Title :
Use of Hopfield neural network for complex image registration
Author :
Qian, Zhebin ; Li, Jie-gu
Author_Institution :
Inst. of Image Process. & Pattern Recognition, Shanghai Jiaotong Univ., China
Abstract :
The paper presents an image registration method based on a two-dimensional Hopfield neural network, where the problem of image matching is treated with the minimization of the energy function of the Hopfield neural network. The input data used for registration are the locations of the corner points extracted from the images. In order to improve and expedite the matching process, a fast block-based algorithm is put forward, together with the laboratory results obtained, which show the effectiveness of the algorithm
Keywords :
Hopfield neural nets; edge detection; feature extraction; image matching; image registration; minimisation; 2D Hopfield neural network; complex image registration; energy function minimization; extracted corner point location; fast block-based algorithm; image matching; input data; Data mining; Hopfield neural networks; Image matching; Image processing; Image recognition; Image registration; Intelligent robots; Minimization methods; Pattern recognition; Pixel;
Conference_Titel :
Tools with Artificial Intelligence, 1997. Proceedings., Ninth IEEE International Conference on
Conference_Location :
Newport Beach, CA
Print_ISBN :
0-8186-8203-5
DOI :
10.1109/TAI.1997.632257
