The <Emphasis Type="SmallCaps">Pascal</Emphasis> Visual Object Classes (VOC) Challenge

The Pascal Visual Object Classes (VOC) challenge is a benchmark in visual object category recognition and detection, providing the vision and machine learning communities with a standard dataset of images and annotation, and standard evaluation procedures. Organised annually from 2005 to present, the challenge and its associated dataset has become accepted as the benchmark for object detection.     

Evaluation of visual saliency analysis algorithms in noisy images

Most existing visual saliency analysis algorithms assume that the input image is clean and does not have any disturbances. However, this situation is not always the case. In this paper, we provide an extensive evaluation of visual saliency analysis algorithms in noisy images. We analyze the noise immunity of saliency analysis algorithms by evaluating the performances of the algorithms in noisy images with increasing noise scales and by studying the effects of applying different denoising methods before performing saliency analysis. We use 10 state-of-the-art saliency analysis algorithms and 7 typical image denoising methods on 4 eye fixation datasets and 2 salient object detection datasets. Our experiments show that the performances of saliency analysis algorithms decrease with increasing image noise scales in general. An exception is that the nonlinear features (NF) integrated algorithm shows good noise immunity. We also find that image denoising methods can greatly improve the noise immunity of the algorithms. Our results show that the combination of NF and Median denoising method works best on eye fixation datasets and the combination of saliency optimization (SO) and color block-matching and 3D filtering (C-BM3D) method works best on salient object detection datasets. The combination of SO and Average denoising method works best for applications wherein time efficiency is a major concern for both types of datasets.     

结合环状原型空间优化的开放集目标检测

目的 现有目标检测任务常在封闭集设定中进行。然而在现实问题中,待检测图片中往往包含未知类别目标。因此,在保证模型对已知类检测性能的基础上,为了提升模型在现实检测任务中对新增类别的目标检测能力,本文对开放集目标检测任务进行研究。方法 区别于现有的开放集目标检测框架在检测任务中将背景类与未知类视为一个类别进行优化,本文框架在进行开放集类别识别的过程中,优先识别候选框属于背景类或是含待识别目标类别,而后再对含待识别目标类别进行已知类与未知类的判别。本文提出基于环状原型空间优化的检测器,该检测器可以通过优化待检测框的特征在高维空间中的稀疏程度对已知类、未知类与背景类进行环状序列判别,从而提升模型对开放集类别的检测性能。在（region proposal networks,RPN）层后设计了随机覆盖候选框的方式筛选相关的背景类训练框,避免了以往开放集检测工作中繁杂的背景类采样步骤。结果 本文方法在保证模型对封闭集设定下检测性能的情况下,通过逐步增加未知类别的数量,在Visual Object Classes-Common Objects in Context-20(VOC-COCO-20),Vi...     

Improved non-maximum suppression for object detection using harmony search algorithm

Non-maximum suppression (NMS) plays a key role in many modern object detectors. It is responsible to remove detection boxes that cover the same object. NMS greedily selects the detection box with maximum score; other detection boxes are suppressed when the degree of overlap between these detection boxes and the selected box exceeds a predefined threshold. Such a strategy easily retain some false positives, and it limits the ability of NMS to perceive nearby objects in cluttered scenes. This paper proposes an effective method combining harmony search algorithm and NMS to alleviate this problem. This method regards the task of NMS as a combination optimization problem. It seeks final detection boxes under the guidance of an objective function. NMS is applied to each harmony to remove imprecise detection boxes, and the remaining boxes are used to calculate the fitness value. The remaining detection boxes in a harmony with highest fitness value are chosen as the final detection results. The standard Pattern Analysis, Statistical Modeling and Computational Learning Visual Object Classes dataset and the Microsoft Common Objects in Context dataset are used in all of the experiments. The proposed method is applied to two popular detection networks, namely Faster Region-based Convolutional Neural Networks and Region-based Fully Convolutional Networks. The experimental results show that the proposed method improves the average precision of these two detection networks. Moreover, the location performance and average recall of these two detectors are also improved.     

