Search

Capon’s minimum-variance method (MVM) and amplitude and phase estimation (APES) spectral estimation algorithms can be applied to synthetic aperture radar (SAR) processing to improve the resolution and suppress sidelobe levels. In this paper, we use Capon-/APES-based SAR reprocessing algorithms to increase the persistent scatterer (PS) density in PS interferometry (PSI). We propose a PS candidate (PSC) selection algorithm applicable to the superresolution reprocessed images and the corresponding processing chain. The performance of the proposed algorithm is evaluated by a number of simulations and a stack of TerraSAR-X data. The results show that the Capon algorithm outperforms others in PSC selection. We present a full PSI time-series analysis on the PSCs extracted from the Capon-reprocessed stacks. The results show that the PS density is increased between 50% and 60%, while their interferometric quality is maintained. [ABSTRACT FROM AUTHOR]

Screen content coding plays an important role in many applications. Conventional reference picture management (RPM) strategies developed for natural content may not work well for screen content. This is because many regions in screen content remain static for a long time, causing a lot of repetitive contents to stay in the decoded picture buffer. The repetitive contents are not conducive to inter prediction, but still occupy valuable memory. This paper proposes a diversity-based RPM scheme for screen content coding. The concept of diversity is introduced for the reference picture set (RPS) to help formulate the RPM problem. By maximizing the diversity of RPS, more potentially better predictions are provided. Better compression performance can then be achieved. Meanwhile, the proposed scheme is nonnormative and compatible with existing video coding standards, such as High Efficiency Video Coding. The experimental results show that, for low delay screen content coding, the bit saving of the proposed scheme is 4.9% on average and up to 13.7%, without increasing encoding time. [ABSTRACT FROM AUTHOR]

Image mosaicking applications require both geometrical and photometrical registrations between the images that compose the mosaic. This paper proposes a probabilistic color correction algorithm for correcting the photometrical disparities. First, the image to be color corrected is segmented into several regions using mean shift. Then, connected regions are extracted using a region fusion algorithm. Local joint image histograms of each region are modeled as collections of truncated Gaussians using a maximum likelihood estimation procedure. Then, local color palette mapping functions are computed using these sets of Gaussians. The color correction is performed by applying those functions to all the regions of the image. An extensive comparison with ten other state of the art color correction algorithms is presented, using two different image pair data sets. Results show that the proposed approach obtains the best average scores in both data sets and evaluation metrics and is also the most robust to failures. [ABSTRACT FROM AUTHOR]

Compared with other applications in computer vision, convolutional neural networks (CNNs) have underperformed on pedestrian detection. A breakthrough was made very recently using sophisticated deep CNN (DCNN) models, with a number of handcrafted features or explicit occlusion handling mechanism. In this paper, we show that by reusing the convolutional feature maps of a DCNN model as image features to train an ensemble of boosted decision models, we are able to achieve the best reported accuracy without using specially designed learning algorithms. We empirically identify and disclose important implementation details. We also show that pixel labeling may be simply combined with a detector to boost the detection performance. By adding complementary handcrafted features such as optical flow, the DCNN-based detector can be further improved. We advance the state-of-the-art results by lowering the log-average miss rate from 11.7% to 8.9% on the Caltech data set and from 11.2% to 8.6% on the Inria data set. We also achieve a comparable result to state-of-the-art approaches on the KITTI data set. [ABSTRACT FROM AUTHOR]

3D video systems transmit depth maps in order to render synthesized views (SVs) at a receiver. To anticipate this purpose when processing a depth map, a sender-side depth processing algorithm (DPA), e.g. a depth encoder, can also render the SVs, compute their SV distortion (SVD), and adapt to it. This requires a low-complexity algorithm as computational resources are usually limited. We propose such an algorithm in this paper. First, we discuss a measure that relates a depth change to an SVD change using rendering. Then, we present an optimized process combining basic rendering steps, as warping, occlusion handling, interpolation, hole filling, and blending. Furthermore, we analyze which parts of an SV are affected by a depth change and modify the process to re-render only them. The resulting algorithm is significantly less complex than an unoptimized rendering-based variant and quantifies the SVD more accurately than existing estimation methods. The algorithm is used by the 3D-High Efficiency Video Coding reference software encoder as the main method for distortion computation and can also be used by other DPAs. [ABSTRACT FROM AUTHOR]

In this paper, we address a super-resolution (SR) problem that constructs a high-resolution (HR) frame/image from a short sequence of low-resolution (LR) frames/images. It is well known that SR is a difficult problem, especially when the number of LR inputs is small. In particular, our previous work involving multisurface fitting-based SR exhibits relatively poor performance in the above case. To cope with this problem, we take advantage of nonlocal pixels to fit local surfaces. The pixels from nonlocal spatial–temporal positions are selected and weighted based on patch similarity and outlier removal. With this method, the fitted surfaces become more elaborate so that more details can be retrieved in SR results. Experiments demonstrate that the proposed method is very effective in producing HR frames through a small number of LR inputs when compared with some state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Band selection is an effective approach to mitigate the “Hughes phenomenon” of hyperspectral image (HSI) classification. Recently, sparse representation (SR) theory has been successfully introduced to HSI band selection, and many SR-based methods have been developed and shown great potential and superiority. However, due to the inherent limitations of the SR scheme, i.e., individually representing each band with only a few other bands from the same subspace, the SR-based methods cannot effectively capture the global structures of the data, which limit the band selection performance. In this paper, to overcome this obstacle, the novel Laplacian-regularized low-rank subspace clustering (LLRSC) algorithm is proposed for HSI band selection. On the one hand, the low-rank subspace clustering model is introduced to capture the global structure information for the learned representation coefficient matrix and deal with the HSI band selection task in the clustering framework. On the other hand, considering the high correlation between adjacent bands, 1-D Laplacian regularization is utilized to incorporate the neighboring band information and further reduce the representation bias. Lastly, an eigenvalue analysis algorithm based on band mutation information is utilized to estimate the appropriate size of the band subset. The experimental results indicate that the proposed LLRSC algorithm outperforms the other state-of-the-art methods and achieves a very competitive band selection performance for HSIs. [ABSTRACT FROM AUTHOR]

