. [ABSTRACT FROM PUBLISHER]

Transmitting compactly represented geometry of a dynamic 3D scene from a sender can enable a multitude of imaging functionalities at a receiver, such as synthesis of virtual images at freely chosen viewpoints via depth-image-based rendering. While depth maps—projections of 3D geometry onto 2D image planes at chosen camera viewpoints—can nowadays be readily captured by inexpensive depth sensors, they are often corrupted by non-negligible acquisition noise. Given depth maps need to be denoised and compressed at the encoder for efficient network transmission to the decoder, in this paper, we consider the denoising and compression problems jointly, arguing that doing so will result in a better overall performance than the alternative of solving the two problems separately in two stages. Specifically, we formulate a rate-constrained estimation problem, where given a set of observed noise-corrupted depth maps, the most probable (maximum a posteriori (MAP)) 3D surface is sought within a search space of surfaces with representation size no larger than a prespecified rate constraint. Our rate-constrained MAP solution reduces to the conventional unconstrained MAP 3D surface reconstruction solution if the rate constraint is loose. To solve our posed rate-constrained estimation problem, we propose an iterative algorithm, where in each iteration the structure (object boundaries) and the texture (surfaces within the object boundaries) of the depth maps are optimized alternately. Using the MVC codec for compression of multiview depth video and MPEG free viewpoint video sequences as input, experimental results show that rate-constrained estimated 3D surfaces computed by our algorithm can reduce coding rate of depth maps by up to 32% compared with unconstrained estimated surfaces for the same quality of synthesized virtual views at the decoder. [ABSTRACT FROM AUTHOR]

Algorithms for fully automatic segmentation of images are often not sufficiently generic with suitable accuracy, and fully manual segmentation is not practical in many settings. There is a need for semiautomatic algorithms, which are capable of interacting with the user and taking into account the collected feedback. Typically, such methods have simply incorporated user feedback directly. Here, we employ active learning of optimal queries to guide user interaction. Our work in this paper is based on constrained spectral clustering that iteratively incorporates user feedback by propagating it through the calculated affinities. The original framework does not scale well to large data sets, and hence is not straightforward to apply to interactive image segmentation. In order to address this issue, we adopt advanced numerical methods for eigen-decomposition implemented over a subsampling scheme. Our key innovation, however, is an active learning strategy that chooses pairwise queries to present to the user in order to increase the rate of learning from the feedback. Performance evaluation is carried out on the Berkeley segmentation and Graz-02 image data sets, confirming that convergence to high accuracy levels is realizable in relatively few iterations. [ABSTRACT FROM AUTHOR]

In this paper, we propose a multiple kernel learning (MKL) algorithm that is based on the sparse representation-based classification (SRC) method. Taking advantage of the nonlinear kernel SRC in efficiently representing the nonlinearities in the high-dimensional feature space, we propose an MKL method based on the kernel alignment criteria. Our method uses a two step training method to learn the kernel weights and sparse codes. At each iteration, the sparse codes are updated first while fixing the kernel mixing coefficients, and then the kernel mixing coefficients are updated while fixing the sparse codes. These two steps are repeated until a stopping criteria is met. The effectiveness of the proposed method is demonstrated using several publicly available image classification databases and it is shown that this method can perform significantly better than many competitive image classification algorithms. [ABSTRACT FROM AUTHOR]

In recent years, there has been growing interest in mapping visual features into compact binary codes for applications on large-scale image collections. Encoding high-dimensional data as compact binary codes reduces the memory cost for storage. Besides, it benefits the computational efficiency since the computation of similarity can be efficiently measured by Hamming distance. In this paper, we propose a novel flexible scale invariant feature transform (SIFT) binarization (FSB) algorithm for large-scale image search. The FSB algorithm explores the magnitude patterns of SIFT descriptor. It is unsupervised and the generated binary codes are demonstrated to be dispreserving. Besides, we propose a new searching strategy to find target features based on the cross-indexing in the binary SIFT space and original SIFT space. We evaluate our approach on two publicly released data sets. The experiments on large-scale partial duplicate image retrieval system demonstrate the effectiveness and efficiency of the proposed algorithm. [ABSTRACT FROM AUTHOR]