结合PCA及字典学习的高光谱图像自适应去噪方法

高光谱图像各波段图像噪声分布复杂,传统去噪方法难以达到理想效果。针对这一问题,在主成分分析（PCA）的基础上,结合噪声估计和字典学习,提出一种新的高光谱去噪方法。首先,对原始高光谱数据进行主成分变换得到一组主成分图像并根据能量比重将其划分为清晰图像组和含噪图像组;然后,根据任一波段图像的信息,利用奇异值分解（SVD）对图像进行噪声估计,再将得到的噪声估计方法与K-SVD字典学习去噪算法结合,提出一种具备自适应噪声估计特性的字典学习去噪算法,并将其应用于信息量较小的含噪图像组进行去噪处理;最后,按各主成分图像对应的信息量比例进行加权融合得到最终的去噪图像。通过对模拟与实际高光谱遥感图像的实验表明,与PCA、PCA-Bish、PCA-Contourlet三种去噪方法相比,所提方法去噪后图像的峰值信噪比（PSNR）可以提升1~3 dB,且具有更多的细节信息和更好的视觉效果。     

基于离群点检测的图形图象噪声滤除算法

图形图象噪声过滤与修正,在媒体制作、图象分析与信息提取中起着十分重要的作用.虽然基于小波变换的算法能够对高斯噪声进行较好的滤噪处理,但对于随机分布于图象中的各种非高斯噪声仍没有普遍适用的滤噪方法.为了对这种随机分布于图象中的噪声进行有效的检测与滤除,采用对数字图象像素进行解析化描述的方法,从离群点检测的角度给出噪声的定义,并在此基础上构造了相应的图象噪声检测与滤除算法.实验结果表明,这一新方法对图象类型具有广泛的适应性和较好的噪声滤除效果,在大规模图形图象处理应用中具有实用价值.     

两阶段多层感知的随机脉冲噪声比例预测

目的 基于卷积神经网络（CNN）在图块级上实现的随机脉冲噪声（RVIN）降噪算法在执行效率方面较经典的逐像素点开关型降噪算法有显著优势,但降噪效果如何取决于能否对降噪图像受噪声干扰程度（噪声比例值）进行准确估计。为此,提出一种基于多层感知网络的两阶段噪声比例预测算法,达到自适应调用CNN预训练降噪模型获得最佳去噪效果的目的。方法 首先,对大量无噪声图像添加不同噪声比例的RVIN噪声构成噪声图像集合;其次,基于视觉码本（visual codebook）采用软分配（soft-assignment）编码法提取并筛选若干能反映噪声图像受随机脉冲噪声干扰程度的特征值构成特征矢量;再次,将从噪声图像上提取的特征矢量及对应的噪声比例分别作为多层感知网络的输入和输出训练噪声比例预测模型,实现从特征矢量到噪声比例值的映射（预测）;最后,采用粗精相结合的两阶段实现策略进一步提高RVIN噪声比例的预测准确性。结果 针对不同RVIN噪声比例的失真图像,从预测准确性、实际降噪效果和执行效率3个方面验证提出算法的性能和实用性。实验数据表明,本文算法在大多数噪声比例下的预测误差小于2%,降噪效果（PSNR指标）较其他主流降噪算法高24 dB,处理一幅大小为512×512像素的图像仅需3 s左右。结论 本文提出的RVIN噪声比例预测算法在各个噪声比例下具有鲁棒的预测准确性,在降噪效果和执行效率两个方面较经典的开关型RVIN降噪算法有显著提升,更具实用价值。     

A corner-weighted bounded Hessian model for image denoising

Image denoising is an essential step in the image processing task. The first-order variational model can remove noise while preserving edges, but it also generates the staircase effect. Although the bounded Hessian regulariser can reduce this side effect, it tends to blur object edges. In this paper, we propose a corner-weighted bounded Hessian model (CWBH) for image denoising, which has capability of removing noise without causing blurring object edges and artifacts. The bounded Hessian regularization at each pixel is controlled by a weight function which has an exponential form and depends on the corner response of the pixel. The split Bregman algorithm is adapted to decompose the proposed minimization problem into several subproblems which are solved directly using fast Fourier transform and the shrinkage operators. The proposed model is evaluated on synthetic and real noisy images for both spatially invariant and variant additive white Gaussian noise (AWGN). Extensive experiments demonstrate that our proposed model outperforms some state-of-the-art variational models for various types of noise and images. For uniform AWGN, CWBH surpasses other models on average by 0.014 for SSIM and by 0.77dB for PSNR; for spatially variant AWGN, these figures are 0.033 and 0.89dB, respectively.