Frame rate up-conversion (FRUC) is a technology for generating a higher frame rate video from one with a lower frame rate. The multi-view plus depth map (MVD) system has been recently considered a promising solution for three-dimensional video systems. Accordingly, an FRUC efficient solution for the MVD system is greatly needed. In this paper, we thus propose an FRUC approach that considers the MVD system characteristics. It divides a frame into multiple layers using a depth map, and it reconstructs occluded regions using neighboring views and depth map information. With reconstructed information, it accurately performs motion estimation when a region occlusion occurs. Experimental results demonstrated that the proposed method significantly improved the quality of interpolated frames, and it can effectively complement other conventional FRUC approaches. [ABSTRACT FROM AUTHOR]

The automatic reconstruction of single neurons from microscopic images is essential to enable large-scale data-driven investigations in neuron morphology research. However, few previous methods were able to generate satisfactory results automatically from 3-D microscopic images without human intervention. In this paper, we developed a new algorithm for automatic 3-D neuron reconstruction. The main idea of the proposed algorithm is to iteratively track backward from the potential neuronal termini to the soma centre. An online confidence score is computed to decide if a tracing iteration should be stopped and discarded from the final reconstruction. The performance improvements comparing with the previous methods are mainly introduced by a more accurate estimation of the traced area and the confidence controlled back-tracking algorithm. The proposed algorithm supports large-scale batch-processing by requiring only one user specified parameter for background segmentation. We bench tested the proposed algorithm on the images obtained from both the DIADEM challenge and the BigNeuron challenge. Our proposed algorithm achieved the state-of-the-art results. [ABSTRACT FROM AUTHOR]

We consider the reconstruction problem of video snapshot compressive imaging (SCI), which captures high-speed videos using a low-speed 2D sensor (detector). The underlying principle of SCI is to modulate sequential high-speed frames with different masks and then these encoded frames are integrated into a snapshot on the sensor and thus the sensor can be of low-speed. On one hand, video SCI enjoys the advantages of low-bandwidth, low-power and low-cost. On the other hand, applying SCI to large-scale problems (HD or UHD videos) in our daily life is still challenging and one of the bottlenecks lies in the reconstruction algorithm. Existing algorithms are either too slow (iterative optimization algorithms) or not flexible to the encoding process (deep learning based end-to-end networks). In this paper, we develop fast and flexible algorithms for SCI based on the plug-and-play (PnP) framework. In addition to the PnP-ADMM method, we further propose the PnP-GAP (generalized alternating projection) algorithm with a lower computational workload. We first employ the image deep denoising priors to show that PnP can recover a UHD color video with 30 frames from a snapshot measurement. Since videos have strong temporal correlation, by employing the video deep denoising priors, we achieve a significant improvement in the results. Furthermore, we extend the proposed PnP algorithms to the color SCI system using mosaic sensors, where each pixel only captures the red, green or blue channels. A joint reconstruction and demosaicing paradigm is developed for flexible and high quality reconstruction of color video SCI systems. Extensive results on both simulation and real datasets verify the superiority of our proposed algorithm. [ABSTRACT FROM AUTHOR]

In this paper, spectral subtraction is successfully applied to image processing and to detect defects in the integrated circuit (IC) image. By utilizing the characteristics of many of the same chips in a wafer, three images with defects located in the same position and different chips are obtained. The defect images contain the spectrum of standard image without any defects. Spectral subtraction presented in the paper can extract the standard image from the three defect images. The algorithm complexity of spectral subtraction detecting defects is close to that of Fourier transform. After obtaining the standard image, the speed and accuracy of defects detection can be greatly enhanced using the detection method presented in the paper. Using the image gray-scale matching technology, impact of illumination on IC defect detection is solved. Experiments demonstrate that spectral subtraction is fast and accurate to defect detection in an IC image, and the method has high robustness for illumination. [ABSTRACT FROM AUTHOR]

Introduces image processing methods for electronic compensation of show-through. Show-through model and analysis; Description on the linearized show-through model; Show-through correction algorithm; Experimental results.

Object recognition is widely used in vision computing for various applications. Traditional CPU and application specific integrated circuit for vision computing cannot provide high performance and enough flexibility, which limit the use of vision systems. In this paper, a hierarchical and parallel pipelined heterogeneous chip for object recognition is proposed to achieve high flexibility, high performance, and area efficiency. In addition, a reformulation of 3D position estimation is proposed. The method uses single precision to achieve the short computing time and accuracy requirement. The hardware resource is small. Application-specific components, such as connected component information extractor and information extraction accelerator, are designed for high performance. Reconfiguration processors and application-specific instruction set processor are introduced to improve flexibility. These components are connected to hierarchical parallel buses. The chip is fabricated in 180-nm CMOS technology and occupies 72.25 mm2 with 1.09M bits on-chip memory. It delivers 204 GOPS + 665M FLOPS operations. The results show that this hierarchical and parallel pipelined heterogeneous chip is suitable for embedded vision systems. [ABSTRACT FROM AUTHOR]

Video surveillance systems have become extremely important recently. It has been observed that information extracted from a single spectrum video is often insufficient in adverse conditions like low illumination, shadowing, smoke, dust, unstable background, and camouflage. Real-time video processing systems also need to be very fast where future frames are often unavailable at the time of processing the current frame. In this paper, we propose a superpixel-based causal multisensor video fusion algorithm suitable for real-time surveillance tasks. We develop new superpixel level spatial and temporal saliency models. Novel superpixel level multiple fusion rules are also designed to obtain the fused output. Comprehensive comparisons with several existing works clearly indicate the benefit of our solution. [ABSTRACT FROM AUTHOR]

