TY  - JOUR
SP  - 45
TI  - Distributed multi-feature recognition scheme for greyscale images
N1  - cited By 3
AV  - none
EP  - 59
SN  - 13704621
KW  - Back propagation neural networks; Classification accuracy; Coarse-grained; Collaborative approach; Computational approach; Computational networks; Distributed process; Facial images; Feature recognition; Grey scale images; Greyscale; Hierarchical graphs; Learning patterns; Multi-class; Parallel and distributed processing; Recognition accuracy; Recognition process; Single cycle; Stored pattern; Sub-network; Tightly-coupled
KW  -  Distributed parameter networks; Image recognition; Neural networks
KW  -  Feature extraction
ID  - scholars2255
IS  - 1
N2  - 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. © 2010 Springer Science+Business Media, LLC.
VL  - 33
UR  - https://www.scopus.com/inward/record.uri?eid=2-s2.0-79751533644&doi=10.1007%2fs11063-010-9163-8&partnerID=40&md5=6c316509f80c70729c573e8d9f1270d6
A1  - Muhamad Amin, A.H.
A1  - Khan, A.I.
JF  - Neural Processing Letters
Y1  - 2011///
ER  -