Depth and surface normal estimation are crucial components in understanding 3D scene geometry from calibrated stereo images. In this paper, we propose visibility and disparity magnitude constraints for slanted patches in the scene. These constraints can be used to associate geometrically feasible planes with each point in the disparity space. The new constraints are validated in the PatchMatch Stereo framework. We use these new constraints not only for initialization, but also in the local plane refinement step of this iterative algorithm. The proposed constraints increase the probability of estimating correct plane parameters, and lead to an improved 3D reconstruction of the scene. Furthermore, the proposed constrained initialization reduces the number of iterations before convergence to the optimal plane parameters. In addition, as most stereo image pairs are not perfectly rectified, we modify the view propagation process by assigning the plane parameters to the neighbors of the candidate pixel. To update the plane parameters in the plane refinement step, we use a gradient free non-linear optimizer. The benefits of the new initialization, propagation, and refinement schemes are demonstrated. [ABSTRACT FROM AUTHOR]

Multi-label problems arise in various domains, including automatic multimedia data categorization, and have generated significant interest in computer vision and machine learning community. However, existing methods do not adequately address two key challenges: exploiting correlations between labels and making up for the lack of labelled data or even missing labelled data. In this paper, we proposed to use a semi-supervised singular value decomposition (SVD) to handle these two challenges. The proposed model takes advantage of the nuclear norm regularization on the SVD to effectively capture the label correlations. Meanwhile, it introduces manifold regularization on mapping to capture the intrinsic structure among data, which provides a good way to reduce the required labelled data with improving the classification performance. Furthermore, we designed an efficient algorithm to solve the proposed model based on the alternating direction method of multipliers, and thus, it can efficiently deal with large-scale data sets. Experimental results for synthetic and real-world multimedia data sets demonstrate that the proposed method can exploit the label correlations and obtain promising and better label prediction results than the state-of-the-art methods. [ABSTRACT FROM PUBLISHER]

In this paper, we propose a novel pixel-level multisensor image fusion algorithm with simultaneous contrast enhancement. In order to accomplish both image fusion and contrast enhancement simultaneously, we suggest a modified framework of the subband-decomposed multiscale retinex (SDMSR), our previous contrast enhancement algorithm. This framework is based on a fusion strategy that reflects the multiscale characteristics of the SDMSR well. We first apply two complementary intensity transfer functions to source images in order to effectively utilize hidden information in both shadows and highlights in the fusion process. We then decompose retinex outputs into nearly nonoverlapping spectral subbands. The decomposed retinex outputs are then fused subband-by-subband, by using global weighting as well as local weighting to overcome the limitations of the pixel-based fusion approach. After the fusion process, we apply a space-varying subband gain to each fused SD retinex output according to the subband characteristic so that the contrast of the fused image can be effectively enhanced. In addition, in order to effectively manage artifacts and noise, we make the degree of enhancement of fused details adjustable by improving a detail adjustment function. From experiments with various multisensor image pairs, the results clearly demonstrate that even if source images have poor contrast, the proposed algorithm makes it possible to generate a fused image with highly enhanced contrast while preserving visually salient information contained in the source images. [ABSTRACT FROM AUTHOR]

In this paper, a weighted similarity-invariant linear algorithm for camera calibration with rotating 1-D objects is proposed. First, we propose a new estimation method for computing the relative depth of the free endpoint on the 1-D object and prove its robustness against noise compared with those used in previous literature. The introduced estimator is invariant to image similarity transforms, resulting in a similarity-invariant linear calibration algorithm which is slightly more accurate than the well-known normalized linear algorithm. Then, we use the reciprocals of the standard deviations of the estimated relative depths from different images as the weights on the constraint equations of the similarity-invariant linear calibration algorithm, and propose a weighted similarity-invariant linear calibration algorithm with higher accuracy. Experimental results on synthetic data as well as on real image data show the effectiveness of our proposed algorithm. [ABSTRACT FROM AUTHOR]

When a catadioptric imaging system suffers from limited depth of field, a single image cannot capture all the objects with clear focus. To solve this problem, a set of multifocal images can be used to extend the depth of the field by fusing the best-focused image regions to an overall well-focused composite image. In this paper, we propose a novel model-based method that avoids the computational cost problem of previous extended-depth-of-field algorithms. On the basis of the special optical geometry properties of catadioptric systems, the proposed model describes the shapes of the best-focused image regions in multifocal images by a series of neighboring concentric annuluses. Then we propose a method to estimate the model parameters. On the basis of this model, an overall well-focused image is obtained by combining the best-focused regions with a fast and reliable online operation. Experiments on catadioptric images of a variety of different scenes and camera settings verify the validity of the model and the robust performance of the proposed method. [ABSTRACT FROM AUTHOR]

