Optimization of stochastic networks using simulated annealing for the storage and recalling of compressed images using SOM

In this paper we are studying the optimization of Stochastic Hopfield neural network and the hybrid SOM-Hopfield neural network for the storage and recalling of fingerprint images. The feature extraction of these images has been performed using FFT, DWT and SOM. The feature vectors are stored in the Hopfield network with Hebbian learning and modified Pseudoinverse learning rules. The study explores the tolerance of Hopfield neural networks for reducing the effect of spurious minima in the recalling process by employing the Simulated annealing process. It is observed from the simulations that the capabilities of the Hopfield network can be sufficiently enhanced by making modifications in the feature extraction of the input data. DWT and SOM together can be used to significantly enhance the recall efficiency. The probability of error in recall in the form of spurious minima is minimized by adopting simulated annealing process in the pattern recalling process.

[1]  Somesh Kumar,et al.  Study of Hopfield neural network with sub-optimal and random GA for pattern recalling of English characters , 2012, Appl. Soft Comput..

[2]  Selin Aviyente,et al.  Fingerprint verification based on wavelet subbands , 2004, SPIE Defense + Commercial Sensing.

[3]  Vivek A. Sujan,et al.  Fingerprint identification using space invariant transforms , 2002, Pattern Recognit. Lett..

[4]  K. L. Du,et al.  Recurrent Neural Networks: Associative Memory and Optimization , 2011 .

[5]  Yanmin Niu,et al.  Fingerprint matching using OrientationCodes and PolyLines , 2007, Pattern Recognit..

[6]  Dinesh K. Sharma,et al.  IMAGE COMPRESSION AND FEATURE EXTRACTION WITH NEURAL NETWORK , 2007 .

[7]  Jie Tian,et al.  Image enhancement and minutiae matching in fingerprint verification , 2003, Pattern Recognit. Lett..

[8]  B. V. K. Vijaya Kumar,et al.  Fingerprint Verification Using Correlation Filters , 2003, AVBPA.

[9]  Frank Emmert-Streib,et al.  Active Learning in Recurrent Neural Networks Facilitated by a Hebb-like Learning Rule with Memory , 2005 .

[10]  Jie Tian,et al.  A minutiae matching algorithm in fingerprint verification , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

[11]  Teuvo Kohonen,et al.  Self-organization and associative memory: 3rd edition , 1989 .

[12]  R. Rosner,et al.  Optimization algorithms: simulated annealing and neural network processing , 1986 .

[13]  Sancho Salcedo-Sanz,et al.  A hybrid Hopfield network-simulated annealing approach for frequency assignment in satellite communications systems , 2004, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[14]  Hong Chen,et al.  Fingerprint matching based on global comprehensive similarity , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  C. Molter,et al.  Introduction of a Hebbian unsupervised learning algorithm to boost the encoding capacity of Hopfield networks , 2005, Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005..

[16]  Shun-ichi Amari,et al.  Learning Patterns and Pattern Sequences by Self-Organizing Nets of Threshold Elements , 1972, IEEE Transactions on Computers.

[17]  Bir Bhanu,et al.  Fingerprint matching by genetic algorithms , 2006, Pattern Recognit..

[18]  Teuvo Kohonen,et al.  Representation of Associated Data by Matrix Operators , 1973, IEEE Transactions on Computers.

[19]  W. Gareth J. Howells,et al.  Consensus fingerprint matching with genetically optimised approach , 2009, Pattern Recognit..

[20]  Anil K. Jain,et al.  Fingerprint classification and matching using a filterbank , 2001 .

[21]  B. Suman,et al.  A survey of simulated annealing as a tool for single and multiobjective optimization , 2006, J. Oper. Res. Soc..

[22]  Kate A. Smith,et al.  Neural Networks for Combinatorial Optimization: a Review of More Than a Decade of Research , 1999 .

[23]  James A. McHugh,et al.  Automated fingerprint recognition using structural matching , 1990, Pattern Recognit..

[24]  L. Personnaz,et al.  Collective computational properties of neural networks: New learning mechanisms. , 1986, Physical review. A, General physics.

[25]  Enrique Mérida Casermeiro,et al.  Hopfield Network as Associative Memory with Multiple Reference Points , 2005, IEC.

[26]  T. Kohonen.  Self-Organized Formation of Correct Feature Maps , 1982 .

[27]  Jascha Sohl-Dickstein,et al.  Efficient and optimal binary Hopfield associative memory storage using minimum probability flow , 2012, 1204.2916.

[28]  Chang-Chou Lin,et al.  Visual cryptography for gray-level images by dithering techniques , 2003, Pattern Recognit. Lett..

[29]  Mahesan Niranjan,et al.  A theoretical investigation into the performance of the Hopfield model , 1990, IEEE Trans. Neural Networks.

[30]  Nicholas Sandirasegaram,et al.  Comparative analysis of feature extraction (2D FFT and wavelet) and classification (Lp metric distances, MLP NN, and HNeT) algorithms for SAR imagery , 2005, SPIE Defense + Commercial Sensing.

[31]  Weiguo Sheng,et al.  A Memetic Fingerprint Matching Algorithm , 2007, IEEE Transactions on Information Forensics and Security.

[32]  Sharath Pankanti,et al.  Novel Approaches for Minutiae Verification in Fingerprint Images , 2005, 2005 Seventh IEEE Workshops on Applications of Computer Vision (WACV/MOTION'05) - Volume 1.

[33]  Teuvo Kohonen,et al.  Self-Organization and Associative Memory , 1988 .

[34]  Satoshi Matsuda,et al.  "Optimal" Hopfield network for combinatorial optimization with linear cost function , 1998, IEEE Trans. Neural Networks.

[35]  Safwat G. Zaky,et al.  Fingerprint identification using graph matching , 1986, Pattern Recognit..

[36]  G Athithan.  A comparative study of two learning rules for associative memory , 1995 .

[37]  Anthony Kuh,et al.  A combined self-organizing feature map and multilayer perceptron for isolated word recognition , 1992, IEEE Trans. Signal Process..

[38]  Anil K. Jain,et al.  On-line fingerprint verification , 1996, Proceedings of 13th International Conference on Pattern Recognition.

[39]  Richard Lepage,et al.  Learning and extracting edges from images by a modified Hopfield neural network , 2002, Object recognition supported by user interaction for service robots.

[40]  Sharath Pankanti,et al.  An identity-authentication system using fingerprints , 1997, Proc. IEEE.

[41]  Ye Zhang,et al.  Study on the Capacity of Hopfield Neural Networks , 2008 .

[42]  Neil Davey,et al.  High Capacity Recurrent Associative Memories , 2002, Neurocomputing.