检索结果-内蒙古大学图书馆

A Spatially Adaptive Gradient-Projection Algorithm to Remove coding artifacts of H.264

IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS 2011年第5期E94D卷 1073-1081页

作者： Choi, Kwon-Yul Hong, Min-Cheol Soongsil Univ Seoul South Korea

In this paper, we propose a spatially adaptive gradient-projection algorithm for the H.264 video coding standard to remove coding artifacts using local statistics. A hybrid method combining a new weighted constrained least squares (WCLS) approach and the projection onto convex sets (POCS) approach is introduced, where weighting components are determined on the basis of the human visual system (HVS) and projection set is defined by the difference between adjacent pixels and the quantization index (QI). A new visual function is defined to determine the weighting matrices controlling the degree of global smoothness, and a projection set is used to obtain a solution satisfying local smoothing constraints, so that the coding artifacts such as blocking and ringing artifacts can be simultaneously removed. The experimental results show the capability and efficiency of the proposed algorithm.

关键词： H.264 coding artifacts weighted constrained least squares human visual system projection onto convex sets

来源：评论

学校读者我要写书评

暂无评论

A Machine Learning Approach to Reducing Image coding artifacts 25

A Machine Learning Approach to Reducing Image Coding Artifac...

引用

25th European Signal Processing Conference (EUSIPCO)

作者： Matsuda, Ichiro Ishikawa, Tomokazu Kameda, Yusuke Itoh, Susumu Tokyo Univ Sci Fac Sci & Technol Dept Elect Engn 2641 Yamazaki Noda Chiba 2788510 Japan

ISBN: (纸本)9780992862671

In this paper, a method for reducing coding artifacts introduced by lossy image compression is proposed. The method is similar to sample adaptive offset (SAO) which is adopted in the H.265/HEVC video coding standard as one of in-loop filtering tools. In the SAO, samples of the reconstructed image are classified into several categories based on some simple algorithms, and an optimum offset value is then added to the samples belonging to each category. Since the classification algorithms are switched on a block-by-block basis, not a negligible amount of side-information must be transmitted to the decoder in addition to the offset values. On the other hand, our method adopts a machine learning technique using a support vector machine (SVM) for the classification process. By applying the common SVM classifier to a whole image, the amount of the side-information can be considerably reduced. Simulation results indicate that the proposed method provides bitrate savings of up to 1.0% for HD size images degraded through intra frame coding of the H. 265/HEVC standard.

关键词： Post filtering coding artifacts machine learning support vector machine (SVM) sample adaptive offset (SAO)

来源：评论

学校读者我要写书评

暂无评论

A real-time visual postprocessor for MPEG-coded video sequences

引用

SIGNAL PROCESSING-IMAGE COMMUNICATION 2001年第8期16卷 809-816页

作者： Atzori, L De Natale, FGB Granelli, F Univ Cagliari Dept Elect & Elect Engn I-09123 Cagliari Italy Univ Trent DICA I-38050 Trent Italy

A novel content-adaptive enhancement filter is described, which aims at reducing compression artifacts in MPEG-coded video streams. The filter locally selects the most appropriate kernel among a set of pre-defined masks, based upon a classification of the pixels to be processed. The features used in the classification phase take into account the distribution of transform coefficients and the presence of nearby contour pixels, previously detected by an edge extractor. An important aspect of the proposed approach is the low computational complexity, very appealing in the scenario of a typical low-cost consumer application (video communication over the Internet, set-top-box DVB receiver, etc.). Experimental results show that the proposed algorithm outperforms existing approaches with similar level of complexity. (C) 2001 Elsevier Science B.V. All rights reserved.

关键词： MPEG video post-processing coding artifacts

来源：评论

学校读者我要写书评

暂无评论

Multiple Description Convolutional Neural Networks for Image Compression

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2019年第8期29卷 2494-2508页

作者： Zhao, Lijun Bai, Huihui Wang, Anhong Zhao, Yao Beijing Jiaotong Univ Inst Informat Sci Beijing Key Lab Adv Informat Sci & Network Techno Beijing 100044 Peoples R China Taiyuan Univ Sci & Technol Inst Digital Media & Commun Taiyuan 030024 Peoples R China

Multiple description coding (MDC) is able to stably transmit signal in un-reliable and non-prioritized networks, which has been broadly studied for several decades. However, traditional MDC does not well leverage image's context features to generate multiple descriptions. In this paper, we propose a novel standard-compliant convolutional neural network-based MDC framework, which efficiently leverages image's context information to compress the image. First, multiple description generator network (MDGN) is designed to produce appearance-similar yet feature-different multiple descriptions automatically according to image's content, which are compressed by a standard codec. Second, we present multiple description reconstruction network (MDRN) including side reconstruction networks (SRNs) and central reconstruction network (CRN). When any one of two lossy descriptions is received at decoder, SRN network is used to improve the quality of this decoded lossy description by simultaneously removing compression artifact and up-sampling. Meanwhile, we utilize CRN network with two decoded descriptions as inputs for better reconstruction, if both of lossy descriptions are available. Third, multiple description virtual codec network is proposed to bridge the gap between MDGN network and MDRN network in order to train an end-to-end MDC framework. Here, two learning algorithms are provided to train our whole framework. In addition to structural dis-similarity loss function, the produced descriptions are used as opposing labels with multiple description distance loss function to regularize the training of MDGN network. These losses guarantee that the generated descriptions are structurally similar yet finely diverse. Experimental results show a great deal of objective and subjective quality measurements to validate the effectiveness of our framework.