In this paper, an algorithm is proposed to extract two illuminant invariant chromaticity features from three image sensor responses. The algorithm extracts these chromaticity features at pixel level and therefore can perform well in scenes illuminated with nonuniform illuminant. An approach is proposed to use the algorithm with cameras of unknown sensitivity. The algorithm was tested for separability of perceptually similar colors under the International Commission on Illumination standard illuminants and obtained a good performance. It was also tested for color-based object recognition by illuminating objects with typical indoor illuminants and obtained a better performance compared to other existing algorithms investigated in this paper. Finally, the algorithm was tested for skin detection invariant to illuminant, ethnic background and imaging device. In this investigation, daylight scenes under different weather conditions and scenes illuminated by typical indoor illuminants were used. The proposed algorithm gives a better skin detection performance compared to widely used standard color spaces. Based on the results presented, the proposed illuminant invariant chromaticity space can be used for machine vision applications including illuminant invariant color-based object recognition and skin detection. [ABSTRACT FROM AUTHOR]

The state-of-the-art interactive image segmentation algorithms are sensitive to the user inputs and often unable to produce an accurate boundary with a small amount of user interaction. They frequently rely on laborious user editing to refine the segmentation boundary. In this paper, we propose a robust and accurate interactive method based on the recently developed continuous-domain convex active contour model. The proposed method exhibits many desirable properties of an effective interactive image segmentation algorithm, including robustness to user inputs and different initializations, the ability to produce a smooth and accurate boundary contour, and the ability to handle topology changes. Experimental results on a benchmark data set show that the proposed tool is highly effective and outperforms the state-of-the-art interactive image segmentation algorithms. [ABSTRACT FROM AUTHOR]

Image restoration is a computationally intensive problem as a large number of pixel values have to be determined. Since the pixel values of digital images can attain only a finite number of values (e.g., 8-bit images can have only 256 gray levels), one would like to recover an image within some dynamic range. This leads to the imposition of box constraints on the pixel values. The traditional gradient projection methods for constrained optimization can be used to impose box constraints, but they may suffer from either slow convergence or repeated searching for active sets in each iteration. In this paper, we develop a new box-constrained multiplicative iterative (BCMI) algorithm for box-constrained image restoration. The BCMI algorithm just requires pixelwise updates in each iteration, and there is no need to invert any matrices. We give the convergence proof of this algorithm and apply it to total variation image restoration problems, where the observed blurry images contain Poisson, Gaussian, or salt-and-pepper noises. [ABSTRACT FROM PUBLISHER]

The performance of dynamic scene algorithms often suffers because of the inability to effectively acquire features on the targets, particularly when they are distributed over a wide field of view. In this paper, we propose an integrated analysis and control framework for a pan, tilt, zoom (PTZ) camera network in order to maximize various scene understanding performance criteria (e.g., tracking accuracy, best shot, and image resolution) through dynamic camera-to-target assignment and efficient feature acquisition. Moreover, we consider the situation where processing is distributed across the network since it is often unrealistic to have all the image data at a central location. In such situations, the cameras, although autonomous, must collaborate among themselves because each camera's PTZ parameter entails constraints on the others. Motivated by recent work in cooperative control of sensor networks, we propose a distributed optimization strategy, which can be modeled as a game involving the cameras and targets. The cameras gain by reducing the error covariance of the tracked targets or through higher resolution feature acquisition, which, however, comes at the risk of losing the dynamic target. Through the optimization of this reward-versus-risk tradeoff, we are able to control the PTZ parameters of the cameras and assign them to targets dynamically. The tracks, upon which the control algorithm is dependent, are obtained through a consensus estimation algorithm whereby cameras can arrive at a consensus on the state of each target through a negotiation strategy. We analyze the performance of this collaborative sensing strategy in active camera networks in a simulation environment, as well as a real-life camera network. [ABSTRACT FROM PUBLISHER]

