Noisy faces recognition based on PCNN and PCA
Sun Feifei, Min He, Nie Rencan, Wu Zhangyong · 2017
An efficient method called for noisy human faces recognition is proposed based on Pulse Coupled Neural Networks(PCNN), Principal Component Analysis(PCA) and Support Vector Machine (SVM). Firstly, the method employs PCNN to cluster the characteristic region of noisy human faces image. Then, PCA is used to do dimensionality reduction and extract a feature vector for noisy human faces image. And ultimately, the SVM classifier is embedded to finish the human faces noise recognition. The experiments using the ORL faces database show that the new method has a good recognition performance for human faces image with different noise value and outstanding robustness as well.