Method and system for processing images

• US 8,416,314 B2
• Filed: 08/20/2010
• Issued: 04/09/2013
• Est. Priority Date: 03/05/2008
• Status: Active Grant

• Current Assignee: Huawei Device Company Limited (Huawei Investment & Holding Co., Ltd.)
• Original Assignee: Huawei Device Company Limited (Huawei Investment & Holding Co., Ltd.)
• Inventors: Li, Kai, Liu, Yuan
• Primary Examiner(s): MOE, AUNG SOE
• Application Number:
  US12/860,339
• Publication Number:
  US 20100315512A1
• Time in Patent Office: 963 Days
• Field of Search: 348/207.99, 348/222.1, 348/175, 348/180, 348/239, 348/188, 382/190, 382/191, 382/194, 382/181, 382/276, 382/173
• US Class Current: 348/222.1
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/20224 Image subtraction
• CPC Class Codes: G06T 7/0002 Inspection of images, e.g. flaw detection
• CPC Class Codes: H04N 17/002 for television cameras

Abstract

A method for processing images includes: obtaining video images or capturing a series of images in real time; detecting difference between two adjacent images, and reserving one of the images when the difference is less than a preset threshold; detecting feature information of the obtained images; and performing definition-related treatment for the images detected as having the feature information, comparing definition of each image with a preset definition criterion, and reserving clear images.

Claims

1. An image processing method, comprising:

capturing two images;

detecting a difference between the two images;

reserving one of the two images when the difference is less than a preset threshold;

detecting feature information of one of the two images;

performing definition-related treatment for the image having detected feature information; and

reserving a clear image according to the definition-related treatment;

wherein, before performing the definition-related treatment, the method further comprises cropping the image having the detected feature information so as to increase a percentage of the detected feature information to the whole image;

wherein performing the definition-related treatment, and reserving the clear image according to the definition-related treatment comprises at least one of;

graying the cropped image;

calculating a gradient value of the grayed image;

outputting a grayscale image which comprises edge information;

setting a grayscale image threshold as a definition criterion according to the grayscale image;

binarizing the cropped image;

obtaining a binarized threshold corresponding to the binarized image;

determining that the image is clear and reserving the image if the binarized threshold corresponding to the binarized image is less than the grayscale image threshold; and

graying the cropped image;

calculating a gradient value of the grayed image;

outputting a grayscale image which comprises edge information;

using a total sum of white pixel points of the edge information of the grayscale image or a percentage of the edge information to the whole image as a definition criterion;

binarizing the cropped image;

obtaining a total sum of white pixel points of the edge information in the binarized image or the percentage of the edge information to the whole image;

determining that the image is clear and reserving the image if the total sum of the white pixel points of the edge information in the binarized image or the percentage of the edge information to the whole image is less than the definition criterion.

2. The image processing method according to claim 1, wherein, after reserving the clear image, the method further comprises capturing additional images if a number of the reserved images does not reach a set number.

3. The image processing method according claim 1, further comprising performing camera calibration according to the reserved clear image and corresponding feature information, and obtaining internal and external parameters of a camera.

4. The image processing method according to claim 1, wherein the feature information comprises one or more of color feature information, brightness feature information, and geometric feature information.

5. The image processing method according to claim 4, wherein the color feature information and the brightness feature information comprise at least one of grayscale feature information, binarized image feature information, and color change feature information.

6. The image processing method according to claim 4, wherein the geometric feature information comprises at least one of edge, profile, vertex, straight line, circle, arc, ellipse, rectangle and curve feature information.

7. The image processing method according to claim 1, wherein detecting feature information comprises:

reading the image;

detecting the feature information of the image; and

judging whether a number of actually detected feature information is the same as a theoretic number of feature information and, if so, proceeding with subsequent operations, otherwise, discarding the detected image, and detecting an image next to the detected image.

8. The image processing method according to claim 1, wherein cropping the image comprises:

obtaining coordinates of the feature information of the image;

obtaining a maximum value and a minimum value of an X-coordinate and a Y-coordinate of each point corresponding to the feature information, and obtaining an image suitable for cropping;

obtaining a boundary formed by points corresponding to the feature information according to the coordinates of the points corresponding to the feature information of the image;

cutting away an area outside the boundary formed by the points and outside an image suitable for cropping; and

obtaining a cropped image according to image information inside the boundary formed by the points.

9. The image processing method according to claim 1, wherein detecting the difference between the two images comprises:

obtaining information about feature points of the two images;

calculating coordinate differences between the feature points in all corresponding positions, and calculating a mean value of coordinate differences; and

judging whether the mean value is less than a preset threshold;

if so, discarding one of the images;

otherwise, proceeding with subsequent operations.

10. The image processing method according to claim 1, wherein performing the definition-related treatment comprises:

calculating content of high frequency components in the feature information of the image; and

if the content of the high frequency components in the feature information of the image is greater than a content of the high frequency components corresponding to the preset definition criterion, determining that the image is clear or in focus.

11. An image processing system, comprising:

an image obtaining module adapted to obtain video images or capture a series of images;

an image difference detecting module adapted to detect a difference between two images and to reserve one of the images when the difference is less than a preset threshold;

a feature information detecting module adapted to detect feature information of the obtained video images or the series of images and to obtain images that have distinct feature information; and

an image definition judging module, adapted to perform definition-related treatment for the images that have the feature information; and

when an image is unclear, to discard the image so that the image obtaining module continues to select a next image;

the system further comprising an image cropping module, adapted to crop the images that have the feature information;

wherein the image definition judging module adapted to perform definition-related treatment comprises at least one of;

gray the cropped image;

calculate a gradient value of the grayed image;

output a grayscale image which comprises edge information;

set a grayscale image threshold as a definition criterion according to the grayscale image;

binarize the cropped image;

obtain a binarized threshold corresponding to the binarized image;

determine that the image is clear and reserving the image if the binarized threshold corresponding to the binarized image is less than the grayscale image threshold; and

gray the cropped image;

calculate a gradient value of the grayed image;

output grayscale image which comprises edge information;

use a total sum of white pixel points of the edge information of the grayscale image or a percentage of the edge information to the whole image as a definition criterion;

binarize the cropped image;

obtain a total sum of white pixel points of the edge information in the binarized image or the percentage of the edge information to the whole image;

determine that the image is clear and reserving the image if the total sum of the white pixel points of the edge information in the binarized image or the percentage of the edge information to the whole image is less than the definition criterion.

12. The image processing system according to claim 11, further comprising an image number judging module, adapted to detect a number of stored images, and to make the image obtaining module select a next image for subsequent operations if the number of stored images does not reach a set number.

13. The image processing system according to claim 11, further comprising a calibrating module, adapted to obtain internal and external parameters of a video obtaining device according to the obtained clear images and the corresponding feature information, and to calibrate the video obtaining device.