This paper presents a 3-D near-field imaging algorithm that is formulated for 2-D wideband multiple-input–multiple-output (MIMO) imaging array topology. The proposed MIMO range migration technique performs the image reconstruction procedure in the frequency–wavenumber domain. The algorithm is able to completely compensate the curvature of the wavefront in the near-field through a specifically defined interpolation process and provides extremely high computational efficiency by the application of the fast Fourier transform. The implementation aspects of the algorithm and the sampling criteria of a MIMO aperture are discussed. The image reconstruction performance and computational efficiency of the algorithm are demonstrated both with numerical simulations and measurements using 2-D MIMO arrays. Real-time 3-D near-field imaging can be achieved with a real-aperture array by applying the proposed MIMO range migration techniques. [ABSTRACT FROM AUTHOR]

This paper presents a nonlinear mixing model for hyperspectral image unmixing. The proposed model assumes that the pixel reflectances are nonlinear functions of pure spectral components contaminated by an additive white Gaussian noise. These nonlinear functions are approximated using polynomial functions leading to a polynomial postnonlinear mixing model. A Bayesian algorithm and optimization methods are proposed to estimate the parameters involved in the model. The performance of the unmixing strategies is evaluated by simulations conducted on synthetic and real data. [ABSTRACT FROM AUTHOR]

Exploring context information for visual recognition has recently received significant research attention. This paper proposes a novel and highly efficient approach, which is named semantic diffusion, to utilize semantic context for large-scale image and video annotation. Starting from the initial annotation of a large number of semantic concepts (categories), obtained by either machine learning or manual tagging, the proposed approach refines the results using a graph diffusion technique, which recovers the consistency and smoothness of the annotations over a semantic graph. Different from the existing graph-based learning methods that model relations among data samples, the semantic graph captures context by treating the concepts as nodes and the concept affinities as the weights of edges. In particular, our approach is capable of simultaneously improving annotation accuracy and adapting the concept affinities to new test data. The adaptation provides a means to handle domain change between training and test data, which often occurs in practice. Extensive experiments are conducted to improve concept annotation results using Flickr images and TV program videos. Results show consistent and significant performance gain (10+\% on both image and video data sets). Source codes of the proposed algorithms are available online. [ABSTRACT FROM AUTHOR]

In this paper, we introduce a digital implementation of the 3-D shearlet transform and illustrate its application to problems of video denoising and enhancement. The shearlet representation is a multiscale pyramid of well-localized waveforms defined at various locations and orientations, which was introduced to overcome the limitations of traditional multiscale systems in dealing with multidimensional data. While the shearlet approach shares the general philosophy of curvelets and surfacelets, it is based on a very different mathematical framework, which is derived from the theory of affine systems and uses shearing matrices rather than rotations. This allows a natural transition from the continuous setting to the digital setting and a more flexible mathematical structure. The 3-D digital shearlet transform algorithm presented in this paper consists in a cascade of a multiscale decomposition and a directional filtering stage. The filters employed in this decomposition are implemented as finite-length filters, and this ensures that the transform is local and numerically efficient. To illustrate its performance, the 3-D discrete shearlet transform is applied to problems of video denoising and enhancement, and compared against other state-of-the-art multiscale techniques, including curvelets and surfacelets. [ABSTRACT FROM AUTHOR]

Dual-energy computerized tomography has gained great interest because of its ability to characterize the chemical composition of a material rather than simply providing relative attenuation images as in conventional tomography. The purpose of this paper is to introduce a novel polychromatic dual-energy processing algorithm, with an emphasis on detection and characterization of piecewise constant objects embedded in an unknown cluttered background. Physical properties of the objects, particularly the Compton scattering and photoelectric absorption coefficients, are assumed to be known with some level of uncertainty. Our approach is based on a level-set representation of the characteristic function of the object and encompasses a number of regularization techniques for addressing both the prior information we have concerning the physical properties of the object and the fundamental physics-based limitations associated with our ability to jointly recover the Compton scattering and photoelectric absorption properties of the scene. In the absence of an object with appropriate physical properties, our approach returns a null characteristic function and, thus, can be viewed as simultaneously solving the detection and characterization problems. Unlike the vast majority of methods that define the level-set function nonparametrically, i.e., as a dense set of pixel values, we define our level set parametrically via radial basis functions and employ a Gauss–Newton-type algorithm for cost minimization. Numerical results show that the algorithm successfully detects objects of interest, finds their shape and location, and gives an adequate reconstruction of the background. [ABSTRACT FROM PUBLISHER]

