Title :
A new recognition algorithm with high result reliability
Author :
Xiaoyu Liu ; Zhongyuan Yu ; Yumin Liu ; Houjian Kang ; Jinhong Mu
Author_Institution :
State Key Lab. of Inf. Photonics & Opt. Commun., Beijing Univ. of Posts & Telecommun., Beijing, China
fDate :
Oct. 30 2012-Nov. 1 2012
Abstract :
High recognition rate is the aim of pattern recognition, which is difficult to obtain without ideal feature extraction. To solve this problem, a new recognition algorithm with high result reliability is proposed. The core contents of this algorithm are MSCM (multiple-set-compete method) and the algorithm of result reliability. In this paper, MSCM improving the recognition rate with nonideal feature extraction and the algorithm of result reliability are illustrated. A specific recognition case of 16 classes of sounds and the test flow of the specific case are given. The results show that the new recognition algorithm can improve the recognition rate greatly.
Keywords :
feature extraction; neural nets; pattern recognition; MSCM method; feature extraction; high result reliability algorithm; multiple-set-compete method; pattern recognition; recognition algorithm; recognition rate; Artificial neural networks; Bayes methods; Context; Feature extraction; Pattern recognition; Reliability theory; MSCM; Recognition algorithm; Recognition rate; Result reliability;
Conference_Titel :
Cloud Computing and Intelligent Systems (CCIS), 2012 IEEE 2nd International Conference on
Conference_Location :
Hangzhou
Print_ISBN :
978-1-4673-1855-6
DOI :
10.1109/CCIS.2012.6664313
