Title :
The design of parallel neural network target recognition system with many DSP
Author :
Qiao, Shuang ; Xu, Ting-fa ; Song, Jian-zhong ; Dong, Zhi-ghong
Author_Institution :
Changchun Inst. of Opt., Chinese Acad. of Sci., Changchun, China
Abstract :
This paper introduces a virtual neural network system that uses many parallel DSP to realize more targets recognition. This system is made up of DSP image capture unit, 3 parallel neural network recognition units, mobile characteristics calculation unit, syncretism logic, and corresponding software. Practical tests indicate that the statistical recognition ratio of 9 targets is more than 90% and the result can be given in 2.8ms. So this system meets the real time demand.
Keywords :
backpropagation; digital signal processing chips; image recognition; neural nets; parallel processing; virtual machines; 2.8 ms; DSP image capture unit; digital signal processing; mobile characteristics calculation unit; parallel DSP; parallel neural network recognition units; parallel neural network target recognition system; statistical recognition ratio; syncretism logic; virtual neural network system; Application software; Cameras; Character recognition; Digital signal processing; Image recognition; Logic; Neural network hardware; Neural networks; Physics; Target recognition;
Conference_Titel :
Machine Learning and Cybernetics, 2003 International Conference on
Print_ISBN :
0-7803-8131-9
DOI :
10.1109/ICMLC.2003.1260117
