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

Image text detection method and device

A text detection and picture technology, applied in the computer field, can solve the problem of losing the position information of the text area, and achieve the effect of saving computing resources and improving robustness.

Active Publication Date: 2016-06-01
SHENZHEN INST OF ADVANCED TECH CHINESE ACAD OF SCI
View PDF3 Cites 31 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In view of this, the embodiment of the present invention provides a method and device for text detection on pictures, so as to solve the problem that the position information of the text area will be lost in the prior art

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
  • Image text detection method and device
  • Image text detection method and device
  • Image text detection method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019] In the following description, for the purpose of illustration rather than limitation, specific details such as a specific system structure and technology are proposed for a thorough understanding of the embodiments of the present invention. However, it should be clear to those skilled in the art that the present invention can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from obstructing the description of the present invention.

[0020] The embodiment of the present invention is based on a two-layer cascaded full convolutional network to extract text lines in a picture, which not only fully saves computing resources between overlapping regions, but also uses higher-level sequence features of the text as supervision information, which improves The robustness of the text detection algorithm is improved.

[0021] figur...

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 is suitable for the technical field of computer, and provides an image text detection method and device. The image text detection method comprises the steps that an image for text detection is acquired; the image is inputted to the first layer of a fully convolutional network, and the text area in the image is detected based on the sequence features of the text area in the first layer; and the text area is inputted to the second layer of the fully convolutional network, the text area is decomposed into independent text line areas to be outputted based on the supervised classified of a text median line in the second layer, and the area of the text median line is defined by a Gaussian distribution function. Text lines in the image are extracted based on the two-layer cascaded fully convolutional network so that computing resource between overlapping areas is fully saved, the higher layer of sequence features of the text are utilized to act as supervision information, and robustness of a text detection algorithm is enhanced.

Description

Technical field [0001] The invention belongs to the field of computer technology, and in particular relates to a method and a device for text detection of pictures. Background technique [0002] At present, the algorithms for text detection on pictures are mainly divided into two categories: methods based on sliding windows and methods based on connected regions. The sliding window-based method is to scan all possible positions of a picture through a variable size sliding sub-window to detect text information. It uses a trained classifier to determine whether there is text information in the window; based on connected regions The method first uses a low-level filter to quickly segment text and non-text pixels, and then connect text pixels with similar attributes to form text components. The stroke width conversion (SWT) algorithm and the most stable extreme region (MSREs) algorithm are such Representative of the method. However, the classification network of the above method us...

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 Applications(China)
IPC IPC(8): G06K9/00G06K9/46
CPCG06V30/413G06V10/462
Inventor 乔宇黄韡林贺通
Owner SHENZHEN INST OF ADVANCED TECH CHINESE ACAD OF SCI
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