Face model matrix training method and apparatus, and storage medium

A face model matrix training apparatus, comprising:

• a memory;
• and
• a processor, coupled to the memory and configured to:
• obtain a face image library, the face image library comprising k groups of face images, and each group of face images comprising at least one face image of at least one person, wherein k>2, and k is an integer;
• separately parse each group of the k groups of face images, and calculate a first matrix and a second matrix according to parsing results, the first matrix being an intra-group covariance matrix of facial features of each group of face images, and the second matrix being an inter-group covariance matrix of facial features of the k groups of face images;
• and
• train face model matrices according to the first matrix and the second matrix calculated by the matrix calculator.

A non-volatile computer readable storage medium, comprising computer-executable program instructions for, when executed by a processor, performing a face model matrix training method, the method comprising:

• obtaining a face image library, the face image library comprising k groups of face images, and each group of face images comprising at least one face image of at least one person, wherein k>2, and k is an integer;
• separately parsing each group of the k groups of face images, and calculating a first matrix and a second matrix according to parsing results, the first matrix being an intra-group covariance matrix of facial features of each group of face images, and the second matrix being an inter-group covariance matrix of facial features of the k groups of face images;
• and
• training face model matrices according to the first matrix and the second matrix.