Compressed sensing (CS) is the theory and practice of sub-Nyquist sampling of sparse signals of interest. Exact reconstruction may then be possible with much fewer than the Nyquist-required number of data. In this paper, we consider a multiview video system in which multiple cameras at different locations perform independent CS to simultaneously capture different views of a scene. At the decoder, we propose a disparity- and motion-compensated total variation minimization algorithm to jointly reconstruct the multiview video sequence. The experimental results show that the proposed joint reconstruction algorithm successfully exploits simultaneously intra-frame, inter-frame, and inter-view sparsity and significantly outperforms existing independent-view reconstruction, residue-view reconstruction, and motion-adaptive reconstruction algorithms. [ABSTRACT FROM AUTHOR]

Sparse modeling representative selection (SMRS) has been recently introduced for selecting the most relevant examples in data sets. SMRS exploits data self-representativeness coding in order to infer a coding matrix with block sparsity constraint. The relevance scores of samples are then derived from the estimated matrix of coefficients. Since SMRS is based on a linear model for data self-representation, it cannot always provide good relevant samples. Besides, most of its selected samples can be found in dense areas in input space. In this paper, we propose to overcome the SMRS method’s shortcomings that are related to the coding matrix estimation. We introduce two nonlinear data self-representativeness coding schemes that are based on Hilbert space and column generation. Experimental evaluation is carried out on summarizing a video movie and on summarizing training image data sets used for classification tasks. These experiments demonstrated that the proposed nonlinear methods can outperform state-of-the art selection methods. [ABSTRACT FROM AUTHOR]

With the rapid development of the integrated circuit (IC) industry, testing of IC chips is becoming more and more important. A chip probe final test is an important means of final chip testing, which makes use of contacts between probes and bumps on the chip for electrical connections of the test instrument and the chip, through which the electrical characteristics of the chip are tested one by one. The IC final test is directly completed on the entire packaging wafer before the packaging wafer is cut into single die. This complete testing of the whole wafer before dicing can greatly improve the efficiency of the final test. The precise alignment of probe and chip bumps is an important aspect of the final test process. In this paper, image processing is carried out based on the rectangular frame of the chip surface, for which the rectangular box image-processing algorithm is designed. The chip image showing the deflection angle is acquired, and the offset distance is calculated. The rectangular box algorithm based on the principle of the Hough transform detects the orientation that is used to determine the offset of the rectangular frame. The detection accuracy and efficiency of the algorithm is evaluated, and it is shown that the image-processing algorithm of the chip alignment is improved significantly. An efficient automatic probe final test of packaging wafers can finally be achieved. [ABSTRACT FROM PUBLISHER]

This paper presents low-cost compressors for video display systems, which compress video data to reduce the size of the frame memory in a display panel in a television or a smartphone. The hardware solution exploits the discrete wavelet transform (DWT) and 1-D set partitioning in hierarchical trees (SPIHT) to support the raster-scan processing order in a display system and meet the fixed target compression ratio (CR). However, the compression efficiency and hardware cost often increase in proportion to the block size and thus, designing a compressor with low cost but high fidelity is challenging. This paper proposes a generic partitioned SPIHT algorithm, which achieves a low-cost design for mobile devices by allowing various sizes of partitioned sub-blocks. By taking advantage of DWT decomposition properties, the proposed algorithm partitions a coding block into sub-blocks, each of which can be processed independently. The independent coding operations among multiple sub-blocks allow the size of the hardware buffer to be decreased, by storing the temporary results only for an individual sub-block. However, the proposed sub-block coding slightly decreases the compression efficiency when each sub-block is compressed with the same target CR. To reduce the drop-off in the compression efficiency, the boundary-pixel handling in DWT is exploited and the proposed partitioned SPIHT method adjusts the target CR for each sub-block depending on the potential quality loss. When compared with the previous 1-D design, experimental results show that the hardware gate count and internal memory are reduced by 59.34% and 75%, respectively. Furthermore, the proposed boundary handling and bit-allocation schemes mitigate the PSNR degradation due to the sub-block coding by 1.11 dB. [ABSTRACT FROM PUBLISHER]

Many patch-based image denoising algorithms can be formulated as applying a smoothing filter to the noisy image. Expressed as matrices, the smoothing filters must be row normalized, so that each row sums to unity. Surprisingly, if we apply a column normalization before the row normalization, the performance of the smoothing filter can often be significantly improved. Prior works showed that such performance gain is related to the Sinkhorn–Knopp balancing algorithm, an iterative procedure that symmetrizes a row-stochastic matrix to a doubly stochastic matrix. However, a complete understanding of the performance gain phenomenon is still lacking. In this paper, we study the performance gain phenomenon from a statistical learning perspective. We show that Sinkhorn–Knopp is equivalent to an expectation-maximization (EM) algorithm of learning a Gaussian mixture model of the image patches. By establishing the correspondence between the steps of Sinkhorn–Knopp and the EM algorithm, we provide a geometrical interpretation of the symmetrization process. This observation allows us to develop a new denoising algorithm called Gaussian mixture model symmetric smoothing filter (GSF). GSF is an extension of the Sinkhorn–Knopp and is a generalization of the original smoothing filters. Despite its simple formulation, GSF outperforms many existing smoothing filters and has a similar performance compared with several state-of-the-art denoising algorithms. [ABSTRACT FROM PUBLISHER]

