Multi-class Scene Recognition based on Codal Module and Neural Network
In this paper, a new scene recognition system IMSI is proposed, which based on partially connected neural evolutionary model and codal module. This module innovatively applies a new unit called codal module to connect several partially connected neural networks together. IMSI is effective for the multiclass scene recognition without feature extraction and solves the neural network oversizing problem when the scene picture becomes larger. After about 1000 generations of evolution, the average correct rate of IMSI in multiclass scene recognition achieved 77.5％. Experimental results show that our system is better than ordinary scene recognition method, single category, and more convenient to use.
genetic algorithm neural network codal modul multi-class scene recognition
Yin Wu Wei Pan
Dept. of Cognitive Science, Fujian Key Laboratory of the Brain-like Intelligent Systems,Xiamen University,Xiamen, China
国际会议
西安
英文
670-674
2011-05-27（万方平台首次上网日期，不代表论文的发表时间）