Title :
Feature Extraction from Noisy Image Using PCNN
Author :
Yide Ma ; Wang, Zhaobin ; Wu, Chenghu
Author_Institution :
Sch. of Inf. Sci. & Eng., Lanzhou Univ.
Abstract :
The entropy sequence of the output image, gotten from the original gray image by pulse-coupled neural network (PCNN), as feature vector of the gray image, can be used as a unique feature expression of gray image, which has been proved by our experiment, therefore, in this paper, it is used in the image classification, and the mean square error (MSE) between the feature vector of the input image and standard feature vector is used to judge the input image belong to which kind of image groups. At the same time, the results of our experiment show that this method is strongly flexible to resist noises and greatly robust to recognize image, if the tested images in our experiment are disturbed with Gaussian noise, impulse noise or both of this
Keywords :
Gaussian noise; feature extraction; image classification; image denoising; impulse noise; mean square error methods; Gaussian noise; feature extraction; gray image entropy sequence; image classification; image denoising; image recognition; impulse noise; mean square error; pulse-coupled neural network; Entropy; Feature extraction; Gaussian noise; Image classification; Image recognition; Impulse testing; Mean square error methods; Neural networks; Noise robustness; Resists; Feature Extraction; Pulse-Coupled Neural Network (PCNN); entropy; pattern recognition;
Conference_Titel :
Information Acquisition, 2006 IEEE International Conference on
Conference_Location :
Weihai
Print_ISBN :
1-4244-0528-9
Electronic_ISBN :
1-4244-0529-7
DOI :
10.1109/ICIA.2006.305834
