Infrared single‐pixel video imaging for sea surface targets surveillance

This paper presents an infrared single‐pixel video imaging to surveille sea surface. Based on the temporal redundancy of the surveillance video, a two‐step scheme, including low‐scale detection and high‐scale detection, is proposed. For each frame, low‐scale detection performs low‐resolution single‐pixel imaging to obtain a “preview” image of the scene, where the moving target can be located. These targets are further refined in the high‐scale detection where the high‐resolution single‐pixel imagings focusing on these targets are used. The frame is reconstructed by merging these two‐level images. The simulated experiments show that for a video with 128 × 128 pixels and 150 frames, the sampling rate of our scheme is about 17.8%, and the reconstructed video presents a good visual quality.     

Robust Image Denoising Using a Virtual Flash Image for Monte Carlo Ray Tracing

We propose an efficient and robust image‐space denoising method for noisy images generated by Monte Carlo ray tracing methods. Our method is based on two new concepts: virtual flash images and homogeneous pixels. Inspired by recent developments in flash photography, virtual flash images emulate photographs taken with a flash, to capture various features of rendered images without taking additional samples. Using a virtual flash image as an edge‐stopping function, our method can preserve image features that were not captured well only by existing edge‐stopping functions such as normals and depth values. While denoising each pixel, we consider only homogeneous pixels—pixels that are statistically equivalent to each other. This makes it possible to define a stochastic error bound of our method, and this bound goes to zero as the number of ray samples goes to infinity, irrespective of denoising parameters. To highlight the benefits of our method, we apply our method to two Monte Carlo ray tracing methods, photon mapping and path tracing, with various input scenes. We demonstrate that using virtual flash images and homogeneous pixels with a standard denoising method outperforms state‐of‐the‐art image‐space denoising methods.     

Spatial error concealment for stereoscopic video coding based on pixel matching

In stereoscopic video coding, the interview correlation between the stereo image pair can be used for error concealment. A new spatial error concealment method for stereoscopic video coding based on pixel matching in the decoder is proposed in this paper. The lost macroblocks are recovered by utilizing disparity matching between two-view images on a pixel-by-pixel basis. Firstly, we get the candidate disparity vectors of the four neighboring pixels of the lost pixel by disparity matching in the decoder. Secondly, by calculating the boundary pixel difference, we determine an optimal replacing pixel in the reference image, and then we recover the lost pixel by the optimal pixel in the reference image. Experimental results show that the proposed algorithm performs better comparing to the previous technique.     

Color-based object segmentation method using artificial neural network

This paper presents a color-based technique for object segmentation in colored digital images. Principally, we make use of some color spaces to segment pixels as either objects of interest or non-objects using artificial neural networks (ANN). This study clearly shows how a novel method for fusion of the existing color spaces produces better results in practice than individual color spaces. The segmented objects include lips, faces, hands, fingers and tree leaves. Using several databases to represent these problems, the ANN was trained on the color of the pixel and its surrounding 8 neighbors to be an object or non-object; in the test mode the trained set was used to segment the 9 pixels in the test image into object or non-object. The feature vector was used for training and testing results from the fusion of different types of color information that came from different color models of the targeted pixel. Several experiments were conducted on different databases and objects to evaluate the proposed method; significant results were recorded, showing the power of expressiveness of color and some texture information to deal with the object segmentation problem.     

HidingGAN: High Capacity Information Hiding with Generative Adversarial Network

Image steganography is the technique of hiding secret information within images. It is an important research direction in the security field. Benefitting from the rapid development of deep neural networks, many steganographic algorithms based on deep learning have been proposed. However, two problems remain to be solved in which the most existing methods are limited by small image size and information capacity. In this paper, to address these problems, we propose a high capacity image steganographic model named HidingGAN. The proposed model utilizes a new secret information preprocessing method and Inception‐ResNet block to promote better integration of secret information and image features. Meanwhile, we introduce generative adversarial networks and perceptual loss to maintain the same statistical characteristics of cover images and stego images in the high‐dimensional feature space, thereby improving the undetectability. Through these manners, our model reaches higher imperceptibility, security, and capacity. Experiment results show that our HidingGAN achieves the capacity of 4 bits‐per‐pixel (bpp) at 256 × 256 pixels, improving over the previous best result of 0.4 bpp at 32 × 32 pixels.     

