Title :
Automatic edge and target extraction base on pulse-couple neuron networks wavelet theory (PCNNW)
Author :
Berthe, Kya ; Yang, Yang
Author_Institution :
Inf. Eng. Sch., Beijing Univ. of Sci. & Technol., China
Abstract :
Recent developments in pulse-coupled neural networks (PCNN) techniques provide is efficiency in edge and target extraction. The detection of targets is facilitated by PCNN multiscale image factorization. But noise is still the enemy of PCNN. An efficient new pulse-coupled neural networks technique has been proposed by combining with wavelet theory. The new pulse-couple neuron network (PCNNW) is based on multiresolution decomposition for extracting the features of interest in the images by eliminating the noise. On the other hand the wavelet coefficients provide supplemental discrimination and lead to characteristic sets of numbers useful in identifying image factors of interest. The efficiency of the new method has been attested through some test images
Keywords :
edge detection; neural nets; noise; wavelet transforms; PCNN multiscale image factorization; PCNNW; edge extraction; feature extraction; multiresolution decomposition; noise; noise elimination; pulse-couple neuron networks wavelet theory; pulse-coupled neural networks; target extraction; Biological neural networks; Data mining; Feature extraction; Filters; Image edge detection; Joining processes; Neural networks; Neurons; Wavelet coefficients; Wavelet transforms;
Conference_Titel :
Info-tech and Info-net, 2001. Proceedings. ICII 2001 - Beijing. 2001 International Conferences on
Conference_Location :
Beijing
Print_ISBN :
0-7803-7010-4
DOI :
10.1109/ICII.2001.983107