Compressive covariance estimation has arisen as a class of techniques whose aim is to obtain second-order statistics of stochastic processes from compressive measurements. Recently, these methods have been used in various image processing and communications applications, including denoising, spectrum sensing, and compression. Notice that estimating the covariance matrix from compressive samples leads to ill-posed minimizations with severe performance loss at high compression rates. In this regard, a regularization term is typically aggregated to the cost function to consider prior information about a particular property of the covariance matrix. Hence, this paper proposes an algorithm based on the projected gradient method to recover low-rank or Toeplitz approximations of the covariance matrix from compressive measurements. The proposed algorithm divides the compressive measurements into data subsets projected onto different subspaces and accurately estimates the covariance matrix by solving a single optimization problem assuming that each data subset contains an approximation of the signal statistics. Furthermore, gradient filtering is included at every iteration of the proposed algorithm to minimize the estimation error. The error induced by the proposed splitting approach is analytically derived along with the convergence guarantees of the proposed method. The proposed algorithm estimates the covariance matrix of hyperspectral images from synthetic and real compressive samples. Extensive simulations show that the proposed algorithm can effectively recover the covariance matrix of hyperspectral images from compressive measurements with high compression ratios ($8-15\%$ approx) in noisy scenarios. Moreover, simulations and theoretical results show that the filtering step reduces the recovery error up to twice the number of eigenvectors. Finally, an optical implementation is proposed, and real measurements are used to validate the theoretical findings. [ABSTRACT FROM AUTHOR]

Dictionary learning has emerged as a powerful tool for a range of image processing applications and a proper dictionary always plays a key issue to the final achievable performance. In this paper, a class-oriented discriminative dictionary learning (CODDL) method is presented for image classification applications. It takes a comprehensive consideration of multiple optimization objectives, emphasizing class discrimination of both dictionary atoms and representation coefficients. The atoms of the learned dictionary should be grouped into class level sub-dictionaries. Meanwhile, the sparse representation coefficients of an input sample should be concentrated on the sub-dictionary of the class it belongs to. Then, based on the learned class-oriented discriminative dictionary, the structured representation coefficients can thus be used for image classification with a simple and efficient classification scheme. The superior performance of the proposed algorithm is demonstrated through extensive experiments. [ABSTRACT FROM AUTHOR]

Wavelet transform using Haar filter is a fast process for decomposing an image into low and high frequency sub-bands, which is an important step in multi-focus image fusion. This transformation alone is usually not sufficient to produce satisfying fused images, and therefore additional tools like focused region decision map and feature extraction are needed to enhance the fusion quality. In this paper, we propose a multi-focus image fusion algorithm that is suitable for efficient hardware implementation. The algorithm speed is significantly improved by utilizing Haar wavelet and computationally simple fusion rules. To further improve the circuit power and delay, we limit the logic operations to additions, subtractions, and multiplications only. Experiments on different benchmarks demonstrate that our proposed algorithm can reduce the fusion time by up to 99.97% compared with the state-of-the-art competing methods without compromising the fusion quality. In addition, the hardware implementation of the proposed algorithm reduces the circuit area and delay by 79.5% and 92.5%, respectively, when compared to the most competitive algorithm in this paper while maintaining similar fusion quality. [ABSTRACT FROM AUTHOR]

Digital image processing (DIP) algorithms used in consumer electronics products have high computational complexities. Therefore, in this paper, we propose a novel low complexity 2D adaptive DIP algorithm. The proposed algorithm reduces computational complexities of 2D DIP algorithms by exploiting pixel correlations in input image without reducing quality of output image. We also designed a low energy 2D adaptive DIP hardware implementing the proposed algorithm. The proposed hardware is verified to work correctly on an FPGA board. It has significantly less energy consumption than original 2D DIP hardware. Therefore, it can be used especially in portable consumer electronics products. [ABSTRACT FROM AUTHOR]

2-D linear discriminant analysis (2DLDA) has been widely used in pattern recognition and image classification. 2DLDA selects discriminative features from the up and left corner of images. However, 2DLDA uses the Frobenius norm (F-norm), which is sensitive to noise or outliers in data, as a metric. In this paper, we propose a novel framework, called horizontal and vertical nuclear norm-based 2DLDA (HVNN-2DLDA) for image representation. In the proposed framework, HVNN-2DLDA methods (i.e., HNN-2DLDA and VNN-2DLDA) are proposed, and both use the nuclear norm as a criterion. The nuclear norm can provide more structure and global information for the reconstruction of noisy images. HNN-2DLDA and VNN-2DLDA represent images in the row and column directions, respectively. In addition, by combining the row and column directions, we propose a bilateral nuclear norm-based 2DLDA method called BNN-2DLDA. The advantage of BNN-2DLDA over HNN-2DLDA and VNN-2DLDA is that an image sample can be represented by both the row and the column directions instead of only the row or column direction. HVNN-2DLDA learns a set of local optimal projection vectors by maximizing the ratio of the nuclear norm of the between-class scatter matrix and the nuclear norm of the within-class scatter matrix. To verify the robustness and recognition performance in image classification of HVNN-2DLDA, six public image databases are used for experiments. The experimental results demonstrate the effectiveness and the feasibility of the proposed framework. [ABSTRACT FROM AUTHOR]

Hyperspectral unmixing has attracted much attention in recent years. Single sparse unmixing assumes that a pixel in a hyperspectral image consists of a relatively small number of spectral signatures from large, ever-growing, and available spectral libraries. Joint-sparsity (or row-sparsity) model typically enforces all pixels in a neighborhood to share the same set of spectral signatures. The two sparse models are widely used in the literature. In this paper, we propose a joint-sparsity-blocks model for abundance estimation problem. Namely, the abundance matrix of size $m\times n$ is partitioned to have one row block and $s$ column blocks and each column block itself is joint-sparse. It generalizes both the single (i.e., $s=n$) and the joint (i.e., $s=1$) sparsities. Moreover, concatenating the proposed joint-sparsity-blocks structure and low rankness assumption on the abundance coefficients, we develop a new algorithm called joint-sparse-blocks and low-rank unmixing. In particular, for the joint-sparse-blocks regression problem, we develop a two-level reweighting strategy to enhance the sparsity along the rows within each block. Simulated and real-data experiments demonstrate the effectiveness of the proposed algorithm. [ABSTRACT FROM AUTHOR]

