Shadow detection combining characters of human vision

Abstract

A shadow detection method using pulse couple neural network inspired by the characters of human visual system is proposed. More precisely, lateral inhibition of human vision and coefficient of variation are combined together to improve the pulse couple neural network. Shadow detection is considered to be a shadow region segmentation problem. Experiment shows that the presented method is consistent with human vision compared to shadow detection methods based on HSV and pulse couple neural network (PCNN) by both subjective and objective assessments.

Keywords

pulse couple neural network / lateral inhibition / shadow detection / coefficient of variation / weight matrix / human vision system

References

[1] YangT, LiJ, PanQuan. Scene modeling and statistical learning based robust Pedestrian detection algorithm [J]. Acta Automatica Sinica, 2010, 36(4): 499-508

[2] ChenY-t, XiongY-y, TangFei. Shadow elimination approach based on region statistics and YUV color [J]. Journal of Optoelectronics Laser, 2009, 20(9): 1218-1222

[3] WeiZ, XiangZ-f, XiaokangK y, et al. . Moving cast shadows detection using ratio edge [J]. IEEE Transactions on Multimedia, 2007, 9(6): 1202-1214

[4] ZhuQ, XuS-h, HanL-tao. A new shadow extraction method from color aerial images based on dempster-shafer evidence theory [J]. Acta Automatica Sinica, 2007, 33(6): 588-595

[5] Yangj, Zhaoz-ming. Shadow processing method based on normalized RGB color model [J]. Opto-Electronic Engineering, 2007, 34(12): 92-96

[6] TangL, XieW-x, HuangJ-jun. Detection of shadow in urban color aerial images [J]. Chinese Journal of Stereology and Image Analysis, 2003, 8(3): 129-134

[7] SaninA, SandersonC, LovellB C. Shadow detection: A survey and comparative evaluation of recent methods [J]. Pattern Recognition, 2012, 45(4): 1684-1695

[8] WangZ-b, MaY-d, ChengF-yan. Review of pulse-coupled neural networks [J]. Image and Vision Computing, 2010, 28(1): 5-13

[9] ChengF-y, WangZ-b, MaY-de. A new approach for edge detection of color microscopic image using modified pulse coupled neural networks [C]. ICBBE 2009. 3rd International Conference on Bioinformatics and Biomedical Engineering, 20091-4

[10] ZhangY-d, WuL-n, WangS-hua. Color image enhancement based on HVS and PCNN [J]. Science China Information Sciences, 2010, 53(10): 1963-1976

[11] WangZ-b, MaY-d, GuJason. Multi-focus Image Fusion using PCNN [J]. Pattern Recognition, 2010, 43(6): 2003-2016

[12] KhojastehnazhandM, OmidM, TabatabaeefarA. Development of a Lemon sorting system based on color and size [J]. African Journal of Plant Science, 2010, 4(4): 122-127

[13] WangNingStudy on Shadow detection and removal [D], 2008, Beijing, Beijing Jiaotong University

[14] BiY-w, QiuT-shuang. An adaptive image segmentation method based on a simplified PCNN [J]. Acta Electronica Sinica, 2005, 334: 647-650

[15] LiJ-f, RaoW-dong. Edge detection algorithm based on intersecting cortical model [J]. Computer Engineering, 2011, 3711: 28-30

[16] KuntimadG, RanganathH S. Perfect image segmentation using pulse coupled neural networks [J]. IEEE Transactions on Neural Networks, 1999, 10(3): 591-598

[17] LiZ-r, RossH, RodneyWalker. A biologically inspired object spectral-texture descriptor and its application to vegetation classification in power-line corridors [J]. IEEE Geoscience and Remote Sensing Letters, 2011, 8(4): 631-635

[18] MengF-feng. A improved image signature based on ICM combined with SRIC [C]. IEEE International Conference on Intelligent System Design and Engineering Application, Changsha, 2010321-329

[19] ChenY-l, ParkS-k, MaY-de. A new automatic parameter setting method of a simplified PCNN for image segmentation [J]. IEEE Transactions on Neural Networks, 2011, 22(6): 880-892

[20] ZhangY-d, WuL-n, GengWei. A novel algorithm for all pairs shortest path problem based on matrix multiplication and pulse coupled neural network [J]. Digital Signal Processing, 2011, 21(4): 517-521

[21] MokhayeriF, AkbarzadehT M R. A novel facial feature extraction method based on ICM network for affective recognition [C]. Proceedings of International Joint Conference on Neural Networks, 2011, San Jose, California, USA, IEEE Press: 256-266

[22] WangY-n, GeJ, ZhangHui. Intelligent injection liquid particle inspection machine based on two-dimensional Tsallis entropy with modified pulse-coupled neural networks [J]. Engineering Applications of Artificial Intelligence, 2011, 24(11): 625-637

[23] LiuF, LiaoY-f, LiangXin. Image fusion based on nonsubsampled contourlet transform and pulse coupled [C]. 2011 Fourth International Conference on Intelligent Computation Technology and Automation, 2011312-322

[24] YaoC, ChenH-jin. Automated retinal blood vessels segmentation based on simplified PCNN and fast 2D-Otsu algorithm [J]. Journal of Central South University of Technology, 2009, 16(4): 640-646

[25] LiJ-f, ZouB-j, XinG-jiang. An image fusion method based on adaptive pulse coupled neural network [J]. Journal of Central South University (Science and Technology), 2011, 427: 2004-2010

[26] MaY-d, LiuQing. Automated image segmentation using improved PCNN model based on cross-entropy [C]. 2004 International Symposium on Intelligent Multimedia, Video and Speech Processing, 2004, Hongkong, IEEE Press: 743-746

[27] XuX-z, DingS-f, ShiZ-zhi. Particle swarm optimization for automatic parameters determination of pulse coupled neural network [J]. Journal of Computers, 2011, 6(8): 1546-1553

[28] BiX-j, ShiZhan. PCNN Parameter setting based on the clone selection algorithm [J]. Control Theory and Applications, 2009, 28(2): 4-8

[29] ChenJ-J, RenY-F, ZhengG-Yong. Contour detection model based on mechanisms of visual perception in environment of low contrast [J]. Pattern Recognition and Artificial Intelligence, 2012, 25(5): 845-850

[30] ZiF, ZhaoD-w, ZhangKe. Image pre-processing algorithm base on lateral inhibition [C]. The Eighth International Conference on Electronic Measurement and Instruments, 2007, Xi’an, China, IEEE Press: 701-705

[31] WU Xiang-long. Shadow detection based on the HSV color space transformation and MATLAB. [CP/OL]. [2011-01-21] http://blog.csdn.net/wuxianglong/article/details/6156919. (in Chinese)

[32] WangY, WangS-gen. Detection and compensation of shadows in high resolution remote sensing images using PCA [J]. Journal of Applied Sciences, 2010, 28(2): 136-141