Facial recognition method and apparatus, device, and medium

A facial recognition apparatus, comprising:

• a memory storing a plurality of instructions;
• and
• a processor configured to execute the plurality of instructions, and upon execution of the plurality of instructions, is configured to:
• fuse a color map and a depth map of a facial image to obtain a fused image of the facial image, the fused image comprising two-dimensional information and depth information of the facial image;
• divide the fused image into blocks to obtain at least two image blocks of the fused image;
• irreversibly shuffle pixels in the at least two image blocks to obtain a pixel-confused facial image;
• determine an object identifier corresponding to the facial image according to the pixel-confused facial image, wherein encrypted feature point data of the fused image is obtained for determining the object identifier;
• obtaining, in response to satisfying an identifier matching failure condition, the object identifier corresponding to the facial image;
• using the pixel-confused facial image and the encrypted feature point data as target facial image data;
• and
• saving the target facial image data and the object identifier.

A non-transitory computer-readable storage medium, storing a plurality of instructions executable by a processor, and upon execution by the processor, the plurality of instructions cause the processor to:

• fuse a color map and a depth map of a facial image to obtain a fused image of the facial image, the fused image comprising two-dimensional information and depth information of the facial image;
• divide the fused image into blocks to obtain at least two image blocks of the fused image;
• irreversibly shuffle pixels in the at least two image blocks to obtain a pixel-confused facial image;
• determine an object identifier corresponding to the facial image according to the pixel-confused facial image, wherein encrypted feature point data of the fused image is obtained for determining the object identifier;
• obtaining, in response to satisfying an identifier matching failure condition, the object identifier corresponding to the facial image;
• using the pixel-confused facial image and the encrypted feature point data as target facial image data;
• and
• saving the target facial image data and the object identifier.