Fast mode decision algorithms have been widely used in the video encoder implementation to reduce encoding complexity yet without much sacrifice in the coding performance. Optimal stopping theory, which addresses early termination for a generic class of decision problems, is adopted in this paper to achieve fast mode decision for the H.264/Scalable Video Coding standard. A constrained model is developed with optimal stopping, and the solutions to this model are employed to initialize the candidate mode list and predict the early termination. Comprehensive simulation results are conducted to demonstrate that the proposed method strikes a good balance between low encoding complexity and high coding efficiency. [ABSTRACT FROM PUBLISHER]

Autofocus algorithms are used to restore images in nonideal synthetic aperture radar imaging systems. In this paper, we propose a bilinear parametric model for the unknown image and the nuisance phase parameters and derive an efficient maximum-likelihood autofocus (MLA) algorithm. In the special case of a simple image model and a narrow range of look angles, MLA coincides with the successful multichannel autofocus (MCA). MLA can be interpreted as a generalization of MCA to a larger class of models with a larger range of look angles. We analyze its advantages over previous extensions of MCA in terms of identifiability conditions and noise sensitivity. As a byproduct, we also propose numerical approximations to the difficult constant modulus quadratic program that lies at the core of these algorithms. We demonstrate the superior performance of our proposed methods using computer simulations in both the correct and mismatched system models. MLA performs better than other methods, both in terms of the mean squared error and visual quality of the restored image. [ABSTRACT FROM PUBLISHER]

A joint model of scalable video coding (SVC) uses exhaustive mode and motion searches to select the best prediction mode and motion vector for each macroblock (MB) with high coding efficiency at the cost of computational complexity. If major characteristics of a coding MB such as the complexity of the prediction mode and the motion property can be identified and used in adjusting motion estimation (ME), one can design an algorithm that can adapt coding parameters to the video content. This way, unnecessary mode and motion searches can be avoided. In this paper, we propose a content-adaptive ME for SVC, including analyses of mode complexity and motion property to assist mode and motion searches. An experimental analysis is performed to study interlayer and spatial correlations in the coding information. Based on the correlations, the motion and mode characteristics of the current MB are identified and utilized to adjust each step of ME at the enhancement layer including mode decision, search-range selection, and prediction direction selection. Experimental results show that the proposed algorithm can significantly reduce the computational complexity of SVC while maintaining nearly the same rate distortion performance as the original encoder. [ABSTRACT FROM PUBLISHER]

One of the most important issues for researchers developing image processing algorithms is image quality. Methodical quality evaluation, by showing images to several human observers, is slow, expensive, and highly subjective. On the other hand, a visual quality matrix (VQM) is a fast, cheap, and objective tool for evaluating image quality. Although most VQMs are good in predicting the quality of an image degraded by a single degradation, they poorly perform for a combination of two degradations. An example for such degradation is the color crosstalk (CTK) effect, which introduces blur with desaturation. CTK is expected to become a bigger issue in image quality as the industry moves toward smaller sensors. In this paper, we will develop a VQM that will be able to better evaluate the quality of an image degraded by a combined blur/desaturation degradation and perform as well as other VQMs on single degradations such as blur, compression, and noise. We show why standard scalar techniques are insufficient to measure a combined blur/desaturation degradation and explain why a vectorial approach is better suited. We introduce quaternion image processing (QIP), which is a true vectorial approach and has many uses in the fields of physics and engineering. Our new VQM is a vectorial expansion of structure similarity using QIP, which gave it its name—Quaternion Structural SIMilarity (QSSIM). We built a new database of a combined blur/desaturation degradation and conducted a quality survey with human subjects. An extensive comparison between QSSIM and other VQMs on several image quality databases—including our new database—shows the superiority of this new approach in predicting visual quality of color images. [ABSTRACT FROM AUTHOR]

Segmenting semantically meaningful whole objects from images is a challenging problem, and it becomes especially so without higher level common sense reasoning. In this paper, we present an interactive segmentation framework that integrates image appearance and boundary constraints in a principled way to address this problem. In particular, we assume that small sets of pixels, which are referred to as seed pixels, are labeled as the object and background. The seed pixels are used to estimate the labels of the unlabeled pixels using Dirichlet process multiple-view learning, which leverages 1) multiple-view learning that integrates appearance and boundary constraints and 2) Dirichlet process mixture-based nonlinear classification that simultaneously models image features and discriminates between the object and background classes. With the proposed learning and inference algorithms, our segmentation framework is experimentally shown to produce both quantitatively and qualitatively promising results on a standard dataset of images. In particular, our proposed framework is able to segment whole objects from images given insufficient seeds. [ABSTRACT FROM AUTHOR]