With the rapid increase of remote sensing images in temporal, spectral, and spatial resolutions, it is urgent to develop effective techniques for joint interpretation of spatial-temporal images. Multitype change detection (CD) is a significant research topic in multitemporal remote sensing image analysis, and its core is to effectively measure the difference degree and represent the difference among the multitemporal images. In this paper, we propose a novel difference representation learning (DRL) network and present an unsupervised learning framework for multitype CD task. Deep neural networks work well in representation learning but rely too much on labeled data, while clustering is a widely used classification technique free from supervision. However, the distribution of real remote sensing data is often not very friendly for clustering. To better highlight the changes and distinguish different types of changes, we combine difference measurement, DRL, and unsupervised clustering into a unified model, which can be driven to learn Gaussian-distributed and discriminative difference representations for nonchange and different types of changes. Furthermore, the proposed model is extended into an iterative framework to imitate the bottom-up aggregative clustering procedure, in which similar change types are gradually merged into the same classes. At the same time, the training samples are updated and reused to ensure that it converges to a stable solution. The experimental studies on four pairs of multispectral data sets demonstrate the effectiveness and superiority of the proposed model on multitype CD. [ABSTRACT FROM AUTHOR]

Despeckling is a fundamental preprocessing step for applications using polarimetric synthetic aperture radar data in most cases. In this paper, a guided filter with nonlinear weight kernels and adaptive filtering windows is presented for PolSAR image despeckling, in which the guidance image is constructed by a weighted average using the statistical traits of the speckled image. The output result is then estimated by another weighted average, with the aid of the fully polarimetric information from both the guidance image and the speckled image. In the experimental part, the filtering results obtained with both simulated and real PolSAR images reveal the positive performance of the proposed method in both reducing speckle and retaining details, when compared with some of the state-of-the-art algorithms. Furthermore, the relatively low computational complexity is another strength of the proposed method. [ABSTRACT FROM AUTHOR]

Fast inspection of a defect is a challenging task in mass production of curved surfaces, and photometric stereo (PS) utilizing multiple images from a single camera under a number of different illumination directions is a promising technique for this task due to its high sensitivity to surface normal perturbations. This paper adapts conventional PS and extends the technique to the inspection of non-Lambertian surfaces with high accuracy and efficiency. A data-driven PS is presented by establishing the Gaussian process (GP) model to represent the nonlinear reflectance behavior of various materials based on measured reflectance data sets. With the trained GP model, the surface normal can be estimated in two steps: prediction of bidirectional reflectance distribution function values under different light directions and the subsequent least-squares estimation of a surface normal. Comparison tests with other algorithms on the Mitsubishi Electric Research Laboratories data set and real workpieces with non-Lambertian materials show the superior accuracy and efficiency of the proposed method in surface normal estimation. After the surface normal of the workpiece is recovered, the defects can be detected by filtering out the perturbation of the surface normal. Experiments on steel and glossy polyester workpieces validate the efficacy of the proposed approach in detecting defects on curved non-Lambertian surfaces. [ABSTRACT FROM AUTHOR]

The advanced Himawari imager (AHI) aboard the Himawari-8 geostationary satellite provides high-frequency observations with broad coverage, multiple spectral channels, and high spatial resolution. In this paper, AHI data were used to develop an algorithm for joint retrieval of aerosol optical depth (AOD) over land and land surface bidirectional reflectance. Instead of performing surface reflectance estimation before calculating AOD, the AOD and surface bidirectional reflectance were retrieved simultaneously using an optimal estimation method. The algorithm uses an atmospheric radiative transfer model coupled with a surface bidirectional reflectance factor (BRF) model. Based on the assumption that the surface bidirectional reflective properties are invariant during a short time period (i.e., a day), multiple temporal AHI observations were combined to calculate the AOD and surface BRF. The algorithm was tested over East Asia for year 2016, and the AOD retrieval results were validated against the aerosol robotic network (AERONET) sites observation and compared with the Moderate Resolution Imaging Spectroradiometer Collection 6.0 AOD product. The validation of the retrieved AOD with AERONET measurements using 14 713 colocation points in 2016 over East Asia shows a high correlation coefficient: $R = 0.88$ , root-mean-square error = 0.17, and approximately 69.9% AOD retrieval results within the expected error of $\pm 0.2\cdot {\mathrm {AOD}}_{\mathrm {AERONET}}\pm 0.05$. A brief comparison between our retrieval and AOD product provided by Japan Meteorological Agency is also presented. The comparison and validation demonstrates that the algorithm has the ability to estimate AOD with considerable accuracy over land. [ABSTRACT FROM AUTHOR]

This paper presents a processing framework to separate moving targets from the clutter, under multichannel synthetic aperture radar (SAR) scenarios, and addresses the moving target imaging and velocity estimation problems for ground moving target indication (GMTI) applications. A practical implementation is introduced to break the SAR/GMTI problem into two processing stages, and the sparsity of the moving targets in the observed scene is exploited throughout the stages. The two-stage process extracts the moving targets from the monitored region via a sparsity-based iterative decomposition algorithm and subsequently estimates the complete velocity vectors of moving targets by enforcing sparsity constraints. The model is sufficiently versatile to incorporate digital elevation map information, which further improves the moving target relocation accuracy. The effectiveness of the presented framework is demonstrated using the Air Force Research Laboratory Gotcha GMTI challenge data. [ABSTRACT FROM AUTHOR]

