a novel infrared image super-resolution method based on sparse representation：一种基于稀疏表示的红外图像超分辨方法.pdfVIP

Infrared Physics Technology 71 (2015) 506–513 Contents lists available at ScienceDirect Infrared Physics Technology journal homepage: www.elsevi /locate/infrared A novel infrared image super-resolution method based on sparse representation Yao Zhao ⇑, Qian Chen, Xiubao Sui, Guohua Gu Jiangsu Key Laboratory of Spectral Imaging Intelligence Sense, Nanjing University of Science and Technology, Nanjing, Jiangsu Province 210094, C hina h i g h l i g h t s Instability of the sparse decomposition and self-similarity of images are considered in the training stage. Detail parts are selected as the object of the proposed method. Our method has robustness to non-uniformity. Proposed method greatly reduces the artifacts caused by the instability of the sparse decomposition. a r t i c l e i n f o a b s t r a c t Article history: This paper presents a novel method for the reconstruction of super-resolution infrared images based on Received 10 February 2015 sparse representation. Assume we can get a pair of dictionaries which makes the low-resolution image Available online 2 July 2015 patches share the same sparse representation with high-resolution image patches, then the high-resolution image patches can be reconstructed through the sparse representation of Keywords: low-resolution image patches. Firstly, considering the instability of the sparse decomposition and the Super-resolution