Fast multidirectional text line detection method

A detection method and text line technology, applied in the field of image processing, can solve problems such as limited scene applicability, high time complexity, and low detection speed, and achieve the effects of reducing computational complexity, speeding up detection speed, and improving accuracy

Active Publication Date: 2018-06-12
NANJING UNIV OF POSTS & TELECOMM
View PDF3 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Not only do these methods severely limit the applicability to scenarios where images are captured casually with mobile devices, but their performance often drops dramatically when applied to multi-oriented text images.
Moreover, most of the methods have high time complexity and relatively low detection speed

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
  • Fast multidirectional text line detection method
  • Fast multidirectional text line detection method
  • Fast multidirectional text line detection method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0060] The technical solutions of the present invention will be further described in detail below in conjunction with the accompanying drawings, and the examples given are only used to explain the present invention, and are not intended to limit the scope of the present invention.

[0061] Such as figure 1 As shown, this embodiment provides a fast multi-directional text line detection method, and the process can be divided into the following steps:

[0062] Step 1: First, use the MSER algorithm to extract candidate connected regions from the natural scene picture to be detected;

[0063] Step 2: Carry out the connected region point-to-point algorithm on the candidate connected regions to obtain candidate character regions, and group them by connected rules, and apply the lost character recovery algorithm to obtain candidate text lines;

[0064] Step 3: Classify text lines and non-text lines by applying the AdaBoost algorithm according to the characteristics of the candidate m...

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 fast multidirectional text line detection method. The method comprises the steps that a candidate connected region of a natural scene picture to be detected is extracted by an MSER algorithm; connected region counter point algorithm is carried out on the candidate connected region to acquire a candidate character region; a connection rule is used for grouping; a lost character recovery algorithm is used to acquire candidate text lines; and finally according to the features of candidate multidirectional text lines, an AdaBoost algorithm is used to classify text lines and non-text lines. According to the invention, the connected region counter point algorithm is used to process the candidate connected region acquired through the MSER, which reduces the computationalcomplexity and speeds up scene text extraction; and the Adaboost algorithm is used to extract the features of the candidate multidirectional text lines, which can greatly improve the accuracy of textdetection.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a fast multi-directional text line detection method. Background technique [0002] With the popularity of smartphones and mobile shooting devices, the number of images is increasing. Text detection in natural images has a wide range of applications, such as robot navigation, human-computer interaction, and image retrieval. At present, document text detection has made great progress and has been widely used, however, text detection in natural scenes is still a challenging task due to the variety of text appearances in natural scene images and the complexity of backgrounds. task. [0003] Existing text detection methods can be roughly divided into three categories: texture-based, connected region-based and hybrid methods. Among the existing methods, most of them focus on detecting horizontal or near-horizontal text. Not only do these methods severely limit ...

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): G06K9/34G06K9/46
CPCG06V30/153G06V10/267G06V10/44
Inventor 方承志樊梦雅黄梅玲顾子超
Owner NANJING UNIV OF POSTS & TELECOMM
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