International Journal of Production Research, Vol. 46, No. 8, 15 April 2008, 2165–2178 Modified gamma correction method to enhance ball grid array image for surface defect inspection CHIEN-CHENG CHUy, BERNARD C. JIANG*y and CHIEN-CHIH WANGz yYuan-Ze University, Taiwan zMing-Chi University of Technology, Taiwan (Revision received September 2006) BGA (Ball Grid Array) surface defect detection requires faster and more accurate methods for semiconductor industry applications. Traditionally, the BGA inspection used gray-scale images. However, the solder pad, wiring and gray scales shown in images depict little variance. Therefore, when the threshold value is poorly set or the contract rate is insignificant, BGA detection may fail to segment an object. This research proposes a modified methodology that uses Gamma correction for image enhancement. Three-color bands were applied to a modified Gamma correction algorithm (i.e. RGB) to better separate the high and low image contrasts. Better results were obtained by dividing the image into background and foreground portions using the Gamma correction. As a result, the proposed method improved the contrast value by 52.09%. After the images were enhanced and segmented, the compactness and internal holes were calculated as features for classification. The results showed that classification correctness was 96.43%. The proposed method used a 640  480 pixel image, performing complete defect detection 0.3 seconds faster than the traditional enhancement method, which requires 1 second. The research results provide an effective solution for the detection and classification of the BGA surface tin ball defect problem. Keywords: Gamma correction; Image enhancement; Defect detection 1. Introduction Many BGA surface defects must be detected in the BGA final inspection process for quality such as foreign articles, contamination, drip nickel, scrapes on green paint, gold-face coarseness, oxidization, edge damage and copper leak, broken hole, gold- face coarseness, and pin marks. Traditionally, the BGA inspection used gray-scale images in machine vision systems. However, the solder pad, wiring and gray scales shown in images depict little variance. Therefore, when selecting a suitable threshold value or the contract rate is insignificant; the BGA detection may fail to segment an object because the BGA substrate is composed of items in various colors. In addition, when the image is transformed from a color image into a gray-scale image, valuable information is lost for an image allows only 256 gray values and the *Corresponding author. Email: iebjiang@saturn.yzu.edu.tw International Journal of Production Research ISSN 0020–7543 print/ISSN 1366–588X online ß 2008 Taylor & Francis http://www.tandf.co.uk/journals DOI: 10.1080/00207540601042464 Downloaded By: [EBSCOHost EJS Content Distribution] At: 15:42 16 June 2009