Edge-based fuzzy detection method

A technology of blur detection and edge, applied in image data processing, instrument, calculation, etc., can solve problems such as inaccuracy of judgment, and achieve the effect of universality and accuracy

CN103413311AActive Publication Date: 2013-11-27MEITU
3 Cites 18 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Publication Date
2013-11-27

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention discloses an edge-based fuzzy detection method. The edge-based fuzzy detection method comprises the following steps that an image is received and is processed in a graying mode to obtain an image A; strong edge detection and weak edge detection are respectively conducted on the image A, and a strong edge result B and a weak edge result C are respectively obtained; the image A is partitioned, and statistics are conducted on blocks, the strong edge result and the weak edge result to obtain strength histogram statistics, wherein the strong edge result and the weak edge result correspond to the blocks respectively; the fuzzy image probability of the image A is worked out through results of the strength histogram statistics. Due to the adoption of the scheme, no matter where an object focused on by people appears in the image, people can carry out fuzzy detection and processing on the image, and universality and accuracy of the detection method are achieved.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention relates to a computer image processing method, in particular to an edge-based fuzzy detection method. Background technique

[0002] The image will encounter the interference of external factors such as shaking, movement and focus during the photo taking process, resulting in blurring; or we use image processing software to process the image resulting in blurring.

[0003] Chinese patent publication CN103065118 discloses a method and device for image blur detection. In this patent document, a method of expanding from the inside to the outside is proposed for image blur detection. It divides the image into multiple regions from the inside to the outside. And according to the fuzzy features of each region, the global fuzzy features of the image are generated to classify. However, there are certain limitations in adopting the above scheme. The above method assumes that the center of the default image is the area where we focus on the object,...

Examples

Embodiment Construction

[0032] In order to make the technical problems, technical solutions and beneficial effects to be solved by the present invention clearer and clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

[0033] Such as figure 1 As shown, the edge-based blur detection method of the present invention includes the following steps 10-40.

[0034] Step 10, receiving the image and performing grayscale processing on the image to obtain image A.

[0035] Specifically, the grayscale processing formula may be one of the following two formulas:

[0036] Gray=0.299*Red+0.587*Green+0.114*Blue, or

[0037] Gray=(Red*306+Green*601+Blue*117+512) / 1024,

[0038] Wherein, Gray is an average gray value, and Red, Green, and Blue are respectively the average color values...