Title :
Image capture of fibrous fracture surface based on BP-neural network and wavelet
Author :
Li, Weimei ; Li, Jing ; Zhang, Jiaquan
Author_Institution :
Key Lab. of Antennas and Microwave Technology, Xidian University, 710071, China
Abstract :
A method is proposed for image capture of fibrous fracture surface based on BP-neural network and wavelet, which solved the problem of uneven luminosity image´s obtaining. Firstly, the automatic focusing function of image acquiring system based on BP-neural network is realized in this method. Then get the best exposure value and choose several exposure values near the best exposure value to get more images. Finally, the images are fused based on wavelet. The practice proved that this method is a great way for image capture of fibrous fracture surface. It also can get high-brightness image and intact conservation of edge information.
Keywords :
Artificial neural networks; Charge coupled devices; Image edge detection; Optical fiber networks; Optical fiber theory; Training; Wavelet analysis; automatic exposure; automatic focusing; fibrous fracture surface; image fusion; neural network;
Conference_Titel :
Information Science and Engineering (ICISE), 2010 2nd International Conference on
Conference_Location :
Hangzhou, China
Print_ISBN :
978-1-4244-7616-9
DOI :
10.1109/ICISE.2010.5690292
