2 results about "Face aging" patented technology

The application provides a fine-grained face age estimation method based on horizontal pyramid matching, and relates to the technical field of image classification. The method is used for face images in different backgrounds. Firstly, the position of the face in the image is detected by using a face detection algorithm. Then, the face image is input into a residual network model Resnet50 to obtain an age feature map. The age feature map is horizontally divided into different pyramid scales to obtain multiple feature slices. Finally, global average pooling and global maximum pooling are respectively performed on each feature slice to obtain the overall age feature and the local age feature of the face, and the face age estimation is completed. The method solves the combination problem of the global feature and the local fine-grained feature of the face age, and realizes the extraction of the overall age feature and the local most recognizable fine-grained feature of the face.

This invention discloses a facial aging level analysis system based on deep metric learning, belonging to the field of intelligent facial image analysis technology. It includes modules for feature mapping, distance calculation, state inference, sequence determination, offset calculation, and result generation. The feature mapping module maps facial depth feature vectors into metric space embedding vectors via a pre-trained deep metric embedding network. The distance calculation module calculates the relative distance between the vectors and preset aging anchor vectors and constructs a distance distribution vector. The state inference module infers the optimal state evolution path based on the aging state transition graph. The sequence determination module determines the aging level and state evolution sequence. The offset calculation module solves for the physiological age offset. The result generation module integrates and outputs the analysis results. This invention achieves refined facial aging level analysis with evolutionary logic through metric space mapping and state evolution inference.