Abstract
Contemporary image recognition schemes either rely on single-feature recognition or focus on solving multi-feature recognition using complex computational approaches. Furthermore these approaches tend to be of tightly-coupled nature, thus not readily deployable within computational networks. Distributed Hierarchical Graph Neuron (DHGN) is a distributed single-cycle learning pattern recognition algorithm that can scale from coarse-grained to fine-grained networks and it has comparable accuracy to contemporary image recognition schemes. In this paper, we present an implementation of DHGN that works for multi-feature recognition of images. Our scheme is able to disseminate recognition of each feature within an image to a separate computational subnetwork. Thereby allowing a number of features being analysed simultaneously using a uniform recognition process. We have conducted tests on a collection of greyscale facial images. The results show that our approach produces high recognition accuracy through a simple distributed process. Furthermore, our approach implements single-cycle learning known as collaborative-comparison learning where new patterns are continuously stored using collaborative approach without affecting previously stored patterns. Our proposed scheme demonstrates higher classification accuracy in comparison with Back-Propagation Neural Network for multi-class images.
Article PDF
We’re sorry, something doesn't seem to be working properly.
Please try refreshing the page. If that doesn't work, please contact support so we can address the problem.
References
Smeulders AWM, Worring M, Santini S, Gupta A, Jain R (2000) Content-based image retrieval at the end of the early years. IEEE Trans Patt Anal Mach Intell 22: 1349–1380
Frome A, Singer Y, Sha F, Malik J (2007) Learning globally consistent local distance functions for shape-based image retrieval and classification, presented at Proceedings of IEEE Eleventh International Conference on Computer Vision (ICCV 2007). Rio de Janeiro, Brazil
Jain AK, Duin RPW, Mao J (2000) Statistical pattern recognition: a review. IEEE Trans Patt Anal Mach Intell 22: 4–37
Agrawal RK, Bala R (2008) Incremental Bayesian classification for multivariate normal distribution data. Patt Recog Lett 29: 1873–1876
Wang L (1999) Multi-associative neural networks and their applications to learning and retrieving complex spatio-temporal sequences. IEEE Trans on Systems, Man, and Cybernetics, Part B Cybernetics 29: 73–82
Raja Mahmood RA, Muhamad Amin AH, Khan AI (2008) A lightweight, fast and efficient distributed hierarchical graph neuron-based pattern classifier. Int J Intell Eng Sys 1: 9–17
Muhamad Amin AH, Raja Mahmood RA, Khan AI (2008) Analysis of pattern recognition algorithms using associative memory approach: a comparative study between the hopfield network and distributed hierarchical graph neuron (DHGN), presented at Computer and Information Technology, IEEE 8th International Conference on Computer and Information Technology Workshops, 2008.
Khan AI, Muhamad Amin AH (2007) One shot associative memory method for distorted pattern recognition. In: Orgun MA, Thornton J (eds) AI 2007: Advances in artificial intelligence, 20th Australian Joint Conference on Artificial Intelligence, Gold Coast, Australia, December 2–6, 2007, Proceedings, vol 4830. Springer, pp 705–709
Muhamad Amin AH, Khan AI (2008) Commodity-grid based distributed pattern recognition framework, presented at Sixth Australasian Symposium on Grid Computing and e-Research (AusGrid 2008). Wollongong, NSW, Australia
Nasution BB, Khan AI (2008) A hierarchical graph neuron scheme for real-time pattern recognition. IEEE Trans Neural Netw 19: 212–229
Ganti V, Gehrke J, Ramakrishnan R (1999) Mining very large databases. IEEE Computer 32: 38–45
Hopfield JJ, Tank DW (1985) Neural computation of decisions in optimization problems. Biol Cybernetics 52: 141–152
Hecht-Nielsen R (1989) Theory of the backpropagation neural network, presented at International Joint Conference on Neural Networks. 1989. IJCNN, Washington, DC, USA
Azimi-Sadjadi MR, Yao D, Jamshidi AA, Dobeck GJ (2002) Underwater target classification in changing environments using an adaptive feature mapping. IEEE Trans Neural Netw 13: 1099–1111
Browne M, Ghidary SS, Mayer NM (2008) Convolutional neural networks for image processing with applications in mobile robotics. In: Speech, Audio, Image and Biomedical Signal Processing using Neural Networks, vol 83/2008, Studies in Computational Intelligence. Springer, Berlin/Heidelberg, pp 327-349
Lu J, Yuan X, Yahagi T (2007) A method of face recognition based on fuzzy c-Means clustering and associated sub-NNs. IEEE Trans Neural Netw 18: 150–160
Hebb D (1949) The organization of behavior. Wiley, New York
Syed NA, Liu H, Sung KK (1999) Handling concept drifts in incremental learning with support vector machines, presented at Proceedings of the fifth ACM SIGKDD international conference on Knowledge discovery and data mining. San Diego, California, USA
Daucé E, Henry F (2006) Hebbian learning in large recurrent neural networks. Movement and Perception Lab, Marseille
Song F, Liu H, Zhang D, Yang J (2008) A highly scalable incremental facial feature extraction method. Neurocomputing 71: 1883–1888
Khan AI, Mihailescu P (2004) Parallel pattern recognition computations within a wireless sensor network, presented at Proceedings of the 17th International Conference on Pattern Recognition (ICPR’04). Cambridge, United Kingdom
Nascimento MA, Chitkara V (2002) Color-based image retrieval using binary signatures, presented at Proceedings of the 2002 ACM Symposium on Applied Computing (SAC’02). Madrid, Spain
Kimmel R, Shaked D, Elad M, Sobel I (2005) Space-dependent color gamut mapping: a variational approach. IEEE Trans Image Process 14: 796–803
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Muhamad Amin, A.H., Khan, A.I. Distributed Multi-Feature Recognition Scheme for Greyscale Images. Neural Process Lett 33, 45–59 (2011). https://doi.org/10.1007/s11063-010-9163-8
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11063-010-9163-8