Automatic visual inspection of complex printed patterns

• Main Author: Ang, Beng Hoe
• Other Authors: D Sundararajan
• Format: Theses and Dissertations
• Language: English
• Published: 2009
• Subjects: DRNTU::Engineering::Computer science and engineering::Computing methodologies::Pattern recognition
• Online Access: http://hdl.handle.net/10356/20427
• Institution: Nanyang Technological University

Machine vision has an increasingly important role in flexible manufacturing systems. It plays an important function in intermediate levels of production technology, such as part identification, inspection and process control. This thesis deals with the development of automatic visual inspection techniques for complex printed patterns. The main objectives are to study the problems of inspection systems and to develop a flexible system that will perform inspection on printed patterns automatically. An extensive survey was carried out in the area of automatic pattern inspection for the purposes of this project. The thesis discusses the need for and the advantages of automated visual inspection systems in manufacturing. In addition, the recent advances in the development of printed circuit board (PCB) inspection algorithms are discussed. A review of the application of mathematical morphology in image analysis is also included.