Computer vision inspection system using image processing algorithms are commonly used by many manufacturing companies as a method of quality control. Since manufacturing industries comprise of different products, various image processing algorithms are developed to suit different type of products. In conventional vision inspection system, manual configuration of the inspection algorithms is required. In this paper, we proposed a QFN faulty detection using Gabor wavelets. The proposed technique uses Gabor wavelets to decompose the image into distinctive scales and orientations. Through chi-square distance computation, the physical quality of Quad Flat No-Lead (QFN) device can be distinguished by computing the dissimilarity of the test image with the trained database. The algorithm is evaluated using 64 samples of QFN images obtained from a 0.3 megapixel monochromatic industrial smart vision camera and it achieved 98.46 accuracy with the average processing time of 0.457 seconds per image. © 2015 IEEE.