Image structure edge positioning method and device

An edge and image technology, applied in the field of positioning method and a positioning device for the edge of an image structure, can solve the problems of application limitations, missed detection and false detection, and achieve the effect of strong robustness and accurate positioning
CN107464245AActive Publication Date: 2017-12-12BEIJING SINOVOICE TECH CO LTD
5 Cites 8 Cited by

Patent Information

Authority / Receiving Office
CN Β· China
Current Assignee / Owner
BEIJING SINOVOICE TECH CO LTD
Publication Date
2017-12-12

Smart Images

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

Abstract

Embodiments of the invention provide an image structure edge positioning method and device. The method comprises the following steps of: detecting structure edges of a to-be-detected image through an edge detection model, and generating an edge score matrix same as the to-be-detected image in the aspect of size, wherein interested structure edge pixel points have high scores and uninterested structure edges and non-structure edge pixel points have low scores; carrying out linear detection on the edge score matrix and obtaining candidate structure edge according to the linear detection result; and finally determining a target structure edge in the candidate structure edges according to a preset constraint condition. Through the method, structure edges are positioned according to the edge score matrix, the linear detection and the constraint condition, so that relatively strong robustness is provided for illumination and shadow, and image structure edge positioning is more correct.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention relates to the technical field of computer science, in particular to a method for locating the edge of an image structure and a device for locating the edge of an image structure. Background technique

[0002] In the existing image text recognition, whether it is a photographed image or a scanned image, it is often necessary to separate the structural edges in the image before text recognition, and then perform four-point perspective transformation and layout analysis. Therefore, the location of the edge of the image structure is of great significance.

[0003] Existing image structure edge detection often uses color or grayscale gradient detection methods to determine the binary image, such as Canny operator, sobel operator, etc., and then detects straight lines from the binary image and locates the structural edge. In the process of determining the binarized image according to the gradient, it is often necessary to set the binarization...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More