Bayesian Block-Wise Segmentation of Interframe Differences in Video Sequences

We present an algorithm for Bayesian estimation of temporally active and inactive spatial regions of video sequences. The algorithm aids in the use of conditional replenishment for video compression in many applications which feature a background/foreground format. For the sake of compatibility with common block-type coders, the binary-valued segmentation is constrained to be constant on square blocks of 8 × 8 or 16 × 16 pixels. Our approach favors connectivity at two levels of scale, with two intended effects. The first is at the pixel level, where a Gibbs distribution is used for the active pixels in the binary field of suprathreshold interframe differences. This increases the value of the likelihood ratio for blocks with spatially contiguous active pixels. The final segmentation also assigns higher probability to patterns of active blocks which are connected, since in general, macroscopic entities are assumed to be many blocks in size. Demonstrations of the advantage of the Bayesian approach are given through several simulations with standard sequences.     

The effects of source resolution on resolution enhancement through shifted superimposition projection

Resolution in a projected display is traditionally defined by the number of pixels in the projector's spatial light modulator (SLM). In recent years, different techniques that increase the resolution on the screen above the number of SLM pixels have gained popularity. In one such technique, called pixel‐shifting or shifted‐superimposition, the display physically shifts every n^th frame on the projected screen, and the overlapping pixel grids forms a finer subpixel grid with a higher pixel count. There is still an open question how much this method increases the resolution and how to quantify it. The resolution on the screen also depends upon the resolution of the input image fed to the projector. In this work, we experimentally investigate how the projector performs with resolution enhancement through pixel‐shifting and how this method relates to the source resolution. We also investigate some known methods of resolution measurement and evaluate how these methods perform for the shifted‐superimposition case. We find that the resolution enhancement through shifted‐superimposition enhances the resolution to about 40% over native resolution, and we also find two different measurement methods (grille contrast and least resolvable line pair method) that is relevant for effectively measuring resolution within such systems.     

Improving the interest operator for face recognition

When the conventional interest operator is used as the feature extraction procedure of face recognition, it has the following two shortcomings: first, though the purpose of the conventional interest operator is to use the intensity variation between neighboring pixels to represent the image, it cannot obtain all variation information between neighboring pixels. Second, under varying lighting conditions two images of the same face usually have different feature extraction results even though the face itself does not have obvious change. In this paper, we propose two new interest operators for face recognition, which are used to calculate the pixel intensity variation information of overlapping blocks produced from the original face image. The following two factors allow the new operators to perform better than the conventional interest operator: the first factor is that by taking the relative rather than absolute variation of the pixel intensity as the feature of an image block, the new operators can obtain robust block features. The second factor is that the scheme to partition an image into overlapping rather than non-overlapping blocks allows the proposed operators to produce more representation information for the face image. Experimental results show that the proposed operators offer significant accuracy improvement over the conventional interest operator.     

基于颜色和边缘方向的图像检索方法

提出了一种新的图像特征表示方法,首先提取图像的底层颜色信息获取颜色特征值 ,通过对图像中物体的边缘检测计算像素点的边缘方向角度值,并对颜色特征值和边缘方向 角度值进行量化。然后根据相邻像素点之间量化结果的数值分析,为每个像素点建立8维特 征向量。再以中心像素点与相邻像素点间不同的位置关系为基础,为每种位置关系赋予不同 的权重,根据像素点的特征向量计算出图像中每一个像素点的特征值。最后统计图像中具有 相同特征值的像素点个数,形成特征直方图,以此作为图像检索的依据。实验表明本文方法 能够有效描述图像的颜色分布和图像中物体的空间结构,更加细致地记录图像信息,进一步 增强图像之间的区分能力。与其他方法相比,本文方法检索效果更好。     

Feature‐Aware Pixel Art Animation

Pixel art is a modern digital art in which high resolution images are abstracted into low resolution pixelated outputs using concise outlines and reduced color palettes. Creating pixel art is a labor intensive and skill‐demanding process due to the challenge of using limited pixels to represent complicated shapes. Not surprisingly, generating pixel art animation is even harder given the additional constraints imposed in the temporal domain. Although many powerful editors have been Designed to facilitate the creation of still pixel art images, the extension to pixel art animation remains an unexplored direction. Existing systems typically request users to craft individual pixels frame by frame, which is a tedious and error‐prone process. In this work, we present a novel animation framework tailored to pixel art images. Our system bases on conventional key‐frame animation framework and state‐of‐the‐art image warping techniques to generate an initial animation sequence. The system then jointly optimizes the prominent feature lines of individual frames respecting three metrics that capture the quality of the animation sequence in both spatial and temporal domains. We demonstrate our system by generating visually pleasing animations on a variety of pixel art images, which would otherwise be difficult by applying state‐of‐the‐art techniques due to severe artifacts.     

