Feature Extraction from Noisy Image Using Intersecting Cortical Model

Abstract:

This paper introduces an efficient approach for feature extraction from noisy image using Intersecting Cortical Model(ICM), which is a simplified model of Pulse-Coupled Neural Network(PCNN). In our research, the entropy sequence of the output image, is obtained from the original gray image by ICM, as feature vector of the gray image, which can be used to represent the gray image, and this has been proved by our experiments. Consequently, it is used in the image classification, and the mean square error (MSE) between the feature vector of the input image and the standard feature vector is used to judge to which image groups the input image belongs. It has been proved that the method is not sensitivity with the Gaussian noise, salt and pepper noise or both of this and greatly robust for image recognition.

• Periodical: Applied Mechanics and Materials (Volumes 40-41)
• Pages: 516-522
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.40-41.516
• Online since: November 2010
• Authors: Xiao Fei Wang, Bo Nian Li, Yan Li Huang, Xin Ran Wang
• Keywords: Feature Extraction, Intersecting Cortical Model (ICM), Mean Square Error (MSE), Pattern Recognition, Pulse Coupled Neural Network (PCNN)

References

[1] Lindblad, J.M. Kinser, Image Processing Using Pulse-coupled Neural Networks, Springer Verlag, London, England, (2005).

[2] Johnson, J. L, Time Signatures of Images, Proceedings, IEEE International Conference on Neural Networks, Orlando, FL. (1994).

[3] J.M. Kinser, A simplified pulse-coupled neural network, Proc. SPIE 2760 (1996) 563–569.

[4] R. Eckhorn, H.J. Reitboeck, M. Arndt, P. Dicke, Feature linking via synchronization among distributed assemblies: Simulation of results from cat cortex Neural Comput. 2 (1990) 293.

DOI: 10.1162/neco.1990.2.3.293

[5] Ulf Ekblad, Jason M. Kinser, Jenny Atmer , Nils Zetterlund , The Intersecting Cortical Model in Image Processing[J]. Nuclear Instruments and Methods in Physics Research, Section A, 2004, 525(1-2): 392-396.

DOI: 10.1016/j.nima.2004.03.102

[6] Nazmy, T.M. Evaluation of the PCNN standard model for image processing purposes. Int. J. Intell. Comput. Inf. Sci. 4(2), 101–111.

[7] Ekblad. U , Kinser. J. M, Theoretical foundation of the intersecting cortical model and its use of change detection of aircraft, cars, and nuclear explosion tests. Signal Process. 84, 1131–1146.

DOI: 10.1016/j.sigpro.2004.03.012

[8] Y. Ma, Li Liu et al. Pulse-coupled neural networks and one-class support vector machines for geometry invariant texture retrieval[J]. Image Vis. Comput. doi: 10. 1016/j. imavis 2010. 03. 006.

DOI: 10.1016/j.imavis.2010.03.006

[9] Guangzhu Xu, Zaifeng Zhang, Yide Ma, A novel method for iris feature extraction based on intersecting cortical model network[J]. Journal of Applied Mathematics and Computing, Volume 26, Numbers 1-2, (2008, 2), 341-352.

DOI: 10.1007/s12190-007-0035-y

[10] Wang Zhaobin et al,. A Novel Method of Iris Feature Extraction Based on the ICM[C]. 2006 IEEE Proceedings of International Conference on Information Acquisition, 2006: 814-818.

DOI: 10.1109/icia.2006.305836

[11] Johnson J L. Pulse-Coupled Neural Nets: Translation, Rotation, Scale, Distortion, and Intensity Signal Invariance for Images[J]. Applied Optics, 1994, 33(26): 6239-6253.

DOI: 10.1364/ao.33.006239

[12] Johnson J L, Ritter D. Observation of Periodic Waves in a Pulse-Coupled Neural Network[J]. Optics Letters, 1993, 18(15): 1253-1255.

DOI: 10.1364/ol.18.001253

[13] G. Kuntimad H.S. Ranganath. Perfect Image segmentation using pulse coupled neural networks, IEEE Trans. Neural Networks, 1999, 10(3), pp.591-598.

DOI: 10.1109/72.761716