Wuhan University

China Railway Wuhan Survey and Design Institute Co., Ltd.

China Railway Major Bridge Reconnaissance & Design Institute Co., Ltd.

Jiajun Cai

Lei Wang

Zhenfeng Shao

Feng Zhang

Zhongyuan Wang

Jingmin Yang

Zongyu Gao

Rui Li

Wen Gu

Nana Lei

Anguan Chen

Anrui Li

He Zhang

Changyu Liu

Zexing Huang

Jianan Zhang

Yunfeng Cai

Zengli Wang

Yusong Xiao

A method for reconstructing a super-resolution image, including: 1) reducing the resolution of an original high-resolution image to obtain an equal low-resolution image, respectively expressed as matrix forms yand y; 2) respectively conducting dictionary training on yand yto obtain a low-resolution image dictionary D; 3) dividing the sparse representation coefficients &#x3b1;and &#x3b1;into training sample coefficients &#x3b1;and &#x3b1;and test sample coefficients &#x3b1;and &#x3b1;; 4) constructing an L-layer deep learning network using a root-mean-square error as a cost function; 5) iteratively optimizing network parameters so as to minimize the cost function by using the low-resolution image sparse coefficient &#x3b1;as the input of the deep learning network; 6) inputting the low-resolution image sparse coefficient &#x3b1;as the test portion into the trained deep learning network in 5), outputting to obtain a predicted difference image sparse coefficient {circumflex over (&#x3b1;)}, computing an error between the {circumflex over (&#x3b1;)}.

Method and system for reconstructing super-resolution image

Growing community of inventors

Wuhan, China

Jiajun Cai