Image formation algorithms in a variety of applications have explicit or implicit dependence on a mathematical model of the observation process. Inaccuracies in the observation model may cause various degradations and artifacts in the reconstructed images. The application of interest in this paper is synthetic aperture radar (SAR) imaging, which particularly suffers from motion-induced model errors. These types of errors result in phase errors in SAR data, which cause defocusing of the reconstructed images. Particularly focusing on imaging of fields that admit a sparse representation, we propose a sparsity-driven method for joint SAR imaging and phase error correction. Phase error correction is performed during the image formation process. The problem is set up as an optimization problem in a nonquadratic regularization-based framework. The method involves an iterative algorithm, where each iteration of which consists of consecutive steps of image formation and model error correction. Experimental results show the effectiveness of the approach for various types of phase errors, as well as the improvements that it provides over existing techniques for model error compensation in SAR. [ABSTRACT FROM AUTHOR]

Rain removal from a video is a challenging problem and has been recently investigated extensively. Nevertheless, the problem of rain removal from a single image was rarely studied in the literature, where no temporal information among successive images can be exploited, making the problem very challenging. In this paper, we propose a single-image-based rain removal framework via properly formulating rain removal as an image decomposition problem based on morphological component analysis. Instead of directly applying a conventional image decomposition technique, the proposed method first decomposes an image into the low- and high-frequency (HF) parts using a bilateral filter. The HF part is then decomposed into a “rain component” and a “nonrain component” by performing dictionary learning and sparse coding. As a result, the rain component can be successfully removed from the image while preserving most original image details. Experimental results demonstrate the efficacy of the proposed algorithm. [ABSTRACT FROM AUTHOR]

In this paper, we investigate the issues over the smooth quality and the smooth bit rate during rate control (RC) in H.264/AVC. An adaptive quantization-parameter (Qp) clip scheme is proposed to optimize the quality smoothness while keeping the bit-rate fluctuation at an acceptable level. First, the frame complexity variation is studied by defining a complexity ratio between two nearby frames. Second, the range of the generated bits is analyzed to prevent the encoder buffer from overflow and underflow. Third, based on the safe range of the generated bits, an optimal Qp clip range is developed to reduce the quality fluctuation. Experimental results demonstrate that the proposed Qp clip scheme can achieve excellent performance in quality smoothness and buffer regulation. [ABSTRACT FROM AUTHOR]

Most existing nonblind image deblurring methods assume that the blur kernel is free of error. However, it is often unavoidable in practice that the input blur kernel is erroneous to some extent. Sometimes, the error could be severe, e.g., for images degraded by nonuniform motion blurring. When an inaccurate blur kernel is used as the input, significant distortions will appear in the image recovered by existing methods. In this paper, we present a novel convex minimization model that explicitly takes account of error in the blur kernel. The resulting minimization problem can be efficiently solved by the so-called accelerated proximal gradient method. In addition, a new boundary extension scheme is incorporated in the proposed model to further improve the results. The experiments on both synthesized and real images showed the efficiency and robustness of our algorithm to both the image noise and the model error in the blur kernel. [ABSTRACT FROM AUTHOR]

This paper proposes a new approach to the image blind super-resolution (BSR) problem in the case of affine interframe motion. Although the tasks of image registration, blur identification, and high-resolution (HR) image reconstruction are coupled in the imaging process, when dealing with nonisometric interframe motion or without the exact knowledge of the blurring process, classic SR techniques generally have to tackle them (maybe in some combinations) separately. The main difficulty is that state-of-the-art deconvolution methods cannot be straightforwardly generalized to cope with the space-variant motion. We prove that the operators of affine warping and blur commute with some additional transforms and derive an equivalent form of the BSR observation model. Using this equivalent form, we develop an iterative algorithm to jointly estimate the triple-coupled variables, i.e., the motion parameters, blur kernels, and HR image. Experiments on synthetic and real-life images illustrate the performance of the proposed technique in modeling the space-variant degradation process and restoring local textures. [ABSTRACT FROM AUTHOR]