Immersive media, such as free view point video and 360° video, are expected to be dominant as broadcasting services. The light field (LF) imaging is being considered as a next generation imaging technology offering the possibility to provide new services, including six degree-of-freedom video. The drawback of this technology is in the size of the generated content thus requiring novel compression systems and the design of ad-hoc methodologies for evaluating the perceived quality. In this paper, the relation between depth map quality and overall quality of LF image is studied. Next, a reduced reference quality assessment metric for LF images is presented. To predict the quality of distorted LF images, the measure of distortion in the depth map is exploited. To test and validate the proposed framework, a subjective experiment has been performed, and a LF image quality dataset has been created. The dataset is also used for evaluating the performance of state-of-the-art quality metrics, when applied to LF images. The achieved results evidence that the estimated quality score by the proposed framework has a significant correlation with subjective quality rating. Consequently, reference data can be delivered to the clients thus allowing the local estimation of the perceived quality of service. [ABSTRACT FROM AUTHOR]

Light-field stereo matching problems are commonly modeled by Markov Random Fields (MRFs) for statistical inference of depth maps. Nevertheless, most previous approaches did not adapt to image statistics but instead adopted fixed model parameters. They explored explicit vision cues, such as depth consistency and occlusion, to provide local adaptability and enhance depth quality. However, such additional assumptions could end up confining their applicability, e.g. algorithms designed for dense view sampling are not suitable for sparse one. In this paper, we get back to MRF fundamentals and develop an empirical Bayesian framework—Robust Pseudo Random Field—to explore intrinsic statistical cues for broad applicability. Based on pseudo-likelihoods with hidden soft-decision priors, we apply soft expectation-maximization (EM) for good model fitting and perform hard EM for robust depth estimation. We introduce novel pixel difference models to enable such adaptability and robustness simultaneously. Accordingly, we devise a stereo matching algorithm to employ this framework on dense, sparse, and even denoised light fields. It can be applied to both true-color and grey-scale pixels. Experimental results show that it estimates scene-dependent parameters robustly and converges quickly. In terms of depth accuracy and computation speed, it also outperforms state-of-the-art algorithms constantly. [ABSTRACT FROM AUTHOR]

The success of minimally invasive interventions and the remarkable technological and medical progress have made endoscopic image enhancement a very active research field. Due to the intrinsic endoscopic domain characteristics and the surgical exercise, stereo endoscopic images may suffer from different degradations which affect its quality. Therefore, in order to provide the surgeons with a better visual feedback and improve the outcomes of possible subsequent processing steps, namely, a 3-D organ reconstruction/registration, it would be interesting to improve the stereo endoscopic image quality. To this end, we propose, in this paper, two joint enhancement methods which operate in the wavelet transform domain. More precisely, by resorting to a joint wavelet decomposition, the wavelet subbands of the right and left views are simultaneously processed to exploit the binocular vision properties. While the first proposed technique combines only the approximation subbands of both views, the second method combines all the wavelet subbands yielding an inter-view processing fully adapted to the local features of the stereo endoscopic images. Experimental results, carried out on various stereo endoscopic datasets, have demonstrated the efficiency of the proposed enhancement methods in terms of perceived visual image quality. [ABSTRACT FROM AUTHOR]

Mismatch removal is a key step in many computer vision problems that involve point matching. The existing methods for checking geometric consistency mainly focus on similarity or affine transformations. In this paper, we propose a novel mismatch removal method that can cope with the projective transformation between two corresponding point sets. Our approach is based on the augmented homogeneous coordinates matrix constructed from the coordinates of anchor matches, whose degeneracy can indicate the correctness of anchor matches. The set of anchor matches is initially all the matches and is iteratively updated by calculating the difference between the estimated matched points, which can be easily computed in a closed form, and the actually matched points and removing those with large differences. Experimental results on synthetic 2D point matching data sets and real image matching data sets verify that our method achieves the highest $F$ -score among all the methods under similarity, affine, and projective transformations with noises and outliers. Our method can also achieve faster speed than all other iterative methods. Those non-iterative methods with slight advantage in speed are not competitive in accuracy when compared with ours. We also show that the set of anchor matches is stable through the iteration and the computation time grows very slowly with respect to the number of matched points. When applied to mismatch removal in partial-duplicate image search, our method achieves the best retrieval precision, and its computing time is also highly competitive. [ABSTRACT FROM AUTHOR]

This paper investigates the problem of determining a binary-valued function through a sequence of strategically selected queries. The focus is an algorithm called Generalized Binary Search (GBS). GBS is a well-known greedy algorithm for determining a binary-valued function through a sequence of strategically selected queries. At each step, a query is selected that most evenly splits the hypotheses under consideration into two disjoint subsets, a natural generalization of the idea underlying classic binary search. This paper develops novel incoherence and geometric conditions under which GBS achieves the information-theoretically optimal query complexity; i.e., given a collection of N hypotheses, GBS terminates with the correct function after no more than a constant times \log N queries. Furthermore, a noise-tolerant version of GBS is developed that also achieves the optimal query complexity. These results are applied to learning halfspaces, a problem arising routinely in image processing and machine learning. [ABSTRACT FROM AUTHOR]

In quantitative magnetic resonance ${T}_{\textsf {1}}$ mapping, the variable flip angle (VFA) steady state spoiled gradient recalled echo (SPGR) imaging technique is popular as it provides a series of high resolution ${T}_{\textsf {1}}$ weighted images in a clinically feasible time. Fast, linear methods that estimate ${T}_{\textsf {1}}$ maps from these weighted images have been proposed, such as DESPOT1 and iterative re-weighted linear least squares. More accurate, non-linear least squares (NLLS) estimators are in play, but these are generally much slower and require careful initialization. In this paper, we present NOVIFAST, a novel NLLS-based algorithm specifically tailored to VFA SPGR ${T}_{\textsf {1}}$ mapping. By exploiting the particular structure of the SPGR model, a computationally efficient, yet accurate and precise ${T}_{\textsf {1}}$ map estimator is derived. Simulation and in vivo human brain experiments demonstrate a twenty-fold speed gain of NOVIFAST compared with conventional gradient-based NLLS estimators while maintaining a high precision and accuracy. Moreover, NOVIFAST is eight times faster than the efficient implementations of the variable projection (VARPRO) method. Furthermore, NOVIFAST is shown to be robust against initialization. [ABSTRACT FROM AUTHOR]

