COMPUTER SYSTEM AND METHOD FOR CALCULATING STRAIGHTNESS OF FACIAL

• US 20080170790A1
• Filed: 01/04/2008
• Published: 07/17/2008
• Est. Priority Date: 01/17/2007
• Status: Active Grant

• Current Assignee: ASUSTek Computer, Inc.
• Original Assignee: ASUSTek Computer, Inc.
• Inventors: Sun, Kuo-Hsiang, Hsu, Wen-Shiu, Chiu, Hsiu-Ling, Teng, Chin-Yuan
• Granted Patent: US 8,165,353 B2
• Time in Patent Office: Days
• US Class Current: 382/190
• CPC Class Codes: G06V 40/171 Local features and components; Facial parts eye characteristics G06V40/18; Occluding parts, e.g. glasses; Geometrical relationships

Abstract

A computer system and a method for calculating straightness of facial are provided. In the method, an image is processed to obtain a facial area and eyes locations. The facial area is divided into two sub-areas. Then, each of the sub-area and the corresponding symmetric image thereof are coupled together to form two reference images. Finally, the characteristic values of the facial area and two of the reference images are used for calculating the straightness of the facial area based on the principle of facial symmetry. As a result, the judgment on the straightness of the facial in an image can be more correct and objective, and the situation of taking an image with a tilted angle of facial can be avoided.

Claims

1. A method for calculating facial straightness, comprising:

capturing an image;

obtaining a facial area and locations of eyes of the image;

dividing the facial area into a first sub-area and a second sub-area according to the locations of eyes;

producing a first symmetric sub-area symmetrical to the first sub-area;

coupling the first sub-area with the first symmetric sub-area to form a reference image;

obtaining a first characteristic value of the facial area;

obtaining a second characteristic value of the reference image; and

calculating straightness of the facial area according to the first characteristic value and the second characteristic value.

2. The method according to claim 1, wherein the first sub-area is a left facial area of the facial area and the second sub-area is a right facial area of the facial area.

3. The method according to claim 1, wherein the step of dividing the facial area further comprises:

obtaining a rectangular block which is the smallest one enclosing the facial area;

determining a dividing line of the rectangular block according to the locations of eyes; and

dividing the rectangular block into the first sub-area and the second sub-area according to the dividing line.

4. The method according to claim 1, wherein the step of calculating the straightness of the facial area comprises:

treating a difference between the first characteristic value and the second characteristic value as the straightness.

5. The method according to claim 1, further comprising:

producing a second symmetric sub-area symmetrical to the second sub-area;

coupling the second sub-area with the second symmetric sub-area to form a second reference image;

obtaining a third characteristic value of the second reference image; and

calculating the straightness of the facial area according to the first characteristic value, the second characteristic value, and the third characteristic value.

6. The method according to claim 5, wherein the step of calculating the straightness of the facial area further comprises:

calculating a first difference between the first characteristic value and the second characteristic value;

calculating a second difference between the first characteristic value and the third characteristic value; and

calculating the straightness according to the first difference and the second difference.

7. The method according to claim 6, wherein the step of calculating the straightness according to the first difference and the second difference comprises:

treating an average value of the first difference and the second difference as the straightness.

8. A computer system, comprising:

an image capture unit for capturing an image; and

a processing unit connecting to the image capture unit for obtaining a facial area and locations of eyes of the image, dividing the facial area into a first sub-area and a second sub-area, producing a first symmetric sub-area symmetrical to the first sub-area, coupling the first sub-area with the first symmetric sub-area to form a reference image, and obtaining a first characteristic value of the facial area and a second characteristic value of the reference image respectively to calculate straightness of the facial area according to the first characteristic value and the second characteristic value.

9. The computer system according to claim 8, wherein the first sub-area is a left facial area of the facial area and the second sub-area is a right facial area of the facial area.

10. The computer system according to claim 8, wherein the processing unit obtains a rectangular block which is the smallest one enclosing the facial area, determines a dividing line of the rectangular block according to the locations of eyes, and divides the rectangular block into the first sub-area and the second sub-area according to the dividing line.

11. The computer system according to claim 8, wherein the processing unit calculates a difference between the first characteristic value and the second characteristic value to treat the difference as the straightness.

12. The computer system according to claim 8, wherein the processing unit produces a second symmetric sub-area symmetrical to the second sub-area, couples the second sub-area with the second symmetric sub-area to form a second reference image, and then obtains a third characteristic value of the second reference image to calculate the straightness of the facial area according to the first characteristic value, the second characteristic value, and the third characteristic value.

13. The computer system according to claim 12, wherein the processing unit calculates a first difference between the first characteristic value and the second characteristic value and a second difference between the first characteristic value and the third characteristic value, and then calculates the straightness according to the first difference and the second difference.

14. The computer system according to claim 13, wherein the processing unit calculates an average value of the first difference and the second difference to treat the average value as the straightness.

15. The computer system according to claim 8, further comprising:

a display unit connecting to the processing unit for displaying the straightness.