In this paper, we propose a denoising method motivated by our previous analysis of the performance bounds for image denoising. Insights from that study are used here to derive a high-performance practical denoising algorithm. We propose a patch-based Wiener filter that exploits patch redundancy for image denoising. Our framework uses both geometrically and photometrically similar patches to estimate the different filter parameters. We describe how these parameters can be accurately estimated directly from the input noisy image. Our denoising approach, designed for near-optimal performance (in the mean-squared error sense), has a sound statistical foundation that is analyzed in detail. The performance of our approach is experimentally verified on a variety of images and noise levels. The results presented here demonstrate that our proposed method is on par or exceeding the current state of the art, both visually and quantitatively. [ABSTRACT FROM AUTHOR]

In this paper, we propose a robust-hash function based on random Gabor filtering and dithered lattice vector quantization (LVQ). In order to enhance the robustness against rotation manipulations, the conventional Gabor filter is adapted to be rotation invariant, and the rotation-invariant filter is randomized to facilitate secure feature extraction. Particularly, a novel dithered-LVQ-based quantization scheme is proposed for robust hashing. The dithered-LVQ-based quantization scheme is well suited for robust hashing with several desirable features, including better tradeoff between robustness and discrimination, higher randomness, and secrecy, which are validated by analytical and experimental results. The performance of the proposed hashing algorithm is evaluated over a test image database under various content-preserving manipulations. The proposed hashing algorithm shows superior robustness and discrimination performance compared with other state-of-the-art algorithms, particularly in the robustness against rotations (of large degrees). [ABSTRACT FROM AUTHOR]

Finding color representations that are stable to illuminant changes is still an open problem in computer vision. Until now, most approaches have been based on physical constraints or statistical assumptions derived from the scene, whereas very little attention has been paid to the effects that selected illuminants have on the final color image representation. The novelty of this paper is to propose perceptual constraints that are computed on the corrected images. We define the category hypothesis, which weights the set of feasible illuminants according to their ability to map the corrected image onto specific colors. Here, we choose these colors as the universal color categories related to basic linguistic terms, which have been psychophysically measured. These color categories encode natural color statistics, and their relevance across different cultures is indicated by the fact that they have received a common color name. From this category hypothesis, we propose a fast implementation that allows the sampling of a large set of illuminants. Experiments prove that our method rivals current state-of-art performance without the need for training algorithmic parameters. Additionally, the method can be used as a framework to insert top–down information from other sources, thus opening further research directions in solving for color constancy. [ABSTRACT FROM AUTHOR]

Recently, extensive research efforts have been dedicated to view-based methods for 3-D object retrieval due to the highly discriminative property of multiviews for 3-D object representation. However, most of state-of-the-art approaches highly depend on their own camera array settings for capturing views of 3-D objects. In order to move toward a general framework for 3-D object retrieval without the limitation of camera array restriction, a camera constraint-free view-based (CCFV) 3-D object retrieval algorithm is proposed in this paper. In this framework, each object is represented by a free set of views, which means that these views can be captured from any direction without camera constraint. For each query object, we first cluster all query views to generate the view clusters, which are then used to build the query models. For a more accurate 3-D object comparison, a positive matching model and a negative matching model are individually trained using positive and negative matched samples, respectively. The CCFV model is generated on the basis of the query Gaussian models by combining the positive matching model and the negative matching model. The CCFV removes the constraint of static camera array settings for view capturing and can be applied to any view-based 3-D object database. We conduct experiments on the National Taiwan University 3-D model database and the ETH 3-D object database. Experimental results show that the proposed scheme can achieve better performance than state-of-the-art methods. [ABSTRACT FROM AUTHOR]

This paper describes two new intraimage prediction methods based on two data dimensionality reduction methods: nonnegative matrix factorization (NMF) and locally linear embedding. These two methods aim at approximating a block to be predicted in the image as a linear combination of k-nearest neighbors determined on the known pixels in a causal neighborhood of the input block. Variable k can be seen as a parameter controlling some sort of sparsity constraints of the approximation vector. The impact of this parameter as well as of the nonnegativity and sum-to-one constraints for the addressed prediction problem has been analyzed. The prediction and RD performances of these two new image prediction methods have then been evaluated in a complete image coding-and-decoding algorithm. Simulation results show gains up to 2 dB in terms of the PSNR of the reconstructed signal after coding and decoding of the prediction residue when compared with H.264/AVC intraprediction modes, up to 3 dB when compared with template matching, and up to 1 dB when compared with a sparse prediction method. [ABSTRACT FROM AUTHOR]

