Convolutional neural network face living body detection method based on adaptive gamma enhancement

• Main Authors: WEI YIJIA, FENG JUNQIAO, ZHU XIAOHAO, WANG WENLONG, YANG DINGLI, PENG YUBIN, CAO JIE
• Format: Patent
• Language: Chinese; English
• Published: 07.06.2024
• Subjects: CALCULATING; COMPUTING; COUNTING; PHYSICS

The invention relates to the technical field of face in-vivo detection and recognition, and discloses a method and a device for performing face in-vivo detection on a multi-feature fusion image based on adaptive Gamma image enhancement and inputting the multi-feature fusion image into a convolutional neural network. The method comprises the following steps of inputting an original image of a face living body image, performing adaptive gamma enhancement on an original RGB image data set, then forming a multi-feature fusion image in combination with an LBP texture image, then loading the enhanced image into an improved ResNet50RFRFCBAM network for training, and finally performing face living body recognition through a trained system by using a test data set. And the recognition accuracy is output. Compared with the prior art, the method has the advantages that the accuracy of face living body recognition is improved on the basis of inputting the improved enhanced image without increasing detection time and trai