关键词： Multiple description networks distance loss virtual codec learning algorithm coding artifacts

来源：评论

学校读者我要写书评

暂无评论

Advanced fine-tuning procedures to enhance DNN robustness in visual coding for machines

引用

EURASIP JOURNAL ON IMAGE AND VIDEO PROCESSING 2024年第1期2024卷 31页

作者： Marie, Alban Desnos, Karol Mercat, Alexandre Morin, Luce Vanne, Jarno Zhang, Lu Tampere Univ Ultra Video Grp Tampere Finland Univ Rennes INSA Rennes CNRS IETRUMR 6164 Rennes France

Video coding for Machines (VCM) is gaining momentum in applications like autonomous driving, industry manufacturing, and surveillance, where the robustness of machine learning algorithms against coding artifacts is one of the key success factors. This work complements the MPEG/JVET standardization efforts in improving the resilience of deep neural network (DNN)-based machine models against such coding artifacts by proposing the following three advanced fine-tuning procedures for their training: (1) the progressive increase of the distortion strength as the training proceeds;(2) the incorporation of a regularization term in the original loss function to minimize the distance between predictions on compressed and original content;and (3) a joint training procedure that combines the proposed two approaches. These proposals were evaluated against a conventional fine-tuning anchor on two different machine tasks and datasets: image classification on ImageNet and semantic segmentation on Cityscapes. Our joint training procedure is shown to reduce the training time in both cases and still obtain a 2.4% coding gain in image classification and 7.4% in semantic segmentation, whereas a slight increase in training time can bring up to 9.4% better coding efficiency for the segmentation. All these coding gains are obtained without any additional inference or encoding time. As these advanced fine-tuning procedures are standard-compliant, they offer the potential to have a significant impact on visual coding for machine applications.

关键词： Video coding for Machines (VCM) coding artifacts Image and video coding Deep neural network (DNN) Deep learning Fine-tuning

来源：评论

学校读者我要写书评

暂无评论

Causes and subjective evaluation of blurriness in video frames

引用

SIGNAL PROCESSING-IMAGE COMMUNICATION 2013年第3期28卷 209-221页

作者： Dardi, Francesca Abate, Leonardo Stessen, Jeroen Ramponi, Giovanni Univ Trieste Dept Engn & Architecture I-34127 Trieste Italy TP Vision Netherlands Innovat Site Eindhoven NL-5616 LZ Eindhoven Netherlands

A method to automatically assess the seriousness of the blurriness artifact in video frames displayed on a state-of-the-art TV monitor is presented. Different types of the artifact are identified, depending on the stage of the video chain where they are originated, namely, blur produced during acquisition, post-processing and encoding. Every type is observed to produce slightly different effects on the frame and, more importantly, to affect image quality differently, so that distinguishing among types is necessary to perform an appropriate restoration. Two main metrics are therefore introduced for classifying the type of blurriness and, when useful, measuring its strength. Particular care was taken in distinguishing the intentional background blur, which does not cause an actual degradation in the frame quality. The appropriateness of the method in classifying the artifact and predicting the subjective frame quality was verified in the experiments. (C) 2012 Elsevier B.V. All rights reserved.

关键词： Blurriness coding artifacts Visual attention Video quality estimation

来源：评论

学校读者我要写书评

暂无评论

Modeling subjectively perceived annoyance of H.264/AVC video as a function of perceived artifact strength

引用

SIGNAL PROCESSING 2010年第1期90卷 80-92页

作者： Wolff, Tobias Ho, Hsin-Han Foley, John M. Mitra, Sanjit K. Tech Univ Darmstadt Dept Elect Engn & Informat Technol D-64283 Darmstadt Germany Univ Calif Santa Barbara Dept Elect & Comp Engn Santa Barbara CA 93106 USA Univ Calif Santa Barbara Dept Psychol Santa Barbara CA 93106 USA

This paper is concerned with the subjective perception of video coding artifacts in H.264/AVC encoded and decoded video. Our objective is to model the perceived annoyance of such low bit rate video sequences as a function of perceived artifact strength. We introduce a new method for determining this function and apply it to the data from two psychophysical experiments. Both experiments produced numerical judgments of the subjectively perceived annoyance of artifact combinations and the perceived strength of the respective coding artifacts. Our method produces a discrete multi-dimensional representation of the relationships in the data from which the function relating annoyance to artifact strength is derived. The method is applied to the data of the first experiment and the resulting function is shown to describe the data from the second experiment as well. (C) 2009 Elsevier B.V. All rights reserved.