     

Root Mean Square filter for noisy images based on hyper graph model

In this paper, we propose a noise removal algorithm for digital images. This algorithm is based on hypergraph model of image, which enables us to distinguish noisy pixels in the image from the noise-free ones. Hence, our algorithm obviates the need for denoising all the pixels, thereby preserving as much image details as possible. The identified noisy pixels are denoised through Root Mean Square (RMS) approximation. The performance of our algorithm, based on peak-signal-to-noise-ratio (PSNR) and mean-absolute-error (MAE), was studied on various benchmark images, and found to be superior to that of other traditional filters and other hypergraph based denoising algorithms.     

基于稀疏结构噪声检测的指静脉图像去噪算法

针对携带污染噪声的指静脉图像中背景区域、静脉区域和噪声区域的稀疏特性,提出一种改进的指静脉图像去噪算法。利用指静脉稀疏结构特性建立鲁棒主成分分析（RPCA）模型,通过交替方向乘子法求解RPCA模型获得含稀疏目标的前景图像并对其进行阈值分割以提取噪声分布图,同时根据提取结果建立修复优先度规则和自适应选择性滤波模板,实现指静脉图像的去噪处理。实验结果表明,与自适应非局部均值去噪算法和基于分数阶微分梯度噪声检测的去噪算法相比,在零误识情况下该算法处理后的带噪指静脉图像拒识率平均降低5.95%和3.64%,有效提升了带噪指静脉图像的识别性能。     

基于小波估计和直方图特征的LSB匹配分析

针对隐写分析中的难点——空域LSB匹配隐写进行检测和分析,描述LSB匹配加性隐写的特点,将匹配隐写建模为图像受到一定强度的脉冲噪声干扰,采用小波变换对退化的图像进行恢复作为载体的估计。对检测图像和恢复图像提取多个直方图特征比值作为特征向量,利用支持向量机对500幅高质量未压缩的自然图像组成的载体、载密图像库进行检测,结果证明该算法在低嵌入率下可获得较好的检测效果。     

基于U-Net融合的保留纹理的图像去噪方法

图像的噪声阻碍了高级视觉任务对图像的理解,且去除图像的噪声是一个具有挑战性的任务.现有的基于卷积神经网络的图像去噪方法在去除噪声的同时,对图像纹理会引入一定程度的破坏,导致去噪后图像无法保留图像的纹理.为了解决这个问题,本文提出一种用二分支U-Net网络来融合特征和保留纹理的图像去噪方法.首先选取一种去噪方法的两个不同...     

基于软门限去噪的图象压缩编码研究

在详细地分析了Donoho提出的子波域软限去噪方法的基础上,给出了含噪图象信号噪声水平的估计及门限值随尺度变化的规律。采用可分离的二维子波滤波器,方便地将Donoho的软门限去噪方法应用于图象信号处理,从而对含噪图象,在去除噪声的同时,又最大限度地进行了压缩。针对含噪的自然景物图象和合成孔径雷达图象的不同特点,分别提出了这在图象的压缩方案。对于SAR图象的压缩编码,通过一个自然对数变换,使得乘性噪声转变为适于软门限去噪的加性噪声。模拟结果显示,用软门限方法处理的解压缩图象比硬门限方法具有更好的视觉质量,因而该方法是解决含噪图象压缩编码的有效技术。     

A two-stage filter for high density salt and pepper denoising

Image restoration is an important and interesting problem in the field of image processing because it improves the quality of input images, which facilitates postprocessing tasks. The salt-and-pepper noise has a simpler structure than other noises, such as Gaussian and Poisson noises, but is a very common type of noise caused by many electronic devices. In this article, we propose a two-stage filter to remove high-density salt-and-pepper noise on images. The range of application of the proposed denoising method goes from low-density to high-density corrupted images. In the experiments, we assessed the image quality after denoising using the peak signal-to-noise ratio and structural similarity metric. We also compared our method against other similar state-of-the-art denoising methods to prove its effectiveness for salt and pepper noise removal. From the findings, one can conclude that the proposed method can successfully remove super-high-density noise with noise level above 90%.

