Check patentability & draft patents in minutes with Patsnap Eureka AI!

Text Detection Method Based on Improved East Algorithm

An improved technology for text detection, applied in computing, computer parts, instruments, etc., can solve the problem of low positioning accuracy of long texts and achieve the effect of improving accuracy

Active Publication Date: 2020-11-27
FUJIAN BOSS SOFTWARE
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a text detection method based on the improved EAST algorithm, which solves the problem of low positioning accuracy of the original algorithm for long text

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
  • Text Detection Method Based on Improved East Algorithm
  • Text Detection Method Based on Improved East Algorithm
  • Text Detection Method Based on Improved East Algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] The content of the present invention will be described in detail below in conjunction with the accompanying drawings and embodiments of the description:

[0027] The present invention is based on the improvement of the EAST text detection technology. In order to better understand the content of the invention, we first set forth the main principles of the EAST text detection technology. The EAST text detection technology is mainly composed of the following two parts:

[0028] 1. Multi-channel FCN, a multi-channel fully convolutional network, which processes the input image and outputs a 9-channel feature map (the output geometric map is the EAST version of the QUAD type). The 9-channel feature map is actually 9 image matrices, named map0, map1, map2, map3, map4, map5, map6, map7, map8, assuming the value at the coordinate (x, y) on the X-th image matrix mapX For mapX[x][y], the coordinates of the four vertices of the quadrilateral text box predicted by each pixel are v1(...

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 relates to a text detection method based on an improved EAST algorithm. The text detection method comprises the following steps: S1, processing an input image by adopting a multi-channelfull convolution network; S2, carrying out threshold selection on pixel points in the map 0; S3, calculating coordinates of four vertexes of the text box predicted by the activated pixel points; S4,combining the text boxes predicted by the activated pixel points according to the overlapping degree to obtain a polygon; S5, screening out a sub-set C1 and a sub-set C2 from the set C; S6, calculating coordinates of two vertexes of the starting end of the textbox through the activated pixels in the subset C1, and calculating coordinates of two vertexes of the terminating end of the textbox through the activated pixels in the subset C2; and combining the coordinates of the two vertexes obtained by the subset C1 with the coordinates of the two vertexes obtained by the subset C2. The method hasthe advantage that the long text prediction accuracy of the EAST algorithm can be improved.

Description

technical field [0001] The invention relates to a text detection method based on an improved EAST algorithm, which is applicable to the field of OCR text recognition such as ID card text recognition, bank card text recognition, electronic bill text recognition, printed document text recognition, and natural scene text recognition. Background technique [0002] OCR (Optical Character Recognition) optical character recognition is an important technology in the field of AI, the main content is to let the computer read the text information in the image. Today's mainstream OCR technology is mainly divided into two steps: 1. Text detection, which refers to locating the precise position of the text in the image; 2. Text recognition, which refers to cutting out the text according to the position information provided by the text detection and adding it. identify. [0003] In the existing OCR field, there are many text detection technologies, and the detection technologies with good ...

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): G06K9/00G06K9/32
Inventor 史天永翁增仁
Owner FUJIAN BOSS SOFTWARE
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com