A New QEM for Parametrization of Raster Images

We present an image processing method that converts a raster image to a simplical two‐complex which has only a small number of vertices (base mesh) plus a parametrization that maps each pixel in the original image to a combination of the barycentric coordinates of the triangle it is finally mapped into. Such a conversion of a raster image into a base mesh plus parametrization can be useful for many applications such as segmentation, image retargeting, multi‐resolution editing with arbitrary topologies, edge preserving smoothing, compression, etc. The goal of the algorithm is to produce a base mesh such that it has a small colour distortion as well as high shape fairness, and a parametrization that is globally continuous visually and numerically. Inspired by multi‐resolution adaptive parametrization of surfaces and quadric error metric, the algorithm converts pixels in the image to a dense triangle mesh and performs error‐bounded simplification jointly considering geometry and colour. The eliminated vertices are projected to an existing face. The implementation is iterative and stops when it reaches a prescribed error threshold. The algorithm is feature‐sensitive, i.e. salient feature edges in the images are preserved where possible and it takes colour into account thereby producing a better quality triangulation.     

用于纹理特征提取的改进的成对旋转不变共生局部二值模式算法

针对用于纹理特征提取的成对旋转不变共生局部二值模式（PRICoLBP）算法计算特征维度大、旋转不变性较差、对光照变化敏感的问题,提出一种融合局部纹理信息的改进PRICoLBP算法。首先,分别最大化和最小化图像像素点的二值序列,得到两个邻域像素点的坐标,由中心像素点坐标和得到的邻域像素点坐标计算出共生点对的坐标;其次,利用完备二值模式（CLBP）算法提取图像的每个像素点的纹理信息。在相同分类器下,对Brodatz、Outex（TC10,TC12）、Outex（TC14）、CUReT和KTH_TIPS数据库的分类实验中,所提算法的识别率比PRICoLBP算法分别提高了0.17、0.24、2.65、2.39和2.04个百分点。实验结果表明,所提算法在处理纹理旋转变化、光照条件多样的图像时具有较好的识别效果。     

前背景骨架区域随机点对策略驱动下的车标识别方法

目的 现有的车标识别算法均为各种经典的图像特征算子结合不同的分类器组合而成,均未分析车标图像的结构特点。综合考虑车标图像的灰度特征和结构特征,提出了一种前背景骨架区域随机点对策略驱动下的车标识别方法。方法 本文算法将标准车标图像分为前景区域和背景区域,分别提取前、背景的骨架区域,在其中进行随机取点,形成点对,通过进行点对的有效性判断,提取能表示车标的点对特征。点对特征表示两点周围局部区域的相似关系,反映了实际车标成像过程中车标图案部分与背景部分的灰度明暗关系。结果 在卡口系统截取的19 044张车标图像上进行实验,结果表明,与其他仅基于灰度特征的识别方法相比,本文提出的点对特征识别方法具有更好的识别效果,识别率达到了95.7%。在弱光照条件下,本文算法的识别算法效果同样优于其他仅基于灰度特征的识别方法,识别率达到了87.2%。结论 本文提出的前背景骨架区域随机点对策略驱动下的车标识别方法,结合了车标图像的灰度特征和结构特征,在进行车标的描述上具有独特性和排他性,有效地提高了车标的识别率,尤其是在弱光照条件下,本文方法具有更强的鲁棒性。     

Efficient image colorization based on seed pixel selection

Colorization is a technique to automatically produce color components for monochrome images and videos based on a few input colors. Generally, image colorization is initialized from a number of seed pixels whose colors are specified by users, and then the colors are gradually prorogating to the monochrome surroundings under a given optimization constraint. So, the performance of colorization is highly dependent on the selection of seed pixels. However, little attention has been paid to the selection of seed pixels, and how to improve the effectiveness of manual input remains a challenging task. To address this, an improved colorization method using seed pixel selection is proposed to assist the users in determining which pixels are highly required to be colorized for a high-quality colorized image. Specifically, the gray-scale image is first divided into non-overlapped blocks, and then, for each block, two pixels that approximate the average luminance of block are selected as the seeds. After the seed pixels are colored by users, an optimization that minimizes the difference between the seeds and their adjacent pixels is employed to propagate the colors to the other pixels. The experimental results demonstrate that, for a given amount of inputs, the proposed method can achieve a higher PSNR than the conventional colorization methods.     

Spatial–spectral locality constrained elastic net hypergraph for hyperspectral image clustering

Hypergraph is an effective method used to represent the contextual correlation within hyperspectral imagery for clustering. Nevertheless, how to discover the closely correlated samples to form hyperedges is the key issue for constructing an informative hypergraph. In this article, a new spatial–spectral locality constrained elastic net hypergraph learning model is proposed for hyperspectral image clustering (i.e. unsupervised classification). In order to utilize the spatial–spectral correlation among the pixels in hyperspectral images, first, we construct a locality-constrained dictionary by selecting K relevant pixels within a spatial neighbourhood, which activates the most correlated atoms and suppresses the uncorrelated ones. Second, each pixel is represented as a linear combination of the atoms in the dictionary under the elastic net regularization. Third, based on the obtained representations, the pixels and their most related pixels are linked as hyperedges, which can effectively capture high–order relationships among the pixels. Finally, a hypergraph Laplacian matrix is built for unsupervised learning. Experiments have been conducted on two widely used hyperspectral images, and the results show that the proposed method can achieve a superior clustering performance when compared to state-of-the-art methods.     