关键词： Video quality Subjectively perceived annoyance H.264/AVC coding artifacts Data analysis Modeling

来源：评论

学校读者我要写书评

暂无评论

Statistical evaluation of image quality measures

引用

JOURNAL OF ELECTRONIC IMAGING 2002年第2期11卷 206-223页

作者： Avcibas, I Sankur, B Sayood, K Uludag Univ Dept Elect Engn Bursa Turkey Bogazici Univ Dept Elect & Elect Engn Istanbul Turkey Univ Nebraska Dept Elect Engn Lincoln NE 68588 USA

In this work we comprehensively categorize image quality measures, extend measures defined for gray scale images to their multispectral case, and propose novel image quality measures. They are categorized into pixel difference-based, correlation-based, edge-based, spectral-based, context-based and human visual system (HVS)-based measures. Furthermore we compare these measures statistically for still image compression applications. The statistical behavior of the measures and their sensitivity to coding artifacts are investigated via analysis of variance techniques. Their similarities or differences are illustrated by plotting their Kohonen maps. Measures that give consistent scores across an image class and that are sensitive to coding artifacts are pointed out. It was found that measures based on the phase spectrum, the multiresolution distance or the HVS filtered mean square error are computationally simple and are more responsive to coding artifacts. We also demonstrate the utility of combining selected quality metrics in building a steganalysis tool. (C) 2002 SPIE and IST.

关键词： .HVS image quality scores quality metrics mean square steganalysis coding artifacts Statistical evaluation based measures image class multiresolution distance

来源：评论

学校读者我要写书评

暂无评论

AN IMPAIRMENT METRIC FOR VIDEO TEMPORAL FLUCTUATION MEASURE

引用

INTERNATIONAL JOURNAL OF IMAGE AND GRAPHICS 2011年第2期11卷 251-264页

作者： Yang, J. X. Tan, D. M. Wu, H. R. RMIT Univ Sch Elect & Comp Engn Bldg 10Swanston St Melbourne Vic 3000 Australia

Temporal fluctuations are often observed in digitally compressed videos. However, it is difficult to accurately measure these fluctuation intensities with the traditional peak signal-to-noise ratio (PSNR) since the PSNR only provides a generic quality measure. Although specialized metrics have been proposed for temporal fluctuation measurement, e.g., the sum of squared differences (SSD) and the motion compensated SSD (MCSSD), these first difference based algorithms may falsely treat smooth continuous change of pixel values as temporal fluctuations. To overcome this problem, a motion estimated mean scaled absolute second difference (MEMSASD) is proposed here. The performance of the MEMSASD is examined using a number of video sequences with varying degrees of temporal fluctuations, generated by an H. 264/AVC compliant codec using standard test video sequences. Compared with the PSNR and the SSD, the behavior of the MCSSD and the proposed metric provide better reflections of temporal fluctuation intensities as perceived by the human visual system (HVS), in terms of the Pearson correlation coefficient. The MEMSASD metric has an advantage over MCSSD in that it avoids misclassification of temporal fluctuations of pixels with smooth continuous change along the temporal axis.

关键词： Video quality metric temporal fluctuation coding artifacts H.264/AVC

来源：评论

学校读者我要写书评

暂无评论

A perceptual distortion measure for edge-like artifacts in image sequences 3

A perceptual distortion measure for edge-like artifacts in i...

引用

Conference on Human Vision & Electronic Imaging

作者： Yeh, EM Kokaram, AC Kingsbury, NG MIT Informat & Decis Syst Lab Cambridge MA 02139 USA

ISBN: (纸本)081942739X

This paper presents an objective perceptual distortion measure quantifying the visibility of edge-like blocking artifacts in coded image sequences resulting from popular transform coding techniques. The prime motivation for this work is the awareness that properties of the human visual system should be central to the design and evaluation of image coding algorithms. The perceptual metric is the output of a visual model incorporating both the spatial and temporal characteristics of the visual system. Parameters of the model are based on results from a number of visual experiments in which sensitivities to simulated blocking artifacts were measured under various spatio-temporal background conditions. The visual model takes a pair of original and distorted sequences as inputs. Distortions are calculated along the vertical and horizontal directions. Visibility dependencies on spatial, temporal and motion activities of the background are incorporated using linear filtering and motion estimation. Pixel-based distortions are combined over local spatial and temporal regions to generate an overall distortion measure for each orientation. The final model output is the sum of the vertical and horizontal distortion measures. The model was applied to coded image sequences and the resulting distortion measures were compared to outcomes of subjective ranking tests. Results indicate that the perceptual distortion measure agrees well with human evaluation.

关键词： distortion measures quality measures human visual systems visual perception motion perception image coding perceptual coding motion estimation coding artifacts

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：