Size Detection System for Integrated Circuit Lead Frame Using Machine Vision

Size detection of the Integrated Circuit Lead Frames (ICLF) still remains a time consuming and labor-intensive manual process. Aiming at a more practical size detection system for ICLF, a machine vision-based size detection approach is proposed in this paper. The main contributions of the proposed work are as follows. (1) A vision-based hardware system for ICLF size detection is designed. (2) Different visual components of the ICLF, including lines and circles, are accurately detected via Hough transformation. (3) With the prior knowledge of the physical size of the camera sensor, the physical size of the ICLF is finally estimated from the accurate detection results. The proposed machine vision-based system reduced the labor cost of the conventional manually based size detection method. Experimental results from real ICLFs show that the physical size error is less than 0.02mm, which verifies the accuracy of our system.