Multiple description coding has been receiving attention as a robust transmission framework for multimedia services. This paper studies the iterative decoding of FEC-based multiple description codes. The proposed decoding algorithms take advantage of the error detection capability of Reed–Solomon (RS) erasure codes. The information of correctly decoded RS codewords is exploited to enhance the error correction capability of the Viterbi algorithm at the next iteration of decoding. In the proposed algorithm, an intradescription interleaver is synergistically combined with the iterative decoder. The interleaver does not affect the performance of noniterative decoding but greatly enhances the performance when the system is iteratively decoded. We also address the optimal allocation of RS parity symbols for unequal error protection. For the optimal allocation in iterative decoding, we derive mathematical equations from which the probability distributions of description erasures can be generated in a simple way. The performance of the algorithm is evaluated over an orthogonal frequency-division multiplexing system. The results show that the performance of the multiple description codes is significantly enhanced. [ABSTRACT FROM AUTHOR]

Observations in many applications consist of counts of discrete events, such as photons hitting a detector, which cannot be effectively modeled using an additive bounded or Gaussian noise model, and instead require a Poisson noise model. As a result, accurate reconstruction of a spatially or temporally distributed phenomenon (\mmb f^\star) from Poisson data (\mmb y) cannot be effectively accomplished by minimizing a conventional penalized least-squares objective function. The problem addressed in this paper is the estimation of \mmb f^\star from \mmb y in an inverse problem setting, where the number of unknowns may potentially be larger than the number of observations and \mmb f^\star admits sparse approximation. The optimization formulation considered in this paper uses a penalized negative Poisson log-likelihood objective function with nonnegativity constraints (since Poisson intensities are naturally nonnegative). In particular, the proposed approach incorporates key ideas of using separable quadratic approximations to the objective function at each iteration and penalization terms related to \mmb \ell1 norms of coefficient vectors, total variation seminorms, and partition-based multiscale estimation methods. [ABSTRACT FROM AUTHOR]

In this paper, we propose a new sharpness enhancement algorithm for stereo images. Although the stereo image and its applications are becoming increasingly prevalent, there has been very limited research on specialized image enhancement solutions for stereo images. Recently, a binocular just-noticeable-difference (BJND) model that describes the sensitivity of the human visual system to luminance changes in stereo images has been presented. We introduce a novel application of the BJND model for the sharpness enhancement of stereo images. To this end, an overenhancement problem in the sharpness enhancement of stereo images is newly addressed, and an efficient solution for reducing the overenhancement is proposed. The solution is found within an optimization framework with additional constraint terms to suppress the unnecessary increase in luminance values. In addition, the reliability of the BJND model is taken into account by estimating the accuracy of stereo matching. Experimental results demonstrate that the proposed algorithm can provide sharpness-enhanced stereo images without producing excessive distortion. [ABSTRACT FROM AUTHOR]

Super-resolution technology provides an effective way to increase image resolution by incorporating additional information from successive input images or training samples. Various super-resolution algorithms have been proposed based on different assumptions, and their relative performances can differ in regions of different characteristics within a single image. Based on this observation, an adaptive algorithm is proposed in this paper to integrate a higher level image classification task and a lower level super-resolution process, in which we incorporate reconstruction-based super-resolution algorithms, single-image enhancement, and image/video classification into a single comprehensive framework. The target high-resolution image plane is divided into adaptive-sized blocks, and different suitable super-resolution algorithms are automatically selected for the blocks. Then, a deblocking process is applied to reduce block edge artifacts. A new benchmark is also utilized to measure the performance of super-resolution algorithms. Experimental results with real-life videos indicate encouraging improvements with our method. [ABSTRACT FROM AUTHOR]

Determining the relationship between the dendritic spine morphology and its functional properties is a fundamental challenge in neurobiology research. In particular, how to accurately and automatically analyse meaningful structural information from a large microscopy image data set is far away from being resolved. As pointed out in existing literature, one remaining challenge in spine detection and segmentation is how to automatically separate touching spines. In this paper, based on various global and local geometric features of the dendrite structure, we propose a novel approach to detect and segment neuronal spines, in particular, a breaking-down and stitching-up algorithm to accurately separate touching spines. Extensive performance comparisons show that our approach is more accurate and robust than two state-of-the-art spine detection and segmentation algorithms. [ABSTRACT FROM AUTHOR]