检索结果-内蒙古大学图书馆

Face illumination processing via dense feature maps and multiple receptive fields

ELECTRONICS LETTERS 2021年第16期57卷 627-629页

作者： Ling, Shenggui Fu, Keren Lin, Ye You, Di Cheng, Peng Sichuan Univ Natl Key Lab Fundamental Sci Synthet Vis Chengdu Sichuan Peoples R China Sichuan Univ Coll Comp Sci Chengdu Sichuan Peoples R China Sichuan Univ Sch Aeronaut & Astronaut Chengdu 610065 Sichuan Peoples R China Neijiang Vocat & Tech Coll Neijiang Sichuan Peoples R China

Recently, illumination processing of facial image based on generative adversarial networks has made favourable progress. However, the image quality is not so satisfactory and the recognition accuracy is low when the face image under extreme illumination conditions. For these reasons, an elaborately-designed architecture based on convolutional neural network and generative adversarial networks for processing face illumination is presented. A novel dense feature maps loss that computes loss by using the varisized feature maps extracted from different convolutional layers of pre-trained feature network is put forward. Moreover, multiple-receptive-fields-based generator that uses multiple encoders during encoding phase is also proposed, and these encoders have the same structure with different kernel size. A variety of experimental results demonstrate that the method is superior to the state-of-the-art methods under various illumination challenges. Code will be available soon at

关键词： image and video coding image recognition Computer vision and image processing techniques Neural nets

来源：评论

学校读者我要写书评

暂无评论

Hausdorff distance for robust and adaptive template selection in visual target detection

引用

ELECTRONICS LETTERS 2002年第25期38卷 1651-1653页

作者： Gastaldo, P Zunino, R Univ Genoa DIBE I-16145 Genoa Italy

Template selection is often crucial for target-detection methods;the Hausdorff distance enhances template matching by implicitly encoding the notion of resemblance. In addition, Hausdorff metrics can build up a decision map to solve the template-sizing and selection problems adaptively. The low computational cost of the method fits video-surveillance applications.

关键词： resemblance encoding video-surveillance applications template-sizing television applications low computational cost Hausdorff metrics image matching data compression Hausdorff distance robust template selection image coding visual target detection Applications of television systems Computer vision and image processing techniques adaptive signal processing surveillance template matching image and video coding adaptive template selection decision map

来源：评论

学校读者我要写书评

暂无评论

Wavelet based image adaptive watermarking scheme

引用

ELECTRONICS LETTERS 2000年第4期36卷 312-313页

作者： Kaewkamnerd, N Rao, KR Univ Texas Dept Elect Engn Arlington TX 76019 USA

An image adaptive watermark casting method based on the wavelet transform is proposed. To increase the robustness and perceptual invisibility, the algorithm is combined with the quantisation model based on the human visual system. The number of factors that affect the noise sensitivity of the human eye are taken into consideration. Experimental results demonstrate the robustness of the algorithm to high compression environments.

关键词： wavelet transforms image and video coding Integral transforms in numerical analysis data compression perceptual invisibility image coding quantisation model quantisation (signal) compression environments robustness noise sensitivity adaptive watermarking scheme human visual system Computer vision and image processing techniques wavelet transform

来源：评论

学校读者我要写书评

暂无评论

Using inter-frame dependence history to select intra-refresh blocks

引用

ELECTRONICS LETTERS 2002年第22期38卷 1337-1338页

作者： Zhao, C Ngan, KN Zhang, J Mathew, R Zhang, X Nanyang Technol Univ Sch Comp Engn Singapore 639798 Singapore Motorola Australia Res Ctr Botany NSW 2019 Australia

To prevent error propagation in predictive video coding, intra-refresh methods are often employed. Here, a new algorithm for macroblock intra-refresh that is based on pixel level inter-frame dependence history is proposed. This new method keeps track of the coding mode of every pixel and refreshes those macroblocks that contain pixels with a long history record. Simulation results show that the new algorithm performs better than the existing methods while maintaining the same bit rate.

关键词： intra-refresh blocks selection macroblock intra-refresh image and video coding inter-frame dependence history error propagation problem video signal processing H.263 video coding MPEG-4 predictive video coding

来源：评论

学校读者我要写书评

暂无评论

Constrained VQ codebook design for noisy channels

引用

ELECTRONICS LETTERS 2001年第10期37卷 662-664页

作者： Chang, WW Hsu, HI Natl Chiao Tung Univ Dept Commun Engn Hsinchu Taiwan

A codebook design approach for constrained vector quantisation using the Hadamard transform of channel transition probabilities is proposed. It is examined for quantisation of Gauss-Markov sources over channels with m... 详细信息

