Image compression via multiple learned geometric dictionaries

doi:10.1109/GlobalSIP.2016.7906066

	Image compression via multiple learned geometric dictionaries
	Danlan Huang 1; Xiaoming Tao 1; Mai Xu 2; Shenghua Gao3 ; Jianhua Lu 1
	2016-12
会议录名称	2016 IEEE GLOBAL CONFERENCE ON SIGNAL AND INFORMATION PROCESSING (GLOBALSIP)
页码	1373-1377
发表状态	已发表
DOI	10.1109/GlobalSIP.2016.7906066
摘要	In this paper, we present a novel image codec by leveraging sparse representation strategy for geometric pattern encoding. Specifically, we propose a Multiple Learned Geometric Dictionaries (MLGD) solution to explore various texture patterns of images, and use different dictionaries to encode homogenous smooth components and heterogeneous directional components. Profiting from model proficiency, our approach better preserves subtle details with high expressiveness and eliminates artifacts such as ringing and blurring. Experimental results indicate the proposed codec outperforms state-of-the-art in both numerical measures and visual fidelity, lifting the quality of experience (QoE) at low bit-rate.
关键词	Dictionaries Image coding Codecs Transform coding Decoding Training
会议地点	Washington, DC
会议日期	7-9 Dec. 2016
URL	查看原文
收录类别	EI
资助项目	National Natural Science Foundation of China[61021001] ; National Natural Science Foundation of China[61471220] ; National Natural Science Foundation of China[91538107]
出版者	Institute of Electrical and Electronics Engineers Inc.
EI入藏号	20172003679318
EI主题词	Encoding (symbols) ; Geometry ; Quality of service
EI分类号	Data Processing and Image Processing:723.2 ; Mathematics:921
原始文献类型	Conferences
引用统计	正在获取...
文献类型	会议论文
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/13364
专题	信息科学与技术学院_PI研究组_高盛华组
作者单位	1.Tsinghua National Laboratory for Information Science and Technology (TNList), Beijing, China 2.Beihang University, Beijing, China 3.ShanghaiTech University, Shanghai, China
推荐引用方式 GB/T 7714	Danlan Huang,Xiaoming Tao,Mai Xu,et al. Image compression via multiple learned geometric dictionaries[C]:Institute of Electrical and Electronics Engineers Inc.,2016:1373-1377.