GABOR BINARY PATTERN-BASED FACE RECOGNITION METHOD AND DEVICE

摘要

Provided are a Gabor binary pattern-based face recognition method and device. The device comprises: a threshold determination module for acquiring discrimination factors of all first filtering response images in a training image set using the Fisher criterion and determining thresholds of pixel points at various scales in various directions according to the discrimination factors; a filtering processing module for conducting Gabor filtering on an image to be processed so as to obtain a pre-set second filtering response image at each scale in each direction; a determination module for determining LGBP binary diagrams of the second filtering response images in accordance with the thresholds of the pixel points of the various second filtering response images; an acquisition module for acquiring a feature vector of the image to be processed according to the LGBP binary diagrams; and a recognition module for acquiring the similarity between the image to be processed and training images according to the feature vector and a feature vector of any training image in the training image set, and obtaining a recognition result according to the similarity threshold. The embodiments of the present invention can improve the discrimination capability for a face.