Open Access Open Access  Restricted Access Subscription or Fee Access

An Innovative Efficient and Light Weighted Approach to Face Recognition using SOM

Shamla T. Mantri


This paper presents a novel Self-Organizing Map (SOM) for face recognition. The SOM method is trained on images from one database. The novelty of this work comes from the integration of Images from input database, Training and Mapping with a single method of self organize map (SOM). The method proposed is less complex, light weighted and more accurate as compare to previous studies. Face Recognition has been identified as one of the attracting research areas and it has drawn the attention of many researchers due to its varying applications such as security systems, medical systems, entertainment, etc. Face recognition is the preferred mode of identification by humans: it is natural, robust and non-intrusive. Applications of face recognition include secure access to buildings, computer systems, laptops, cellular phones, and ATMs. Face Recognition using unsupervised mode in neural network by SOM. Among the architectures and algorithms suggested for artificial neural network, the Self-Organizing Map has special property of effectively creating spatially organized „internal representation‟ of various features of input signals and their abstractions. After supervised fine tuning of its weight vectors, the Self-Organizing Map has been particularly successful in various pattern recognition tasks involving very noisy signal. So far all the face recognition systems were using combination of machine intelligent techniques for learning and classification which were making the system more complex and bulky.SOM has good feature extracting property due to its topological ordering. The Facial Analytics results for the database contain 213 images posed by 10 Japanese female models. Database reflects that the face recognition rate using one of the neural network algorithms, SOM is 98% for 10 Female.


Artificial Neural Networks, Face Recognition, ICA, Principal Component Analysis, SOM (Self-Organizing Map).

Full Text:



Teuvo Kohonen, “1990The Self Organizing Map” proc. IEEE, vol. 78, No. 9, September

M. Turk and A. Pentland , “Eigenfaces for recognition” Journal of Cognitive Neuroscience 3 (1): 1993.

M moataz, Bdelwahab Salah A. AlyIslam Yousry, “Efficient web-based facial recognition system employing 2dhog”, 11 Feb 2011

“Introduction to artificial neural networks”, Electronics Tech Direction IEEE 0-8186-7085-1, 1995.

“Face Recognition: A Convolution Neural Network Approach,” IEEE transactions on neural networks, vol. 8, no. 1, January 1997

Dr. M. Tury Taner, Rock Solid Images,” Kohonen‟s Self Organizing Networks” Nov 1997

“Special Issue on Neural Networks and Pattern Recognition” IEEE Transactions on Neural Networks, Volume 8, Number 1, pp. 98-113, 1997.

Marian Stewart Bartlett, Javier R. Movellan, “Face Recognition by ICA,” IEEE Transaction on NN Vol 13, No 6, Nov 2002.

Victor, Armand Drogos, “Concurrent Self Organizing Maps for Pattern Classification,” Proceedings of the First IEEE International Conference on Cognitive Informatics 2002 IEEE

Dinesh Kumar, “Face Recognition using Self-Organizing Map and Principal Component Analysis” 2007

Qiu Chen Kotani, K.Fei-Fei Lee, Ohmi T A, “ VQ-Based Fast Recognition Algorithm using Optimized codebook ,”Vol 1, 2008

P. Gupta, “ An Efficient Fusion-based Classifier,” IIT Kanpur INDIA. March 2009

Dinesh Kumar , “Dimention reduction using SOM based Technique for Face Recognition,” Hisar, Hariyana, INDIA 2008.

Nilesh Deotale, “2010 Face Recognition using artificial neural networks,” Vol 2

Alexandru-Cristian Mugioiu, “ Face Recognition using PCA versus ICA versus LDA cascaded with the Neural Classifier of Concurrent Self-Organizing ,”June 2010


  • There are currently no refbacks.

Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.