     

基于滤波器的局部自适应全变分图像去噪模型

综合利用冲击滤波器和非线性各向异性扩散滤波器对含噪图像做预处理,然后基于边缘检测函数建立反映图像局部特征的自适应权函数,构建能同时兼顾图像平滑去噪与边缘保留的局部自适应性的全变分模型,并建议用本原对偶算法快速求解。实验结果表明,同传统的全变分图像去噪模型相比,该局部自适应全变分模型在消除噪声的同时能很好地保持图像的边缘轮廓和纹理等细节特征,得到的复原图像在客观评价标准和主观视觉效果方面均有所提高。     

基于无监督深度图像生成的盲降噪模型

鉴于有监督神经网络降噪模型的数据依赖缺陷,提出了一种基于无监督深度生成（UDIG）的盲降噪模型。首先,利用噪声水平评估（NLE）算法测定给定噪声图像中的噪声水平值并输入到主流FFDNet降噪模型中,所得到降噪后的图像（称为初步降噪图像）作为UDIG降噪模型的输入。其次,选用编码器—解码器架构作为UDIG模型的骨干网络并用UDIG模型的输出图像（即生成图像）分别与初步降噪图像、噪声图像之间的均方误差之和构建混合loss函数;再次,以loss最小化为优化目标,通过随机梯度下降（SGD）网络训练算法调整网络模型的参数值从而获得一系列生成图像;最后,当残差图像（噪声图像与生成图像之间）的标准差逼近之前NLE算法所测定的噪声水平估计值时及时终止网络迭代训练过程,从而确保生成图像（作为降噪后图像）的图像质量最佳。实验结果表明：与现有的主流降噪模型（算法）相比,UDIG降噪模型在降噪效果上具有显著优势。     

Visual tracking with multiple Hough detectors

We propose a visual tracking method using multiple Hough detectors to address the problem of long-term robust object tracking in unconstrained environments. The method constructs the detectors based on the feature selection by the mutual information. These detectors serve to learn the partial appearances of target and synchronously evaluate image locations via the voting based detection with the generalized Hough transform. According to the result of detections, the best detector is selected by the minimum entropy criterion and delivers the final hypotheses for target location. The feature selection allows our tracker to be able to obtain and use the most discriminative parts of target and thus more robust to its changes, e.g. occlusion and deformation. The detector selection can correct undesirable model updates and restore the tracker after tracking failure. Meanwhile, the Hough-based detection can reduce the amount of noise introduced during online self-training and thus effectively prevent the tracker from drifting. The method is evaluated on the CVPR2013 Visual Tracker Benchmark and the experimental results demonstrate our method outperforms other tracking algorithms in terms of both success rate and precision.     

多尺度多阶段特征融合的带噪图像语义分割

在图像的采集过程中,图像往往会带有一定的噪声信息,这些噪声信息会破坏图像的纹理结构,进而干扰语义分割任务.现有基于带噪图像的语义分割方法,大都是采取先去噪再分割的模型.然而,这种方式会导致在去噪任务中丢失语义信息,从而影响分割任务.为了解决该问题,提出了一种多尺度多阶段特征融合的带噪图像语义分割的方法,利用主干网络中各阶段的高级语义信息以及低级图像信息来强化目标轮廓语义信息.通过构建阶段性协同的分割去噪块,迭代协同分割和去噪任务,进而捕获更准确的语义特征.在PASCAL VOC 2012和Cityscapes数据集上进行了定量评估,实验结果表明,在不同方差的噪声干扰下,模型依旧取得了较好的分割结果.     

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.