3D image classification method and apparatus, device, and storage medium

A three-dimensional (3D) image classification apparatus, comprising:

• at least one memory configured to store program code;
• and
• at least one processor configured to read the program code and operate as instructed by the program code, the program code comprising:
• image obtaining code configured to cause the at least one processor to obtain a 3D image, the 3D image comprising image information of a first dimension, image information of a second dimension, and image information of a third dimension, wherein the first dimension, the second dimension, and the third dimension are respectively represented by X, Y, and Z in a 3D coordinate system;
• first extraction code configured to cause the at least one processor to extract a first image feature corresponding to planar image information from the 3D image, the planar image information corresponding to at least one region in a plane comprising the first dimension and the second dimension;
• second extraction code configured to cause the at least one processor to extract, from the 3D image, a second image feature corresponding to the image information of the third dimension;
• feature fusion code configured to cause the at least one processor to fuse the first image feature and the second image feature, to obtain a fused image feature;
• and
• image classification code configured to cause the at least one processor to determine a result of classifying the 3D image according to the fused image feature.

A non-transitory computer-readable storage medium, storing at least one instruction, the at least one instruction being loaded and executed by a processor to perform:

• obtaining a 3D image, the 3D image comprising image information of a first dimension, image information of a second dimension, and image information of a third dimension, wherein the first dimension, the second dimension, and the third dimension are respectively represented by X, Y, and Z in a 3D coordinate system;
• extracting a first image feature corresponding to planar image information from the 3D image, the planar image information corresponding to at least one region in a plane comprising the first dimension and the second dimension;
• extracting, from the 3D image, a second image feature corresponding to the image information of the third dimension;
• fusing the first image feature and the second image feature, to obtain a fused image feature;
• and
• determining a result of classifying the 3D image according to the fused image feature.