A Novel Fast Face Recognition Method of Two-Dimensional Principal Component Analysis Based on BP Neural Networks
Pacific-Asia Workshop on Computational Intelligence and Industrial Application, IEEE (2008)
Dec. 19, 2008 to Dec. 20, 2008
Two-dimensional principal component analysis technique is an important and well-developed area of image recognition and to date this method has been put forward. A new face recognition method two-dimensional principal component analysis (2DPCA) based on BP neural networks, named 2DPCA-BP method, was proposed. 2DPCA was used to obtain a family of projected feature vectors, in which face image was projected into this family of projected feature vectors to get the feature matrix. BP-based neural network was used as classifier for its good learning capability. Experiment proved that 2DPCA-BP is better than 2DPCA-SVMs in velocity and its recognition accuracy is 98.246%. The CVL database showed that the system achieved excellent performance.
face recognition, two-dimensional component analysis (2DPCA), BP-based neural networks, face reconstruction, support vector machines (SVMs)
Wenjing Han, Jing Li, Nongliang Sun, "A Novel Fast Face Recognition Method of Two-Dimensional Principal Component Analysis Based on BP Neural Networks", Pacific-Asia Workshop on Computational Intelligence and Industrial Application, IEEE, vol. 01, no. , pp. 44-48, 2008, doi:10.1109/PACIIA.2008.220