《人脸识别英文文献.pdf》由会员分享，可在线阅读，更多相关《人脸识别英文文献.pdf（17页珍藏版）》请在三一文库上搜索。
1、D. Bhattacharjee, M. K. Bhowmik, M. Nasipuri, D. K. Basu thus increasing the performance of the neural networks. Of course, it is very complex to construct such types of neural networks. These kinds of networks are called as auto associative neural networks. As the name implies, they use back-propag
2、ation algorithms. One of the main problems associated with back- propagation algorithms is local minima. In addition, neural networks have issues associated with learning speed, architecture selection, feature representation, modularity and scaling. Though there are problems and difficulties, the po
3、tential advantages of neural networks are vast. Pattern recognition can be done both in normal computers and neural networks. Computers use conventional arithmetic algorithms to detect whether the given pattern matches an existing one. It is a straightforward method. It will say either yes or no. It
4、 does not tolerate noisy patterns. On the other hand, neural networks can tolerate noise and, if trained properly, will respond correctly for unknown patterns. Neural networks may not perform miracles, but if constructed with the proper architecture and trained correctly with good data, they will gi
5、ve amazing results, not only in pattern recognition but also in other scientific and commercial applications 4. 2A. Network Architecture The computing world has a lot to gain from neural networks. Their ability to learn by example makes them very flexible and powerful. Once a network is trained prop
6、erly there is no need to devise an algorithm in order to perform a specific task; i.e. no need to understand the internal mechanisms of that task. The architecture of any neural networks generally used is All-Class-in- One-Network (ACON), where all the classes are lumped into one super-network. Henc
7、e, the implementation of such ACON structure in parallel environment is not possible. Also, the ACON structure has some disadvantages like the super-network has the burden to simultaneously satisfy all the error constraints by which the number of nodes in the hidden layers tends to be large. The str
8、ucture of the network is All-Classes-in-One-Network (ACON), shown in Figure 1(a) where one single network is designed to classify all the classes but in One-Class-in-One-Network D. Bhattacharjee, M. K. Bhowmik, M. Nasipuri, D. K. Basu “Classification of Fused Face Images using Multilayer Perceptron
9、Neural Network”, proceeding of International Conference on Rough sets, Fuzzy sets and Soft Computing, Nov 57, 2009, organized by Department of Mathematics, Tripura University pp. 289-300. 12. M.K. Bhowmik, D. Bhattacharjee, M. Nasipuri, D.K. Basu and M. Kundu, “Classification of Polar-Thermal Eigenf
10、aces using Multilayer Perceptron for Human Face Recognition”, proceedings of the 3rd IEEE Conference on Industrial and Information Systems (ICIIS-2008), IIT Kharagpur, India, Dec 8-10, 2008, pp. 118. 13. M.K. Bhowmik, D. Bhattacharjee, M. Nasipuri, D.K. Basu and M. Kundu, “Classification of Log-Pola
11、r-Visual Eigenfaces using Multilayer Perceptron for Human Face Recognition”, proceedings of The 2nd International Conference on Soft computing (ICSC-2008), IET, Alwar, Rajasthan, India, Nov 810, 2008, pp.107-123. D. Bhattacharjee, M. K. Bhowmik, M. Nasipuri, D. K. Basu & M. Kundu International Journ
12、al of Computer Science and Security (IJCSS), Volume (3): Issue (6) 17 14. M.K. Bhowmik, D. Bhattacharjee, M. Nasipuri, D.K. Basu and M. Kundu, “Human Face Recognition using Line Features”, proceedings of National Seminar on Recent Advances on Information Technology (RAIT-2009), Indian School of Mine
13、s University, Dhanbad, Feb 6- 7,2009, pp. 385-392. 15. P. Raviram, R.S.D. Wahidabanu Implementation of artificial neural network in concurrency control of computer integrated manufacturing (CIM) database, International Journal of Computer Science and Security (IJCSS), Volume 2, Issue 5, pp. 23-25, S
14、eptember/October 2008. 16. Teddy Mantoro, Media A. Ayu, “Toward The Recognition Of User Activity Based On User Location In Ubiquitous Computing Environments,” International Journal of Computer Science and Security (IJCSS)Volume 2, Issue 3, pp. 1-17, May/June 2008. 17. Sambasiva Rao Baragada, S. Ramakrishna, M.S. Rao, S. Purushothaman , “Implementation of Radial Basis Function Neural Network for Image Steganalysis,” International Journal of Computer Science and Security (IJCSS) Volume 2, Issue 1, pp. 12-22, January/February 2008.