关键词： block codes noise Integral transforms in numerical analysis speech coding Gauss-Markov sources noisy channels Codes probability speech compression constrained VQ codebook design image coding genetic algorithms Hadamard transforms image compression image and video coding Optimisation techniques vector quantisation channel transition probabilities Speech and audio coding constrained vector quantisation block code selection Hadamard transform

来源：评论

学校读者我要写书评

暂无评论

Method for estimating lossless image compression bound

引用

ELECTRONICS LETTERS 1999年第22期35卷 1931-1932页

作者： Zhang, N Zhang, YJ Lin, QD Lin, XG Tsing Hua Univ Dept Elect Engn Beijing 100084 Peoples R China

A practical method for estimating the lossless image compression bound based on high-order conditional entropy analysis is proposed. This analysis can be performed within an ordinary image as opposed to dealing with an enormous training set. Its feasibility and reliability have been verified on a large group of images naturally acquired by various imaging sensors.

关键词： image and video coding data compression high-order conditional entropy analysis image coding lossless image compression bound estimation entropy

来源：评论

学校读者我要写书评

暂无评论

Very low bit rate video coding using virtual SPIHT

引用

ELECTRONICS LETTERS 2001年第1期37卷 40-42页

作者： Khan, E Ghanbari, M Univ Essex Dept Elect Syst Engn Colchester CO4 3SQ Essex England

A virtual SPIHT (VSPIHT) technique that is based on the SPIHT and virtual zero-tree concepts is proposed. It combines virtually generated zero trees on the top of SPIHT's zero trees to reduce the effective number of zero trees. The simulation results show that the proposed video coder is more efficient compared to SPIHT based video coders, particularly at very low bit rates.

关键词： trees (mathematics) set partitioning in hierarchical trees VSPIHT algorithm image and video coding video coder virtual SPIHT video signal processing very low bit rate video coding virtual zero-tree concept Combinatorial mathematics video coding decoding

来源：评论

学校读者我要写书评

暂无评论

Motion vector re. nement in a Wyner-Ziv to H.264 transcoder for mobile telephony

引用

IET image PROCESSING 2009年第6期3卷 335-339页

作者： Martinez, J. L. Fernandez-Escribano, G. Kalva, H. Cuenca, P. Univ Castilla La Mancha Inst Invest Informat Albacete I3A Albacete 02071 Spain Florida Atlantic Univ Dept Comp Sci & Engn Boca Raton FL 33431 USA

The authors develop a decoder/encoder system (transcoder) to solve the consumption constraint in the communications between end-user devices, when a new Wyner-Ziv (WZ)/H.264 framework is defined for being used in mobile-to-mobile environments. This approach is based on leaving to the devices only WZ video encoding and traditional video decoding;the lowest complexity algorithms in both paradigms. The system shifts the burden of complexity to the network, where an improved transcoder that reuses information between both paradigms is allocated. The WZ decoding motion vectors are used to reduce the H. 264 motion estimation process. The proposed transcoder offers a complexity reduction up to 60% on average, without any rate distortion drop.

关键词： consumption constraint transcoding motion vector refinement Computer vision and image processing techniques image and video coding mobile-to-mobile environments video decoding motion estimation video coding Telephony lowest complexity algorithms Computational complexity video signal processing telephony encoder system computational complexity mobile radio H.264 motion estimation process Mobile radio systems mobile telephony decoder system Wyner-Ziv video encoding H.264 transcoder

来源：评论

学校读者我要写书评

暂无评论

Multifidelity JPEG based compression of images using variable quantisation

引用

ELECTRONICS LETTERS 2001年第7期37卷 423-424页

作者： Golner, MA Mikhael, WB Krishnan, V Univ Cent Florida Sch Elect Engn & Comp Sci Orlando FL 32816 USA

In image processing applications. certain regions in an image may be of greater interest to the user. For these types of applications a multifidelity region based variable quantisation scheme is proposed. The resulting subjective visual quality is considerably higher than for comparable compression ratios employing the standard JPEG implementation.

关键词： subjective visual duality image and video coding data compression multifidelity JPEG based compression compression ratios image coding quantisation (signal) image compression Computer vision and image processing techniques variable quantisation

来源：评论

学校读者我要写书评

暂无评论

Moving video object segmentation using statistical hypothesis testing

引用

ELECTRONICS LETTERS 2000年第2期36卷 128-129页

作者： Kim, M Kim, J Elect & Telecommun Res Inst Yusong Gu Taejon 305350 South Korea

Object-based coding is one of the distinct features of the MPEG-4 standard. Hence, video object segmentation is an indispensable process for MPEG-4 coding. A method of localising moving objects for video object segmentation is introduced which utilises a statistical hypothesis test without the need for true statistical parameters to be known a priori.

关键词： statistical hypothesis testing MPEG-4 coding image and video coding image segmentation normal distribution MPEG-4 standard video signal processing moving video object segmentation video coding Other topics in statistics statistical analysis

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：