Image processing method and apparatus, device, storage medium, and computer program product

An image processing 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:
• obtaining code configured to cause at least one of the at least one processor to obtain an original image, the original image comprising biological features of a to-be-detected object;
• global detection code configured to cause at least one of the at least one processor to fuse a global frequency domain map corresponding to the original image with the original image to obtain a global fusion image, and perform living body detection on the global fusion image to obtain a first detection result corresponding to the original image;
• directly determine that the original image does not pass the living body detection when the first detection result indicates that the original image belongs to a screen reproduced image;
• local detection code configured to cause at least one of the at least one processor to obtain, when the first detection result indicates that the original image does not belong to the screen reproduced image, a biological feature image based on the biological features in the original image, fuse a local frequency domain map corresponding to the biological feature image with the biological feature image to obtain a local fusion image, perform living body detection on the local fusion image to obtain a second detection result corresponding to the original image;
• and
• determining code configured to cause at least one of the at least one processor to determine a living body detection result corresponding to the original image according to the first detection result and the second detection result.

A non-transitory computer-readable storage media storing computer code that, when executed by at least one processor, causes the at least one processor to at least:

• obtain an original image, the original image comprising biological features of a to-be-detected object;
• fuse a global frequency domain map corresponding to the original image with the original image to obtain a global fusion image;
• perform living body detection on the global fusion image to obtain a first detection result corresponding to the original image;
• directly determine that the original image does not pass the living body detection when the first detection result indicates that the original image belongs to a screen reproduced image;
• and
• obtain, when the first detection result indicates that the original image does not belong to the screen reproduced image, a biological feature image based on the biological features in the original image, fuse a local frequency domain map corresponding to the biological feature image with the biological feature image to obtain a local fusion image, perform living body detection on the local fusion image to obtain a second detection result corresponding to the original image, and determine a living body detection result corresponding to the original image according to the first detection result and the second detection result.