In this paper, visual servoing based on photometric moments is advocated. A direct approach is chosen by which the extraction of geometric primitives, visual tracking and image matching steps of a conventional visual servoing pipeline can be bypassed. A vital challenge in photometric methods is the change in the image resulting from the appearance and disappearance of portions of the scene from the camera field of view during the servo. To tackle this issue, a general model for the photometric moments enhanced with spatial weighting is proposed. The interaction matrix for these spatially weighted photometric moments is derived in an analytical form. The correctness of the modeling, effectiveness of the proposed strategy in handling the exogenous regions, and improved convergence domain are demonstrated with a combination of simulation and the experimental results. [ABSTRACT FROM AUTHOR]

Blind source separation (BSS) aims to discover the underlying source signals from a set of linear mixture signals without any prior information of the mixing system, which is a fundamental problem in signal and image processing field. Most of the state-of-the-art algorithms have independently handled the decompositions of mixture signals. In this paper, we propose a new algorithm named multi-task sparse model to solve the BSS problem. Source signals are characterized via sparse techniques. Meanwhile, we regard the decomposition of each mixture signal as a task and employ the idea of multi-task learning to discover connections between tasks for the accuracy improvement of the source signal separation. Theoretical analyses on the optimization convergence and sample complexity of the proposed algorithm are provided. Experimental results based on extensive synthetic and real-world data demonstrate the necessity of exploiting connections between mixture signals and the effectiveness of the proposed algorithm. [ABSTRACT FROM AUTHOR]

Colorant-based direct binary search (CB-DBS) halftoning proposed in [27] provides an image quality benchmark for dispersed-dot halftoning algorithms. The objective of this paper is to further push the image quality limit. An algorithm called hierarchical colorant-based direct binary search (HCB-DBS) is developed in this paper. By appropriately integrating yellow colorant into dot-overlapping and dot-positioning controls, it is demonstrated that HCB-DBS can achieve better halftone texture of both individual and joint dot-color planes, without compromising the dot distribution of more visible halftone of cyan and magenta colorants. The input color specification is first converted from colorant space to dot-color space with minimum brightness variation principle for full dot-overlapping control. The dot-colors are then split into groups based upon dot visibility. Hierarchical monochrome DBS halftoning is applied to make dot-positioning decision for each group, constrained on the already generated halftone of the groups with higher priority. And dot-coloring is decided recursively with joint monochrome DBS halftoning constrained on the related total dot distribution. Experiments show HCB-DBS improves halftone texture for both individual and joint dot-color planes. And it reduces the halftone graininess and free of color mottle artifacts, comparing to CB-DBS. [ABSTRACT FROM AUTHOR]

The problem of reassembling image fragments arises in many scientific fields, such as forensics and archaeology. In the field of archaeology, the pictorial excavation findings are almost always in the form of painting fragments. The manual execution of this task is very difficult, as it requires great amount of time, skill and effort. Thus, the automation of such a work is very important and can lead to faster, more efficient, painting reassembly and to a significant reduction in the human effort involved. In this paper, an integrated method for automatic color based 2-D image fragment reassembly is presented. The proposed 2-D reassembly technique is divided into four steps. Initially, the image fragments which are probably spatially adjacent, are identified utilizing techniques employed in content based image retrieval systems. The second operation is to identify the matching contour segments for every retained couple of image fragments, via a dynamic programming technique. The next step is to identify the optimal transformation in order to align the matching contour segments. Many registration techniques have been evaluated to this end. Finally, the overall image is reassembled from its properly aligned fragments. This is achieved via a novel algorithm, which exploits the alignment angles found during the previous step. In each stage, the most robust algorithms having the best performance are investigated and their results are fed to the next step. We have experimented with the proposed method using digitally scanned images of actual torn pieces of paper image prints and we produced very satisfactory reassembly results. [ABSTRACT FROM AUTHOR]

This paper deals with the imaging problem of one-stationary bistatic SAR (BiSAR) with large bistatic angle. An improved nonlinear chirp scaling (NLCS) algorithm is proposed for this BiSAR. The main work here includes three aspects. First, a range chirp scaling function for correcting the differential range cell migration correction is derived. Then, the azimuth perturbation is generated by local fit method, which makes the NLCS algorithm suitable for the large bistatic angle case. Furthermore, the negative effects introduced by the perturbation (including phase error and locality error) are discussed, and some compensation methods are proposed to enhance the capability of the algorithm.. The simulating results exhibited at the end of this paper validate the correctness of the analysis and the feasibility of the algorithm. [ABSTRACT FROM AUTHOR]

Various 3-D face synthesis techniques have been proposed and extensively used in many applications. Compared with others, single view-based face synthesis technology allows unsupervised 3-D face reconstruction without any offline operations. Although many algorithms have been published, automatic and robust single view-based 3-D face synthesis still remains unsolved. In contrast to other methods, the single view-based 3-D face synthesis algorithm conducted in this paper enables automated 3-D face synthesis from an arbitrary head-and-shoulder image with the complex background. The developed system first detects the face using Bayesian skin-tone classification based on only the chrominance component, Cr. Based on the detected face, a few salient facial features, such as the corners of the eyebrows and contours of the eyes, mouth, and chin are in turn extracted using variant algorithms, including a dynamic chin extraction mechanism that will be detailed in this paper. Then, face model adaptation consisting of both global and local adaptations is imposed, according to geometric information provided by the extracted facial features. Finally, the 3-D specific face is synthesized using the adapted 3-D face model with a texture map directly derived from the input face image, followed by the implementation of facial animation using this synthesized face. [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]

