物理学报Issue(4)：044202-1-044202-8,8.DOI:10.7498/aps.63.044202
基于局部约束群稀疏的红外图像超分辨率重建
Infrared image sup er-resolution via lo cality-constrained group sparse mo del
摘要
Abstract
Aiming at the problems of low-resolution and poor visual quality of infrared images, a locality-constrained group sparsity based infrared image super-resolution algorithm is proposed. Firstly with considering the texture self-similarity of infrared images and group structural sparsity of atom coefficients, a locality-constrained group sparse (LCGS) model is proposed. Secondly, under LCGS and K-singular value decomposition, a pair of group structural dictionaries is learned. The dictionary pair can well capture and preserve the intrinsic geometrical manifold of low and high resolution data. Finally, the high-resolution infrared images are recovered by the high-resolution dictionary and the corresponding low-resolution group sparse coefficients. Experimental results show that the proposed method obtains excellent performance in objective evaluation and subjective visual effect.关键词
红外图像/超分辨率/群稀疏/字典学习Key words
infrared image/super-resolution/group sparse/dictionary learning引用本文复制引用
邓承志,田伟,陈盼,汪胜前,朱华生,胡赛凤..基于局部约束群稀疏的红外图像超分辨率重建[J].物理学报,2014,(4):044202-1-044202-8,8.基金项目
国家自然科学基金(批准号:61162022,61362036)、江西省自然科学基金(批准号:20132BAB201021)、江西省科技落地计划(批准号：KJLD12098)和江西省教育厅科技项目(批准号：GJJ12632)资助的课题.* Project supported by the National Natural Science Foundation of China (Grant Nos.61162022,61362036), the Natural Science Foundation of Jiangxi Province, China (Grant No.20132BAB201021), the Jiangxi Science and Technology Re-search Development Project, China (Grant No. KJLD12098), and the Jiangxi Science and Technology Research Project of Education Department, China (Grant No. GJJ12632) （批准号:61162022,61362036）
