Unlock instant, AI-driven research and patent intelligence for your innovation.

Natural scene text detection method based on adaptive color clustering

A color clustering and text detection technology, applied in the field of pattern recognition, can solve the problem of low accuracy

Inactive Publication Date: 2015-07-29
CENT SOUTH UNIV
View PDF3 Cites 31 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The present invention provides a natural scene text detection method based on adaptive color clustering, and its purpose is to overcome the problem of low accuracy in the prior art when the text detection background is complex

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
  • Natural scene text detection method based on adaptive color clustering
  • Natural scene text detection method based on adaptive color clustering
  • Natural scene text detection method based on adaptive color clustering

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0070] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with specific embodiments and with reference to the accompanying drawings.

[0071] A method for text detection in natural scenes based on adaptive color clustering, such as figure 1 shown, including the following steps:

[0072] to figure 2 (a) Take text detection as an example, the specific steps are as follows:

[0073] Step 1: Input the image to be detected, such as figure 2 (a);

[0074] Step 2: Use the Canny edge detection algorithm to extract the edge pixels of the image to be detected to form an edge image, denoted as I e ; then the edge image I e The middle pixel is removed from the original image to obtain the main color image, denoted as I m ;

[0075] Step 3: Initialize the color clustering centers:

[0076] First, the primary color image I from step 2 m Project the pixels i...

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 natural scene text detection method based on adaptive color clustering. The method comprises the steps of: firstly, providing an adaptive color clustering scheme which can be used for clustering to obtain different number of color layers for images with different complexities, so that text connected areas are effectively extracted; then training an extreme learning machine (ELM), so as to construct a neighborhood character model and merge to form a character string, so that the robustness of the method is increased; finally, further increasing the system text detection performance. According to the method, the text character string is verified by adopting a strategy that a convolutional neural network (CNN) and a support vector machine (SVM) are combined, and compared with a traditional method, the text detection accuracy is increased.

Description

technical field [0001] The invention belongs to the technical field of pattern recognition and relates to a natural scene text detection method based on adaptive color clustering. Background technique [0002] With the popularity of mobile phones and camera equipment, the number of images and videos is increasing. These images and videos contain a lot of important information, how to extract and understand the information in the images is particularly important. Text is the most important and direct information in the image. Extracting and recognizing the text in the image can assist the computer to understand the content of the image. Currently, printed text detection has made great progress and is widely used. However, the text in natural scene images, due to its variable font size and style, is also affected by lighting, shadows, and shooting angles, making its detection effect poor. Therefore, natural scene text detection is still a challenging work. [0003] At pres...

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
IPC IPC(8): G06K9/62
CPCG06F18/2111G06F18/285G06F18/24137G06F18/2411
Inventor 邹北骥吴慧郭建京赵于前
Owner CENT SOUTH UNIV
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