Automatic Recognition for the Bearing of Scraped Surfaces by Image Processing Techniques
Summary
An automatic image recognition system that comprises a CCD camera, frame memory and computer, has been built to recognize the bearing of scraped surfaces. Elimination of the influence due to uneven lighting by computer software, and reduction of the noise component contained in image data by introducing the mathematical morphology method were attempted. The results were successful. Furthermore, comparison of unevenness of the scraped surface measured by coordinate measuring machine with the results obtained by the image processing system, has been made. Introduction of image processing techniques enables us to count the number of bearing spots per unit area on the scraped surface automatically, and the possibility of quantitative evaluation of flatness has also been shown.
Preview
Unable to display preview. Download preview PDF.
References
- 1.Wayne R. Moore: Foundation of Mechanical Accuracy, The Moore Special Tool Company (1970)Google Scholar
- 2.Y. Takeuchi et al.: The Recognition of Bearings by Means of a CCD Line Sensor and the Automation of Scraping Works, J. of the JSPE, 52–12 (1986) 93. (in Japanese)Google Scholar
- 3.Y. Yamane et al.: Application of Multi-Joint Type Industrial Robot to Scraping of Surface Plate, J. of the JSPE, 55–10 (1989) 55. (in Japanese)Google Scholar
- 4.H. Okamoto, M. Yamada, Y. Yonezawa: Image Processing System for Automatic Scraper, Trans. of the Society of Instrument and Control Engineers, Vol. 26, No. 6 (1990) 620. (in Japanese)CrossRefGoogle Scholar
- 5.R. M. Haralick, S. R. Sternberg, Xinhua Zhuang: Image Analysis Using Mathematical Morphology, IEEE Trans. of Pattern Analysis and Machine Intelligence, Vol. PAMI-9, No. 4 (1987) 532.CrossRefGoogle Scholar