Image detection method and apparatus and terminal

1. A method implemented by a terminal with a dual-lens camera, comprising:

obtaining a color to-be-detected original image from a first lens of the dual-lens camera and a monochrome to-be-detected original image from a second lens of the dual-lens camera;

determining, in a skin detection mode, a to-be-detected original image that is in a raw format based on a to-be-detected feature, wherein the to-be-detected original image comprises the color to-be-detected original image from the first lens and the monochrome to-be-detected original image from the second lens;

processing the to-be-detected original image according to a preset rule corresponding to the to-be-detected feature to obtain a detection-specific image;

determining a normal image that is in a Joint Photographic Experts Group (JPEG) format by:

performing pixel-level synchronization on the color to-be-detected original image from the first lens and on the monochrome to-be-detected original image from the second lens; and

synthesizing a first part of the color to-be-detected original image from the first lens and a second part of the monochrome to-be-detected original image from the second lens;

detecting the detection-specific image to determine a detection result image; and

determining a to-be-displayed image based on the detection result image and the normal image.

2. The method of claim 1 , wherein the to-be-detected feature comprises a skin color, a stain, a red zone, acne, grease, a wrinkle, an eye feature, or a pore, and wherein the eye feature comprises under-eye puffiness, a dark under-eye circle, or an eye fine line.

3. The method of claim 2 , further comprising:

identifying that the to-be-detected feature comprises the skin color, the stain, the red zone, or the acne; and

determining, in response to the identifying, that the to-be-detected original image is the color to-be-detected original image.

4. The method of claim 2 , further comprising:

identifying that the to-be-detected feature comprises the grease, the wrinkle, the eye feature, or the pore; and

determining, in response to the identifying, that the to-be-detected original image is the monochrome to-be-detected original image.

5. The method of claim 1 , further comprising processing the detection result image and the normal image, using an image matching method and an image fusion method, to determine the to-be-displayed image.

6. The method of claim 1 , further comprising:

displaying a detection feature option in the skin detection mode; and

determining the to-be-detected feature based on selection of a user.

7. The method of claim 1 , further comprising displaying the to-be-displayed image.

8. An electronic device, comprising:

a dual-lens camera;

a non-transitory memory comprising instructions; and

a processor coupled to the dual-lens camera and the non-transitory memory, wherein the instructions when executed by the processor, cause the electronic device to:

obtain a color to-be-detected original image from a first lens of the dual-lens camera and a monochrome to-be-detected original image from a second lens of the dual-lens camera;

determine, in a skin detection mode, a to-be-detected original image that is in a raw format based on a to-be-detected feature, wherein the to-be-detected original image comprises the color to-be-detected original image from the first lens and the monochrome to-be-detected original image from the second lens;

process the to-be-detected original image according to a preset rule corresponding to the to-be-detected feature to obtain a detection-specific image;

determine a normal image that is in a Joint Photographic Experts Group (JPEG) format by:

performing pixel-level synchronization on the color to-be-detected original image from the first lens and on the monochrome to-be-detected original image from the second lens; and

synthesizing a first part of the color to-be-detected original image from the first lens and a second part of the monochrome to-be-detected original image from the second lens;

detect the detection-specific image to determine a detection result image; and

determine a to-be-displayed image based on the detection result image and the normal image.

9. The electronic device of claim 8 , wherein the to-be-detected feature comprises a skin color, a stain, a red zone, acne, grease, a wrinkle, an eye feature, or a pore, and wherein the eye feature comprises under-eye puffiness, a dark under-eye circle, or an eye fine line.

10. The electronic device of claim 9 , wherein the instructions further cause the electronic device to:

identify that the to-be-detected feature comprises the skin color, the stain, the red zone or the acne; and

determine, in response to the identifying, the to-be-detected original image is the color to-be-detected original image.

11. The electronic device of claim 9 , wherein the instructions further cause the electronic device to:

identify that the to-be-detected feature comprises the grease, the wrinkle, the eye feature or the pore; and

determine, in response to the identifying, that the to-be-detected original image is the monochrome to-be-detected original image.

12. The electronic device of claim 8 , wherein the instructions further cause the electronic device to process the detection result image and the normal image, using an image matching method and an image fusion method, to determine the to-be-displayed image.

13. The electronic device of claim 8 , wherein the instructions further cause the electronic device to:

display a detection feature option in the skin detection mode; and

determine the to-be-detected feature based on selection of a user.

14. The electronic device of claim 8 , wherein the instructions further cause the electronic device to display the to-be-displayed image.

15. A computer program product comprising computer-executable instructions stored on a non-transitory computer-readable medium that, when executed by a processor, cause an apparatus to:

obtain a color to-be-detected original image from a first lens of a dual-lens camera and a monochrome to-be-detected original image from a second lens of the dual-lens camera;

determine, in a skin detection mode, a to-be-detected original image that is in a raw format based on a to-be-detected feature, wherein the to-be-detected original image comprises the color to-be-detected original image from the first lens and the monochrome to-be-detected original image from the second lens;

process the to-be-detected original image according to a preset rule corresponding to the to-be-detected feature to obtain a detection-specific image;

determine a normal image that is in a Joint Photographic Experts Group (JPEG) format by:

performing pixel-level synchronization on the color to-be-detected original image from the first lens and on the monochrome to-be-detected original image from the second lens; and

synthesizing a first part of the color to-be-detected original image from the first lens and a second part of the monochrome to-be-detected original image from the second lens;

detect the detection-specific image to determine a detection result image; and

determine a to-be-displayed image based on the detection result image and the normal image.

16. The computer program product of claim 15 , wherein the computer-executable instructions further cause the apparatus to process the detection result image and the normal image, using an image matching method and an image fusion method, to determine the to-be-displayed image.

17. The computer program product of claim 15 , wherein the computer-executable instructions further cause the apparatus to:

display a detection feature option in the skin detection mode; and

determine the to-be-detected feature based on selection of a user.

18. The computer program product of claim 15 , wherein the computer-executable instructions further cause the apparatus to display the to-be-displayed image.

19. The method of claim 1 , wherein the raw format comprises 10-bit to 16-bit color information, and wherein the JPEG format comprises 8-bit color information.

20. The electronic device of claim 8 , wherein the raw format comprises 10-bit to 16-bit color information, and wherein the JPEG format comprises 8-bit color information.