Spectral Gradient Sampling for Path Tracing

Spectral Monte‐Carlo methods are currently the most powerful techniques for simulating light transport with wavelength‐dependent phenomena (e.g., dispersion, colored particle scattering, or diffraction gratings). Compared to trichromatic rendering, sampling the spectral domain requires significantly more samples for noise‐free images. Inspired by gradient‐domain rendering, which estimates image gradients, we propose spectral gradient sampling to estimate the gradients of the spectral distribution inside a pixel. These gradients can be sampled with a significantly lower variance by carefully correlating the path samples of a pixel in the spectral domain, and we introduce a mapping function that shifts paths with wavelength‐dependent interactions. We compute the result of each pixel by integrating the estimated gradients over the spectral domain using a one‐dimensional screened Poisson reconstruction. Our method improves convergence and reduces chromatic noise from spectral sampling, as demonstrated by our implementation within a conventional path tracer.     

Denoising Deep Monte Carlo Renderings

We present a novel algorithm to denoise deep Monte Carlo renderings, in which pixels contain multiple colour values, each for a different range of depths. Deep images are a more expressive representation of the scene than conventional flat images. However, since each depth bin receives only a fraction of the flat pixel's samples, denoising the bins is harder due to the less accurate mean and variance estimates. Furthermore, deep images lack a regular structure in depth—the number of depth bins and their depth ranges vary across pixels. This prevents a straightforward application of patch‐based distance metrics frequently used to improve the robustness of existing denoising filters. We address these constraints by combining a flat image‐space non‐local means filter operating on pixel colours with a deep cross‐bilateral filter operating on auxiliary features (albedo, normal, etc.). Our approach significantly reduces noise in deep images while preserving their structure. To our best knowledge, our algorithm is the first to enable efficient deep‐compositing workflows with denoised Monte Carlo renderings. We demonstrate the performance of our filter on a range of scenes highlighting the challenges and advantages of denoising deep images.     

In-place Algorithm for Erasing a Connected Component in a Binary Image

Removing noise in a given binary image is a common operation. A generalization of the operation is to erase an arbitrarily specified component by reversing pixel values in the component. This paper shows that this operation can be done without using any data structure like a stack or queue, or more exactly using only constant extra memory (consisting of a constant number of words of O(log n) bits for an image of n pixels) in O(mlog m) time for a component consisting of m pixels. This is an in-place algorithm, but the image matrix cannot be used as work space since it has just one bit for each pixel. Whenever we flip a pixel value in a target component, the component shape is also deformed, which causes some difficulty. The main idea for our constant work space algorithm is to deform a component so that its connectivity is preserved.     

Extracting non-negative basis images using pixel dispersion penalty

Non-negativity matrix factorization (NMF) and its variants have been explored in the last decade and are still attractive due to its ability of extracting non-negative basis images. However, most existing NMF based methods are not ready for encoding higher-order data information. One reason is that they do not directly/explicitly model structured data information during learning, and therefore the extracted basis images may not completely describe the “parts” in an image [1] very well. In order to solve this problem, the structured sparse NMF has been recently proposed in order to learn structured basis images. It however depends on some special prior knowledge, i.e. one needs to exhaustively define a set of structured patterns in advance. In this paper, we wish to perform structured sparsity learning as automatically as possible. To that end, we propose a pixel dispersion penalty (PDP), which effectively describes the spatial dispersion of pixels in an image without using any manually predefined structured patterns as constraints. In PDP, we consider each part-based feature pattern of an image as a cluster of non-zero pixels; that is the non-zero pixels of a local pattern should be spatially close to each other. Furthermore, by incorporating the proposed PDP, we develop a spatial non-negative matrix factorization (Spatial NMF) and a spatial non-negative component analysis (Spatial NCA). In Spatial NCA, the non-negativity constraint is only imposed on basis images and such constraint on coefficients is released, so both subtractive and additive combinations of non-negative basis images are allowed for reconstructing any images. Extensive experiments are conducted to validate the effectiveness of the proposed pixel dispersion penalty. We also experimentally show that Spatial NCA is more flexible for extracting non-negative basis images and obtains better and more stable performance.