Face Recognition Using FastICA Algorithm

Autor:	Xiaoli Huang, Xianqiu Wang, Xiubi Wang
Rok vydání:	2011
Předmět:	Fastica algorithm Computer science business.industry Feature extraction Pattern recognition Independent component analysis Facial recognition system ComputingMethodologies_PATTERNRECOGNITION Robustness (computer science) Algorithm design Artificial intelligence business Decorrelation Image based
Zdroj:	2011 International Conference on Control, Automation and Systems Engineering (CASE).
Popis:	A new adaptive feature extraction method of facial image based on FastICA algorithm is presented. We present favorable comparisons to the Fixed-point ICA algorithm and the Power ICA algorithm in extensive simulations. Experimental results have demonstrated that the proposed method can not only yields the highest performance for identifying faces but also significant improves the face recognition performance.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::b1195f34f8791bc38b1aed9034f49e18 https://doi.org/10.1109/iccase.2011.5997715 Zobrazit plný text záznamu