Multi-layer perceptron mapping on a SIMD architecture

S. Vitabile1, A. Gentile2, G.B. Dammone2, F. Sorbello2
1CEntro di studio sulle Reti di Elaboratori, Italian National Council of Research, Palermo, Italy
2Dipartimento di ingegneria INFOrmatica, University of Palermo, Italy

Tóm tắt

An automatic road sign recognition system, A(RS)/sup 2/, is aimed at the detection and recognition of one or more road signs from real-world color images. The authors have proposed an A(RS)/sup 2/ able to detect and extract sign regions from real world scenes on the basis of their color and shape features. Classification is then performed on extracted candidate regions using multi-layer perceptron neural networks. Although system performances are good in terms of both sign detection and classification rates, the entire process requires a large computational time, so real-time applications are not allowed. We present the implementation of the neural layer on the Georgia Institute of Technology SIMD (single instruction, multiple data) pixel processor. Experimental trials supporting the feasibility of real-time processing on this platform are also reported.

Từ khóa

#Multilayer perceptrons #Roads #Image recognition #Concurrent computing #Computer architecture #Layout #Shape #Neural networks #Multi-layer neural network #Real time systems

Tài liệu tham khảo

gentile, 1999, Real-time image processing on a focal plane simd array, in parallel and distributed processing, Lecture Notes in Computer Science, 400, 10.1007/BFb0097923 10.1109/IVS.1994.639514 sorbello, 1999, Handwritten Character Recognition using a MLP chapter 5, 91 10.1109/PCCC.1997.581367 10.1109/IJCNN.2002.1007503 10.1109/ICIAP.2001.957071 10.1007/BF01212298 pilato, 2001, An Innovative Way to Measure the Quality of a Neural Network without the Use of the Test Set, 2002 IEEE World Congress on Computational Intelligence - IJACI International Journal of Advanced Computational Intelligence, 5, 31 10.4271/870239