Photograph processing method and system

• US 10,354,125 B2
• Filed: 09/25/2017
• Issued: 07/16/2019
• Est. Priority Date: 12/16/2015
• Status: Active Grant

• Current Assignee: Tencent Technology Company Limited (Tencent Holdings Limited)
• Original Assignee: Tencent Technology Company Limited (Tencent Holdings Limited)
• Inventors: Tan, Guofu
• Primary Examiner(s): Allison, Andrae S
• Application Number:
  US15/713,990
• Publication Number:
  US 20180012066A1
• Time in Patent Office: 659 Days
• Field of Search: None
• CPC Class Codes: G06T 11/00 2D [Two Dimensional] image generation
• CPC Class Codes: G06T 11/60 Editing figures and text; Combining figures or text
• CPC Class Codes: G06T 2207/10024 Color image
• CPC Class Codes: G06T 2207/30201 Face
• CPC Class Codes: G06T 5/94 based on local image properties, e.g. for local contrast enhancement
• CPC Class Codes: G06V 40/166 using acquisition arrangements
• CPC Class Codes: G06V 40/171 Local features and components; Facial parts eye characteristics G06V40/18; Occluding parts, e.g. glasses; Geometrical relationships
• CPC Class Codes: G06V 40/18 Eye characteristics, e.g. of the iris

Abstract

Embodiments of the present invention provide a photograph processing method and system. The method includes: performing face detection on a photograph to obtain a detected human face; performing alignment on the detected human face, so as to obtain contour points of a left eye and a right eye of the detected human face; separately calculating a left eye area, being an area of the left eye, and a right eye area, being an area of the right eye, according to the contour points of the left eye and the right eye; performing stretching transformation on each pixel in the left eye area and the right eye area to generate a stretched left eye area and a stretched right eye area; and performing histogram equalization processing on the stretched left eye area and the stretched right eye area, so as to generate a processed photograph.

Claims

1. A photograph processing method, comprising:

performing face detection on a photograph to obtain a detected human face;

performing alignment on the detected human face, so as to obtain contour points of a left eye and a right eye of the detected human face;

separately calculating a left eye area, being an area of the left eye, and a right eye area, being an area of the right eye, according to the contour points of the left eye and the right eye;

performing color-stretching transformation on each pixel in the left eye area and the right eye area to generate a color-stretched left eye area and a color-stretched right eye area, comprising;

decomposing each pixel in the left eye area and the right eye area into a plurality of color attribute values corresponding to a plurality of color channels of the photograph, wherein each color attribute value of a pixel corresponds to one color channel; and

performing color-stretching transformation on each pixel by adjusting the color attribute values of each pixel using a transformation function to generate the color-stretched left eye area and the color-stretched right eye area, wherein the transformation function is configured to recolor a center area of an eye by scaling up the corresponding color attribute values and recolor an edge area of the eye by scaling down the corresponding color attribute values so that the left eye and the right eye appear rounder and brighter; and

performing histogram equalization processing on the color-stretched left eye area and the color-stretched right eye area, so as to generate a processed photograph.

2. The processing method according to claim 1, wherein the performing stretching transformation on each pixel in the left eye area and the right eye area comprises:

decomposing each pixel in the left eye area and the right eye area into a red attribute value, a green attribute value, and a blue attribute value; and

performing the color-stretching transformation on the red attribute value, the green attribute value, and the blue attribute value of each pixel to generate the color-stretched left eye area and the color-stretched right eye area.

3. The processing method according to claim 2, wherein the performing the color-stretching transformation on the red attribute value, the green attribute value, and the blue attribute value to generate the color-stretched left eye area and the color-stretched right eye area comprises:

separately inserting the red attribute value, the green attribute value, and the blue attribute value into the transformation function to perform stretching, so as to generate color-stretched color attribute values; and

separately forming the color-stretched left eye area and the color-stretched right eye area according to the color-stretched color attribute values.

4. The processing method according to claim 1, wherein the performing face detection on a photograph comprises:

performing detection on the photograph to determine a position of the detected human face; and

detecting face attributes according to the position of the detected human face.

5. The processing method according to claim 1, wherein the performing alignment on the detected human face comprises:

locating facial features of the detected human face and calculating contour points constituting the detected human face; and

extracting contour points of the left eye and contour points of the right eye from the contour points.

6. The processing method according to claim 5, wherein, before performing face detection on a photograph, the processing method further comprises:

displaying an operation interface having at least a select option and a beautify option;

selecting the photograph using the select option;

decoding the photograph to generate an RGB format photograph; and

starting the face detection on the photograph using the beautify option.

7. The processing method according to claim 6, wherein the operation interface further includes a save option and, after the performing histogram equalization processing on the color-stretched left eye area and the color-stretched right eye area, the processing method further comprises:

encoding, using the save option, the processed photograph to generate a JPEG format file.

8. The processing method according to claim 1, wherein the transformation function is uniform for the color attribute values corresponding to all color channels of the pixels in the left eye area and the right eye area.

