Title :
Automotive airbag assembly quality visual inspection method studies based on MATLAB
Author :
Shi Xianjiang ; Zhao Yue ; Song Peng ; Sun Han ; Ling Xiaohui ; Wang Andong
Author_Institution :
Mech. & Power Eng. Coll., Harbin Univ. of Sci. & Technol., Harbin, China
Abstract :
Based on BP artificial neural network, a method for the recognition of buckle which connect the airbag gas generator brackets and decorative cover is discussed in this paper. First, MATLAB is applied for image binarization and edge extraction. Then extract linear feature of the edge by using Hough transform. Finally, BP neural network is applied for image recognition and classification. It is demonstrated by practice that this method can be used for fast and efficient recognition of completely fasten buckle and incompletely fasten buckle with high accuracy and practical value.
Keywords :
Hough transforms; assembling; automobile manufacture; automotive components; backpropagation; edge detection; feature extraction; image classification; inspection; neural nets; production engineering computing; BP artificial neural network; Hough transform; MATLAB; airbag gas generator brackets; automotive airbag assembly; backpropagation; buckle recognition; decorative cover; edge extraction; image binarization; image classification; image recognition; linear feature extraction; quality visual inspection method; BP neural network; MATLAB; aairbag; image recognition; sssembly quality;
Conference_Titel :
Computer Science and Network Technology (ICCSNT), 2012 2nd International Conference on
Conference_Location :
Changchun
Print_ISBN :
978-1-4673-2963-7
DOI :
10.1109/ICCSNT.2012.6526145
