Title :
Colour vision for industrial applications
Author :
Mital, Dinesh P. ; Leng, Goh Wee ; Khwang, Tech Earn
Author_Institution :
Sch. of Electr. & Electron. Eng., Nanyang Technol. Inst., Singapore
Abstract :
A vision system for colour object recognition is presented. The proposed system is low in cost and sufficiently fast and reliable for simple industrial applications. The system comprises a fiber optic illumination system lenses, a camera, a frame grabber and an IBM PC/AT microcomputer with a colour monitor. DT 2853/2873 frame grabbers are used for digitizing the image. The recognition algorithms are based on red-green-blue and hue-saturation-intensity modes. The approach and development of these algorithms are elaborated. The accuracy, reliability and speed of recognition has been very good. The recognition is based on closest path, thresholding and mathematical modeling algorithms
Keywords :
colour vision; computer vision; microcomputer applications; IBM PC/AT microcomputer; closest path; colour monitor; colour object recognition; colour vision; fiber optic illumination system; frame grabber; hue-saturation-intensity; industrial applications; red-green-blue; thresholding; vision system; Cameras; Costs; Lenses; Lighting; Machine vision; Mathematical model; Microcomputers; Monitoring; Object recognition; Optical fibers;
Conference_Titel :
TENCON '89. Fourth IEEE Region 10 International Conference
Conference_Location :
Bombay
DOI :
10.1109/TENCON.1989.176991
