Title :
Machine vision algorithms for automated inspection thin-film disk heads
Author :
Sanz, Jorge L C ; Petkovic, Dragutin
Author_Institution :
IBM Almaden Res. Lab., San Jose, CA, USA
fDate :
11/1/1988 12:00:00 AM
Abstract :
Machine vision algorithms and a supporting architecture that were integrated in a fully automated prototype system for disk head inspection are presented. Some specific methods are elaborated on, including the computation of the Hough transform and multicode masks in pipeline architectures, object segmentation in textured backgrounds, and matching of extracted defects with inspection specifications. Extensive experimental results are given.
Keywords :
computer vision; computerised pattern recognition; inspection; parallel architectures; transforms; Hough transform; automatic visual inspection; computer vision; computerized pattern recognition; machine vision; multicode masks; pipeline architectures; segmentation; thin-film disk heads; Computer architecture; Computer vision; Inspection; Machine vision; Machinery production industries; Magnetic heads; Manufacturing; Prototypes; System testing; Transistors;
Journal_Title :
Pattern Analysis and Machine Intelligence, IEEE Transactions on