Face recognition method based on low-illumination self-adaption

Abstract

The invention discloses a face recognition method based on low-illumination self-adaption. With popularization and application of face recognition, the requirement of face recognition for recognitionprecision is multiplied, and improvement of recognition accuracy becomes a bottleneck problem of practical application. Due to the fact that under the condition of low illumination, a face image is prone to being influenced by many factors such as image backgrounds, brightness and image noise, the face recognition detection rate is not high and the recognition precision is reduced, and face recognition and application search are restricted. Under the condition, the face image under the low-illumination condition is taken as a sample; a low-illumination adaptive algorithm based on an OTSU segmentation algorithm is innovatively designed. The adaptive low-illumination environment image collection is realized, and the low-illumination face image Adaboost classification detector verifies the low-illumination environment image collection before and after processing, so that the calculation speed of the algorithm is effectively improved, and the face detection accuracy under low illuminationis improved. Verification is performed on a standard face libraries Yale B and CMU-PIE.

Description

technical field [0001] The invention relates to a face recognition method based on low-illuminance self-adaptation, which belongs to the field of image processing and can provide theoretical and technical basis for hot issues such as nighttime security monitoring and complex environment target positioning. Background technique [0002] Face recognition technology has been developed from the development of face recognition and video coding systems in the 1970s, the application of face detection based on image features to principal component analysis (Principal Component Analysis, PCA), probability model, hidden Markov model (Hidden Markov Model, The face change description of HMM), especially the classifier design and training based on neural network (Neural Networks, NN), support vector machine (Support Vector Machine, SVM), and Boosting method, has gradually entered into practical use, but under low illumination However, face recognition accuracy and detection rate have alw...

AI Technical Summary

Problems solved by technology

In face image acquisition, the lighting environment has a significant impact on the quality of face imaging, especially under low-illumination conditions, face images are easily affected by many factors such as image background, brightness and image noise, resulting in a low detection rate of face recognition. Problems such as low recognition accuracy and low recognition accuracy restrict face recognition and application search

Images