Abstract

Multiband polarization epithelial tissue imaging is an effective tool to measure tissue’s birefringence and structure for quantitative pathology analysis. To discriminate the pathology accurately, high-resolution multiband polarization images are essential. But it is difficult to acquire high-resolution polarization images because of the limitations of imaging systems. The polarization image calculation process can be regarded as image fusion with fixed rules, and multiband polarization images are intrinsically sparse. In this paper, we propose a novel high-resolution multiband polarization image calculation method by utilizing the sparse representation and image fusion method. The multiband images are first represented in the sparse domain and we further introduce total-variation-regularization terms into the sparse representation framework. Then, polarization parameter images are calculated by simultaneous fusion and reconstruction. Higher quality multiband polarization images can be obtained through additional regularization constraint in the fusion process. Extensive experiments validate that the proposed method achieves much better results than many state-of-the-art algorithms in terms of both peak signal-to-noise-ratio and visual perception.

©2012 Optical Society of America

Image decomposition fusion method based on sparse representation and neural network

Lihong Chang, Xiangchu Feng, Rui Zhang, Hua Huang, Weiwei Wang, and Chen Xu
Appl. Opt. 56(28) 7969-7977 (2017)

Image fusion via nonlocal sparse K-SVD dictionary learning

Ying Li, Fangyi Li, Bendu Bai, and Qiang Shen
Appl. Opt. 55(7) 1814-1823 (2016)

Regional multifocus image fusion using sparse representation

Long Chen, Jinbo Li, and C. L. Philip Chen
Opt. Express 21(4) 5182-5197 (2013)

Multi-stage classification method oriented to aerial image based on low-rank recovery and multi-feature fusion sparse representation

Xu Ma, Yongmei Cheng, and Shuai Hao
Appl. Opt. 55(35) 10038-10044 (2016)

Infrared and visible image fusion via joint convolutional sparse representation

Minghui Wu, Yong Ma, Fan Fan, Xiaoguang Mei, and Jun Huang
J. Opt. Soc. Am. A 37(7) 1105-1115 (2020)