To facilitate images under the nonlinear geometric transformation T and its inverse transformation T[SUP-1], we have developed numerical algorithms in [1]-[19]. A cycle conversion T[SUP-1]T of image transformations is said if an image is distorted by a transformation T and then restored back to itself. The combination (CSIM) of splitting-shooting-integrating methods was first proposed in Li [1] for T[SUP-1]T. In this paper other two combinations, CIIM and CI[SUP#] IM, of splitting integrating methods for T[SUP-1]T are provided. Combination CSIM has been successfully applied to many topics in image processing and pattern recognition (see [2]). Since combination CSIM causes large greyness errors, it well suited to a few greyness level images, but needs a huge computation work for 256 greyness level images of enlarged transformations (see [16]). We may instead choose combination CIIM which involves nonlinear solutions. However, the improved combination CI[SUP#] IM may bypass the nonlinear solutions completely. Hence, both CIIM and CI[SUP#] IM can be applied to q(q ≤ 256) greyness level images of any enlarged transformations. On the other hand, the combined algorithms, CSIM, CIIM, and CI[SUP#] IM, are applied to several important topics of image processing and pattern recognition: binary images, multi-greyness level images, image condensing, illumination, affine transformations, prospective and projection, wrapping images, handwriting characters, image concealment, the transformations with arbitrary shapes, and face transformation. This paper may also be regarded as a review of our recent research papers [1]-[19J. [ABSTRACT FROM AUTHOR]

Color demosaicing is an essential step in the camera image processing pipeline, especially on hardware platforms for real-time video applications. Though many demosaicing algorithms have been proposed in the past two decades, there remains a substantial gap between industrial needs and academic research. On one hand, industry requires a high perceptual quality, artifact-free, and low-cost demosaicing algorithm that is noniterative and small window based ready to be implemented on a hardware platform with a limited line buffer. On the other hand, academia is targeting high PSNR/SSIM, with the computation cost and line buffer receiving second priority, and often a frame buffer and iterative operation are used. The cost, large line buffer and iteration requirement make most existing demosaicing algorithms inapplicable on hardware platforms. In this paper, we introduce a novel low-cost demosaicing algorithm to narrow the gap. We keep the operation window size and computation cost as the first priority and achieve both high PSNR/SSIM and visual perceptual quality compared to previous state-of-the-art methods on standard test datasets. We fully investigate the a priori knowledge of natural scene raw images and find several key cues that are beneficial to demosaicing. Our demosaicing algorithm is a smart fusion of these useful cues. Furthermore, we solve typical demosaicing issues that occur in many traditional methods, including false color artifacts, T-section closing, and zippering artifacts. The proposed method has no learning stage, no iteration operation, a small line buffer and a limited number of parameters, so it can easily be applied to hardware platforms. [ABSTRACT FROM AUTHOR]

An algorithm for the simultaneous filling-in of texture and structure in regions of missing image information is presented in this paper. The basic idea is to first decompose the image into the sum of two functions with different basic characteristics, and then reconstruct each one of these functions separately with structure and texture filling-in algorithms. The first function used in the decomposition is of bounded variation, representing the underlying image structure, while the second function captures the texture and possible noise. The region of missing information in the bounded variation image is reconstructed using image in-painting algorithms, while the same region in the texture image is filled-in with texture synthesis techniques. The original image is then reconstructed adding back these two sub-images. The novel contribution of this paper is then in the combination of these three previously developed components, image decomposition with in-painting and texture synthesis, which permits the simultaneous use of filling-in algorithms that are suited for different image characteristics. Examples on real images show the advantages of this proposed approach. [ABSTRACT FROM AUTHOR]

The ultrafast speed and the large spatial area scanning autonomy are the two main advantages of the new radar presented in this paper. Indeed, the autonomous beam scanning capability with high pulse repetition frequency (PRF) is obtained by coherent combining of electrical fields emitted from active antennas’ array integrating photoconductive switching devices. An original signal processing associated with this new radar system is presented. We show a hybrid version of a CLEAN algorithm able to overcome the depth limitation induced by high PRF with standard imaging signal processing. Simulations and measurements are performed to validate the proper operation of the algorithm. [ABSTRACT FROM PUBLISHER]

Increasing demand of high-speed portable modules for multimedia applications has motivated the development of hardware-based solutions for image processing applications. Most of the nonrigid image registration algorithms are found to be unsuitable for hardware implementation because of their nonlinearity and computationally intensive nature. In this paper, an algorithm for nonrigid image registration based on Demons approximation is proposed. The algorithm has been simulated in MATLAB and results show a 15% improvement in peak-signal-to-noise-ratio with a 17% reduction in registration time for $256 \times 256$ image over the original Demons algorithm. The proposed algorithm is synthesized in Virtex6-xc6vlx760-2-ff1760 and maximum synthesized frequency is found to be 174 MHz. The proposed architecture provides the low cost, high-speed solution for the registration process, which is also helpful for making a portable system. [ABSTRACT FROM AUTHOR]

Blind motion deblurring from a single image is a highly under-constrained problem with many degenerate solutions. A good approximation of the intrinsic image can, therefore, only be obtained with the help of prior information in the form of (often nonconvex) regularization terms for both the intrinsic image and the kernel. While the best choice of image priors is still a topic of ongoing investigation, this research is made more complicated by the fact that historically each new prior requires the development of a custom optimization method. In this paper, we develop a stochastic optimization method for blind deconvolution. Since this stochastic solver does not require the explicit computation of the gradient of the objective function and uses only efficient local evaluation of the objective, new priors can be implemented and tested very quickly. We demonstrate that this framework, in combination with different image priors produces results with Peak Signal-to-Noise Ratio (PSNR) values that match or exceed the results obtained by much more complex state-of-the-art blind motion deblurring algorithms. [ABSTRACT FROM PUBLISHER]