Super-resolution reconstruction of images based on uncontrollable microscanning and genetic algorithm

Abstract

Aiming at these disadvantages like lack of details, poor contrast and blurry edges of infrared images reconstructed by traditional controllable microscanning super-resolution reconstruction (SRR), this paper proposes a novel algorithm, which samples multiple low-resolution images (LRIs) by uncontrollable microscanning, and then uses LRIs as chromosomes of genetic algorithm (GA). After several generations of evolution, optimal LRIs are got to reconstruct the high-resolution image (HRI). The experimental results show that the average gradient of the image reconstructed by the proposed algorithm is increased to 1.5 times of that of the traditional SRR algorithm, and the amounts of information, the contrast and the visual effect of the reconstructed image are improved.

Keywords

Genetic Algorithm / Fitness Function / Pixel Point / Infrared Focal Plane Array / Optimal Chromosome

References

[1] ZhuB, LiH, GaoW, SongZ-x. Journal of Optoelectronics·Laser, 2013, 24: 2024

[2] TsaiR Y, HuangT S. Advances in Computer Vision and Image Processing, 1984, 1: 317

[3] HardieR C, BarnardK J. Optics Express, 2012, 20: 21053

[4] ZhangC, YangH-r, ChengH, WeiS. Journal of Optoelectronics·Laser, 2013, 24: 805

[5] ParkS C, ParkM K, KangM G. IEEE Signal Processing, 2003, 20: 21

[6] EladM, Hel-OrY. IEEE Transactions on Image Processing, 2001, 10: 1187

[7] FarsiuS, RobinsonM D, EladM, MilanfarP. IEEE Transactions on Image Processing, 2004, 13: 1327

[8] SchultzR R, MengL, StevensonR L. Journal of Visual Communication and Image Representation, 1998, 9: 38

[9] YeF, SuL, LiS. Chinese Optics Letters, 2006, 4: 386

[10] LiaoH, LiF, NgM K. Journal of Optical Society of America A, 2009, 26: 2311

[11] YangJ, WrightJ, HuangT S. IEEE Transactions on Image Processing, 2010, 19: 2861

[12] DaiS-s, LiuY-p. Semiconductor Optoelectronics, 2012, 33: 891

Just Accepted

This article has successfully passed peer review and final editorial review, and will soon enter typesetting, proofreading and other publishing processes. The currently displayed version is the accepted final manuscript. The officially published version will be updated with format, DOI and citation information upon launch. We recommend that you pay attention to subsequent journal notifications and preferentially cite the officially published version. Thank you for your support and cooperation.