Face recognition method based on bidirectional 2DPCA and cascade forward neural network

Abstract

The invention discloses a face recognition method based on a bidirectional 2DPCA and a cascade forward neural network, and the method generally comprises the steps: 1, carrying out the histogram equalization of an original image, and improving the contrast; 2, using bidirectional 2DPCA for feature extraction; and 3, inputting the extracted features into a cascade forward neural network for training, and establishing a face recognition classifier. According to the method, the characteristic values can be quickly and accurately extracted, the cascade forward neural network can also be used for identification, the identification accuracy is improved through continuous learning of samples, and effective identification of the human face is achieved.

Description

technical field [0001] The invention relates to a face recognition method based on bidirectional 2DPCA and cascaded forward neural network, belonging to the field of pattern recognition. Background technique [0002] In recent years, the rapid development of artificial intelligence and machine learning has made many emerging technologies possible. At present, recognition technology is one of the fields where artificial intelligence is widely used, such as face recognition and fingerprint recognition. Among them, face recognition has important applications in security, transaction payment, information security and other aspects. At present, the methods of face recognition mainly include eigenface, Fisherface and BP neural network. [0003] The eigenface is converted into a eigenvector set by using the original picture, which is called "eigenface", and the eigenvector set is used as a tool for recognition. When a picture to be recognized appears, the picture is projected in...

AI Technical Summary

Problems solved by technology

However, light has a serious impact on the recognition accuracy of the above two methods.

Images