Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Picture words detecting method

A text detection and image technology, applied in character and pattern recognition, instruments, computing, etc., can solve the problems of not being able to locate the text area well, difficult to locate text information, not making full use of the color information of the text area, etc. rate and precision, simple edge cases, simple and accurate text detection

Inactive Publication Date: 2009-08-12
PEKING UNIV
View PDF2 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method has the following disadvantages: (1) how to find the text information that can accurately describe the content of the picture itself is a very difficult thing in the webpage; (2) there is no corresponding webpage information for a large number of pictures
This method only uses the edge features of the text area, but does not make full use of the color information of the text area, so it cannot locate the text area well, and the text detection results need to be improved

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
  • Picture words detecting method
  • Picture words detecting method
  • Picture words detecting method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] The present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0024] Such as figure 1 As shown, a kind of picture text detection method of the present invention specifically comprises the following steps:

[0025] (1) Merge the edge maps of the original image on multiple color components to obtain the cumulative edge map.

[0026] The cumulative edge map is obtained by merging multiple edge maps detected by the improved Sobel edge detection operator on each YUV component of the picture. The method of merging is shown in formula 1, E is the cumulative edge map, E Y ,E U and E V are the edge maps detected by the improved Sobel edge detection operator on each YUV component of the picture, and E(x, y) is the edge intensity value of the point whose coordinates are (x, y) in the cumulative edge map, which is equal to E. Y ,E U and E VThe smaller one of the cumulative sum of the edge intensity ...

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 provides a kind of method of picture text detection, comprise the following steps: (1) merge the edge map of original image on each color component, obtain cumulative edge map; (2) set the edge point in cumulative edge map as its According to the corresponding color in the original image, according to the different colors of the edge points, the cumulative edge map is decomposed into several sub-edge maps by clustering method, and each sub-edge map contains edge points with similar colors; (3) in each In the Zhangzi edge image, horizontal and vertical projections are performed multiple times, and the area segmentation in the vertical direction and the horizontal direction is performed according to the projection image, and the text area in the image is located. After the cumulative edge map of the original image is obtained, the present invention uses a color-based clustering method to decompose the cumulative edge map into several sub-edge maps, so that the edges in the sub-edge maps are simplified, so that the detection of the text area of ​​the picture is relatively simple and accurate.

Description

technical field [0001] The invention belongs to the technical field of image processing and retrieval, and in particular relates to a method for detecting text in pictures. Background technique [0002] With the rapid development of Internet technology and multimedia technology, the picture content on the Internet shows an explosive growth trend. How to quickly retrieve the desired picture from the massive picture content has become a key problem that needs to be solved urgently. The existing methods are mainly based on the text description information in the webpage corresponding to the picture, but do not go deep into the analysis of the picture content. This method has the following disadvantages: (1) how to find the text information that can accurately describe the content of the picture itself is a very difficult thing in the webpage; (2) there is no corresponding webpage information for a large number of pictures. [0003] On the other hand, a large number of pictures...

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): G06K9/20G06K9/46
Inventor 易剑彭宇新肖建国
Owner PEKING UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com