Character segmentation method, device, equipment and storage medium

A character segmentation and character technology, which is applied in the field of image processing, can solve problems such as character segmentation errors and affect character recognition, and achieve the effect of small noise influence, high accuracy, and simple slope calculation

Active Publication Date: 2019-09-20
SHENZHEN YIHUA COMP +2
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The above character segmentation scheme relies on the determination of character boundaries. If the determination of character boundaries is incorrect due to noise, it will further lead to character segmentation errors, which will affect character recognition.

Method used

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
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Character segmentation method, device, equipment and storage medium
  • Character segmentation method, device, equipment and storage medium
  • Character segmentation method, device, equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0034] figure 1 It is a flow chart of the character segmentation method provided by Embodiment 1 of the present invention. This embodiment is applicable to character segmentation in the process of character recognition, especially applicable to character images with prior information, such as banknote images, license plate images, etc. The method can be performed by a character segmentation device, such as a device with computing and processing functions. Such as figure 1 As shown, the method specifically includes the following steps:

[0035] Step 110, binarize the character image to be segmented to obtain a binary image.

[0036] Wherein, the image of the character to be segmented may be an image whose boundary (upper boundary, lower boundary, left boundary and right boundary) of the entire character has been determined, and the method for determining the boundary of the character may use an existing method. The existing binarization method can be used to binarize the ima...

Embodiment 2

[0058] This embodiment provides a character segmentation method on the basis of the first embodiment above, and for character images to be segmented for which the overall character boundary has not been determined, the character boundary can also be determined by using the slope of the curve. Compared with Embodiment 1, this embodiment adds the step of determining the character boundary according to the slope of the curve, wherein, the left boundary and the right boundary of the character can be determined according to the graph of the column number and the integral column sum, and the left boundary and the right boundary of the character can be determined according to the row number and the integral sum. The graph of determines the upper and lower boundaries of the character. In this embodiment, the repeated steps in the first embodiment will not be explained in detail, please refer to the first embodiment for details.

[0059] Such as Image 6 As shown, the character segmen...

Embodiment 3

[0083] This embodiment provides a character segmentation device, which can be used to implement the character segmentation methods described in the first and second embodiments above. Such as Figure 7 As shown, the device includes: an image binarization module 710 , an integral column sum calculation module 720 , a graph creation module 730 , a segmentation position determination module 740 and a character segmentation module 750 .

[0084] The image binarization module 710 is used to binarize the character image to be segmented to obtain a binary image;

[0085] Integral column sum calculation module 720, for calculating the integral column sum of each column in the binary image respectively, wherein the integral column sum is the sum of the number of foreground points of the current column and all columns before it;

[0086] Graph building module 730, used for setting up a graph according to the integral column sum of each column;

[0087] The segmentation position determ...

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

PUM

No PUM Login to view more

Abstract

The invention discloses a character segmentation method and device, equipment and a storage medium. The method comprises the steps that binarization is performed on a character image to be segmented so as to obtain a binary image; the integral column sum of each column of the binary image is calculated, wherein the integral column sum is the sum of the number of the foreground points of the current column and all the previous columns; a curve graph is established according to the integral column sum of each column; the character segmentation position is determined according to character prior information and the slope in the curve graph; and character segmentation is performed on the binary image according to the character segmentation position. The curve graph is established by using the integral column sum, and the character segmentation position is determined according to the curve slope characteristics so that the accuracy is high without depending on determination of the character boundary and the influence of noise is low; meanwhile, slope calculation is simple without complex operation, calculation speed is fast and the time complexity is low.

Description

technical field [0001] Embodiments of the present invention relate to image processing technology, and in particular to a character segmentation method, device, equipment and storage medium. Background technique [0002] When recognizing characters, it is first necessary to preprocess the character image, such as denoising, brightness compensation, edge detection, and tilt correction, etc., and then determine the boundaries of the characters and segment the characters to obtain individual characters for character recognition. Character segmentation is an important step in the recognition process and has a great impact on the final recognition result. [0003] At present, character segmentation is generally performed according to a preset segmentation template, because the character spacing is fixed, and character boundaries can be found manually based on known character images to determine the character spacing. Based on the left boundary of the character, character segment...

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

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Patents(China)
IPC IPC(8): G06T7/11G06T7/194G06T11/20
Inventor 李杰
Owner SHENZHEN YIHUA COMP
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap