Loading...
Unified histogram equalization for defect detection on air bearing surfaces
Author(s)
Kunakornvong, Pichate
Date Issued
February 1, 2017
Type
Article
Abstract
Delivery of zero-defect products to customers in due time is key to customer satisfaction. This paper presents a new machine vision system for detecting the defects on the air bearing surface of the head gimbal assembly (HGA). The paper presents two contributions: a practical software implementation by using unified histogram equalization, and a defect detection algorithm with a block matrix technique and texture analysis. In order to test the algorithm with a real-time system, a high speed capsule conveyor was built as a new, fast in-line conveyor for transporting capsules containing HGAs. According to the experimental results, the defect detection was drastically enhanced and the performance of the proposed algorithm was satisfactory for use in a real assembly line. In other words, the visual subsystem was successful at capturing moving parts during image acquisition and at equalizing the acquired image. This new system can be used to replace a slow-speed detection system in order to increase the unit per hour production of an industrial assembly line.
Citation
International Journal of Innovative Computing Information and Control, 13(1), 1-21, 2017