A positioning method and device for image text

A positioning method and positioning device technology, applied in the field of image processing, can solve problems such as difficult models, low accuracy, and insufficient application scenarios, and achieve the effect of overcoming technical problems and improving accuracy

Inactive Publication Date: 2021-03-30
GUANGDONG XIAOTIANCAI TECH CO LTD
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] At present, traditional text positioning is mainly based on extracting relevant text features to distinguish fields and backgrounds. However, this method is mainly suitable for printed text positioning. Positioning is performed through the characteristic parameters of printed text. The accuracy rate is not high, and it is suitable for scenarios. not wide enough
In addition, there is also a method to achieve text positioning by training a deep neural network. However, this method often requires a large amount of manually labeled data for training, which consumes a lot of resources for modeling. At the same time, it is difficult to directly train a well-trained model. Expand to more other application scenarios

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
  • A positioning method and device for image text
  • A positioning method and device for image text
  • A positioning method and device for image text

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0070] see figure 1 , figure 1 It is a schematic flowchart of a method for locating image characters disclosed in an embodiment of the present invention. Among them, the method shown in the embodiment of the present invention is applicable to electronic devices, such as smart phones, tablet computers, and desktop computers, etc., to quickly and accurately locate the position of each character from the captured character image, so as to facilitate subsequent character recognition To achieve the purpose of extracting text information from text images, the method and device for locating text in images provided in the embodiments of the present invention may be the above-mentioned electronic equipment. Such as figure 1 As shown, the positioning method of the image text may include the following steps:

[0071] 101. Perform connected domain marking on a text image to obtain at least one text connected domain.

[0072] In the embodiment of the present invention, before step 101 ...

Embodiment 2

[0082] see figure 2 , figure 2 It is a schematic flow chart of another image text positioning method disclosed in the embodiment of the present invention. Such as figure 2 As shown, the positioning method of the image text may include the following steps:

[0083] 201. Perform connected domain marking on the text image to obtain at least one text connected domain.

[0084] 202. Calculate an area corresponding to at least one text-connected domain, and filter out text-connected domains whose area exceeds a preset area threshold, to obtain at least one target text-connected domain.

[0085] In the embodiment of the present invention, text connected domains whose area exceeds the preset area threshold can be preliminarily determined as connected domains of non-text content, and can be connected domains corresponding to icons in the image, so these text connected domains with too large areas need to be filter processing.

[0086]203. Sorting at least one target text connec...

Embodiment 3

[0103] see image 3 , image 3 It is a schematic flow chart of another image text positioning method disclosed in the embodiment of the present invention. Such as image 3 As shown, the positioning method of the image text may include the following steps:

[0104] 301-306. Wherein, steps 301-306 are the same as steps 201-206 described in Embodiment 2, and the present invention is not limited here.

[0105] 307. Merge row units having a coordinate inclusion relationship in at least one row unit to obtain at least one target row unit.

[0106] In the embodiment of the present invention, if the distance between two target line units is too large, it can be preliminarily determined that the two target line units belong to the content of the upper and lower paragraphs of text, and then segment division can be performed according to the distance between the target line units. Specifically, as an optional implementation, it may be judged whether the distance between any two targ...

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 embodiment of the present invention relates to the technical field of image processing, and discloses a method and device for positioning image characters. The method includes: marking the text image with connected domains, obtaining at least one text connected domain, dividing at least one text connected domain into rows according to the azimuth angle, and obtaining at least one row unit, where the azimuth angle is the center point of any two text connected domains The angle between the straight line and the horizontal line; according to the interdomain distance, at least one text connected domain is divided into columns to obtain at least one column unit, and the interdomain distance is the distance between the center points of any two text connected domains; according to at least one row unit and at least one The row unit determines at least one text positioning frame, which is used to indicate the position of the text contained in the text image, and one text positioning frame corresponds to one text. Implementing the embodiment of the present invention can improve the accuracy of image text positioning.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a method and device for positioning image characters. Background technique [0002] In the era of mobile Internet, people use cameras on smart devices to capture the world they see every day, resulting in a surge in image and video data, creating the era of image big data. Nowadays, people rely on image recognition, and there is an increasing demand for extracting text information from captured text images. For example, during the learning process, students often need to extract text information from captured text images to search for answers. In this process, the text image recognition task can be divided into two main stages, one is text positioning, and the other is text recognition. Among them, text positioning is to determine the position of the text in the image. The accuracy of text positioning has a profound impact on the accuracy of text recognition. Simply pu...

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): G06K9/32G06K9/34
CPCG06V20/635G06V30/153G06V30/10
Inventor 谭维
Owner GUANGDONG XIAOTIANCAI TECH CO LTD
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