Pattern recognition technique for PAD inspection using chain-code-discrete fourier transform and signal correlation

Abstract

This paper presents a new technique to recognize pattern for inspecting PAD, which is an important part in Hard Disk Drive (HDD) component and IC circuit. The proposed technique uses chain-code and discrete Fourier's transform for feature extraction, and uses signal correlation technique for classifying the pattern. The extraction of object's edge is performed to determine the position and alignment of PAD. The accuracy and inspection time of the proposed algorithm are investigated and compared with the other pattern recognition techniques, such as full template matching, coarse to fine method, etc. Experimental results show the effectiveness of the proposed technique.