Title :
A method of detecting bearing´s quality based on image edge morphologic analysis
Author :
Qin, Wei ; Pei, Song-Wen ; Zhang, Shi-Le ; Wu, Bai-Feng
Author_Institution :
Sch. of Comput. Sci., Fudan Univ., Shanghai, China
Abstract :
In this paper, a method of detecting industrial bearing´s quality based on image edge morphologic analysis and recognition technology was proposed. The image filter, enhancement and segmentation were adopted to pre-process the image and a novel image coding method based on relative direction coding was presented as well. Furthermore, an improved method based on image edge morphologic analysis was proposed, which can analyze the image edge with large quantities. Finally, a customized neural network classifier was utilized to sort images. The experimental results show that the approach to detecting bearing´s quality is effective and practical.
Keywords :
filtering theory; image coding; image enhancement; image segmentation; machine bearings; bearing quality detection; image coding method; image edge morphologic analysis; image enhancement; image filter; image segmentation; image sorting; recognition technology; relative direction coding; Cameras; Computer science; Filtering; Image analysis; Image coding; Image edge detection; Image recognition; Manufacturing industries; Neural networks; Optical filters; customized neural network classifier; image edge morphologic analysis; novel image coding method;
Conference_Titel :
Computer-Aided Industrial Design & Conceptual Design, 2009. CAID & CD 2009. IEEE 10th International Conference on
Conference_Location :
Wenzhou
Print_ISBN :
978-1-4244-5266-8
Electronic_ISBN :
978-1-4244-5268-2
DOI :
10.1109/CAIDCD.2009.5374893
