METHOD AND APPARATUS FOR PROCESSING IMAGE

• US 20110116716A1
• Filed: 03/12/2010
• Published: 05/19/2011
• Est. Priority Date: 11/16/2009
• Status: Active Grant

• Current Assignee: Samsung Electronics Co. Ltd.
• Original Assignee: Samsung Electronics Co. Ltd.
• Inventors: KIM, Kwang-min, KWON, Joon-hwan, LEE, Seung-soo, KANG, Man-seok
• Granted Patent: US 8,396,316 B2
• Time in Patent Office: Days
• US Class Current: 382/199
• CPC Class Codes: G06V 10/993 Evaluation of the quality of the acquired pattern

Abstract

A method, apparatus, and computer readable recording medium for processing an image. The method includes detecting a face area and a blur area from an image; checking a degree of overlap between the face area and the blur area by comparing a location of the face area with a location of the blur area; and determining whether the image is an abnormal image according to the degree of overlap between the face area and the blur area.

Claims

1. A method of processing an image, the method comprising:

detecting a face area and a blur area from an image;

checking a degree of overlap between the face area and the blur area by comparing a location of the face area with a location of the blur area; and

determining whether the image is an abnormal image according to the degree of overlap between the face area and the blur area.

2. The method of claim 1, wherein the detecting of the face area and the blur area comprises:

detecting the face area based on previously analyzed facial features, and

detecting the blur area and a non-blur area of the image by analyzing a frequency component of the image.

3. The method of claim 1, wherein the checking of the degree of overlap between the face area and the blur area comprises:

obtaining a ratio of the face area to the non-blur area by comparing the blur area with the face area; and

checking the degree of overlap between the face area and the blur area according to the ratio of the face area to the non-blur area.

4. The method of claim 1, wherein the checking of the degree of overlap between the face area and the blur area comprises:

inputting an original image having an original size and converting the original image into a first binary image in which the blur area and a non-blur area are expressed with binary numbers;

converting the original image having the original size into a second binary image where the face area and the non-face area are expressed with binary numbers;

generating a third binary image by ANDing the first binary image with the second binary image; and

obtaining a ratio of the face area to the non-blur area by comparing the third binary image with the second binary image.

5. The method of claim 4, wherein the obtaining of the ratio of the face area to the non-blur area comprises:

obtaining a ratio of the face area to the non-blur area by comparing a number of pixels of an overlapping area between the face area and the non-blur area in the third binary image with a number of pixels of the face area in the second binary image.

6. The method of claim 4, wherein, if a ratio of the face area overlapping with the non-blur area is greater than a reference ratio, it is determined that the image is a normal blur image, and if the ratio of the face area overlapping with the non-blur area is less than or equal to the reference ratio, it is determined that the image is an abnormal blur image.

7. The method of claim 6, wherein, if it is determined that the image is an abnormal blur image, the method further comprises automatically correcting or removing the image.

8. The method of claim 6, wherein, if it is determined that the image is an abnormal blur image, the method further comprises displaying on a screen a menu indicating whether the image is to be restored or removed.

9. The method of claim 1, wherein, if a plurality of faces are detected in the face area, the checking of the degree of overlap between the face area and the blur area comprises determining whether there is overlap between the non-blur area and an area of a largest face from among the plurality of faces.

10. The method of claim 1, wherein, if a plurality of faces are detected in the face area, the checking of the degree of overlap between the face area and the blur area comprises checking whether there is overlap between the non-blur area and an area of a face closest to a center of the image.

11. The method of claim 1, wherein, if a plurality of faces are detected in the face area, the checking of the degree of overlap between the face area and the blur area comprises determining whether there is overlap between the non-blur area and an area of a face having a size greater than a threshold size.

12. The method of claim 1, wherein, if faces do not exist in the face area, the method further comprises:

determining a ratio of the blur area to an entire area of the image;

correcting or separately managing the image according to the ratio of the blur area to the entire area of the image.

13. An apparatus for processing an image, the apparatus comprising:

a blur detecting unit that analyzes a frequency component of an image and detects a blur area in the image;

a face area detecting unit that detects a face area in the image based on previously analyzed facial features;

a location comparing unit that obtains a ratio of the blur area to the face area by comparing a location of the blur area detected by the blur detecting unit with a location of the face area detected by the face detecting unit; and

a post-processing unit that determines whether the image is an abnormal image according to a result of the comparison performed by the location comparing unit, and corrects or removes the image if it is determined that the image is an abnormal image.

14. The apparatus of claim 13, wherein the post-processing unit determines whether a blur occurring in the image is intended according to the result of the comparison performed by the location comparing unit, and restores the image or considers the image an undesirable image according to a result of the determination of whether the blur occurring in the image is intended.

15. A computer-readable recording medium having embodied thereon a program for executing a method comprising:

detecting a face area and a blur area from an image;

checking a degree of overlap between the face area and the blur area by comparing a location of the face area with a location of the blur area; and

determining whether the image is an abnormal image according to the degree of overlap between the face area and the blur area.