1.University of Electronic Science and Technology of China, Chengdu, Sichuan 610054, China;
2.The Institute of Optics and Electronics the Chinese Academy of Sciences, Chengdu, Sichuan 610209, China
Abstract：In order to reduce the impact of craftsmanship and lighting equipment which were produced in the processing of detection, the principle of color deviation was analysed and a new algorithm of the board and between the board chromatic correction was proposed. The method firstly analyses illumination model and obtain correction function to correct the color difference between the boards,then adopts luminance channel of LAB color model and takes advantage of the accumulated illumination histogram to calculate mapping function which is to correct chrominance aberration. The experiments have shown that the algorithm correct color deviation in the board and between boards in the preprocessing of PCB detection,which improve detection accuracy and efficiency of automatic optical inspection. It will have a wide applications in the field of optical image measurement.
［1］吴凤和.基于计算机视觉测量技术的图像轮廓提取方法研究［J］.计量学报,2007,28(1): 18-22.
［2］Cheung H K, et al. A Novel Illumination Compensation Scheme for Sprite Coding［C］//Signal Processing, 2004. Proceedings ICSP '04. 2004 7th International Conference on, Beijing, China, 2004,1223-1226.
［3］黄永林,叶玉堂,陈镇龙,等.PCB导线上下线宽检测算法研究［J］.计量学报,2011,32（3）:766-771.
［4］Heidrich W, Seidel H P. Realistic, hardware accelerated shading and lighting［C］// In processing of SIGGRAPH 99, Los Angeles, USA, 1999, 171-178.
［5］Chang Y C,Reid J F. RGB calibration for color image analysis in machine vision［J］. Image Processing, IEEE Transactions on, 1996, 5(10): 1414-1422.
［6］Van Mieghem J A,Avi-Itzhak H I,Melen R D.Straight line extraction using iterative total least squares methods［J］.Journal of Visual Communication and Image Representation tation,1995,6(1):59-68.
［7］Assen H C V, Egmont Petersen M,Reiber J H C. Accurate object localization in gray level images using the center of gravity measure: Accuracy versus precision ［J］. IEEE Transactions on Image Processing(S1057-7149),2002,11(12):1379-1384.
［8］袁红中,付炜,郭永魁.一种基于动态阈值的镀铜表面缺陷检测算法 ［J］.燕山大学学报,2018,34(4):336-340.
［9］Liu K C.Color-edge detection based on discrimination of noticeable color contrasts ［J］.International Journal of Imaging Systems and Technology,2009,19(4):332-339.
［10］Chen H C,Chien W J,Wang S J. Contrast- based color image segmentation ［J］.IEEE Signal Pro cessingLetters,2004,11(7): 641-644.
［11］Wei G W.Generalized Perona-Malik equation for Image Restoration ［J］.IEEE Signal Processing Lett,1999,6(7):65-167.
2015, Vol. 36 