9. The processing method according to claim 1, wherein the transformation function is a sinusoidal function.

10. A photograph processing system, comprising:

a memory storing instructions; and

a processor coupled to the memory and, when executing the instructions, configured for;

performing face detection on a photograph to obtain a detected human face;

performing alignment on the detected human face, so as to obtain contour points of a left eye and a right eye of the detected human face;

separately calculating a left eye area, being an area of the left eye, and a right eye area, being an area of the right eye, according to the contour points of the left eye and the right eye;

performing color-stretching transformation on each pixel in the left eye area and the right eye area to generate a color-stretched left eye area and a color-stretched right eye area, comprising;

decomposing each pixel in the left eye area and the right eye area into a plurality of color attribute values corresponding to a plurality of color channels of the photograph, wherein each color attribute value of a pixel corresponds to one color channel; and

performing color-stretching transformation on each pixel by adjusting the color attribute values of each pixel using a transformation function to generate the color-stretched left eye area and the color-stretched right eye area, wherein the transformation function is configured to recolor a center area of an eye by scaling up the corresponding color attribute values and recolor an edge area of the eye by scaling down the corresponding color attribute values so that the left eye and the right eye appear rounder and brighter; and

performing histogram equalization processing on the color-stretched left eye area and the color-stretched right eye area, so as to generate a processed photograph.

11. The photograph processing system according to claim 10, wherein the performing stretching transformation on each pixel in the left eye area and the right eye area comprises:

decomposing each pixel in the left eye area and the right eye area into a red attribute value, a green attribute value, and a blue attribute value; and

performing the color-stretching transformation on the red attribute value, the green attribute value, and the blue attribute value of each pixel to generate the color-stretched left eye area and the color-stretched right eye area.

12. The photograph processing system according to claim 11, wherein the performing the color-stretching transformation on the red attribute value, the green attribute value, and the blue attribute value to generate the color-stretched left eye area and the color-stretched right eye area comprises:

separately inserting the red attribute value, the green attribute value, and the blue attribute value into the transformation function to perform stretching, so as to generate color-stretched color attribute values; and

separately forming the color-stretched left eye area and the color-stretched right eye area according to the color-stretched color attribute values.

13. The photograph processing system according to claim 10, wherein the performing face detection on a photograph comprises:

performing detection on the photograph to determine a position of the detected human face; and

detecting face attributes according to the position of the detected human face.

14. The photograph processing system according to claim 10, wherein the performing alignment on the detected human face comprises:

locating facial features of the detected human face and calculating contour points constituting the detected human face; and

extracting contour points of the left eye and contour points of the right eye from the contour points.

15. The photograph processing system according to claim 14, wherein, before performing face detection on a photograph, the processor is further configured for:

displaying an operation interface having at least a select option and a beautify option;

selecting the photograph using the select option;

decoding the photograph to generate an RGB format photograph; and

starting the face detection on the photograph using the beautify option.

16. The photograph processing system according to claim 15, wherein the operation interface further includes a save option and, after the performing histogram equalization processing on the color-stretched left eye area and the color-stretched right eye area, the processor is further configured for:

encoding, using the save option, the processed photograph to generate a JPEG format file.

17. A non-transitory computer-readable storage medium containing computer-executable instructions for, when executed by a processor, performing a photograph processing method, the method comprising:

performing face detection on a photograph to obtain a detected human face;

performing alignment on the detected human face, so as to obtain contour points of a left eye and a right eye of the detected human face;

separately calculating a left eye area, being an area of the left eye, and a right eye area, being an area of the right eye, according to the contour points of the left eye and the right eye;

performing color-stretching transformation on each pixel in the left eye area and the right eye area to generate a color-stretched left eye area and a color-stretched right eye area, comprising;

decomposing each pixel in the left eye area and the right eye area into a plurality of color attribute values corresponding to a plurality of color channels of the photograph, wherein each color attribute value of a pixel corresponds to one color channel; and

performing color-stretching transformation on each pixel by adjusting the color attribute values of each pixel using a transformation function to generate the color-stretched left eye area and the color-stretched right eye area, wherein the transformation function is configured to recolor a center area of an eye by scaling up the corresponding color attribute values and recolor an edge area of the eye by scaling down the corresponding color attribute values so that the left eye and the right eye appear rounder and brighter; and

performing histogram equalization processing on the color-stretched left eye area and the color-stretched right eye area, so as to generate a processed photograph.

18. The non-transitory computer-readable storage medium according to claim 17, wherein the performing face detection on a photograph comprises:

performing detection on the photograph to determine a position of the detected human face; and

detecting face attributes according to the position of the detected human face.

19. The non-transitory computer-readable storage medium according to claim 17, wherein the performing alignment on the detected human face comprises:

locating facial features of the detected human face and calculating contour points constituting the detected human face; and

extracting contour points of the left eye and contour points of the right eye from the contour points.

20. The non-transitory computer-readable storage medium according to claim 19, wherein, before performing face detection on a photograph, the method further comprises:

displaying an operation interface having at least a select option and a beautify option;

selecting the photograph using the select option;

decoding the photograph to generate an RGB format photograph; and

starting the face detection on the photograph using the beautify option.