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

Method and device for identifying icons

The technology of a recognition device and recognition method, which is applied in the field of recognition icons, can solve problems such as difficulty in character recognition and interference with recognition results

Inactive Publication Date: 2011-07-20
FUJITSU LTD
View PDF2 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in the case of mixed graphics and text, it is difficult to perform high-accuracy text recognition, because the icons contained in it will interfere with the recognition results
There is currently no effective way to identify icons

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
  • Method and device for identifying icons
  • Method and device for identifying icons
  • Method and device for identifying icons

Examples

Experimental program
Comparison scheme
Effect test

no. 1 approach

[0032] The inventor has discovered through research that text is usually composed of lines, and icons may include various geometric shapes, such as solid circles, rectangles, or solid blocks of various shapes, and the like. For a line, the ratio of the number of pixels of its edge points to the number of pixels of the entire line is relatively large, while for a solid block, the ratio of the number of pixels of its edge points to the number of pixels of the solid block is small. That is to say, text images and icon images usually have different characteristics of foreground edge density. Therefore, the icon image can be recognized by utilizing this difference between the character image and the icon image.

[0033] For example, figure 1 A flowchart of an icon recognition method according to an embodiment of the present invention is shown. The method includes: obtaining the foreground edge density feature of the image to be recognized; and a classification step, wherein wheth...

no. 2 approach

[0045]On the basis of the first embodiment, the inventor further researched and found that the foreground edge density feature can be further subdivided. For example, the analysis according to the first embodiment may be performed on the foreground edge density feature of the entire image to be recognized, or the image to be recognized may be first divided into multiple parts, and the analysis according to the first embodiment may be performed on each part. The foreground edge density feature (also referred to as the first foreground edge density feature in the present invention) of the entire image to be recognized can be analyzed simply by using the method described in the first embodiment. The method for dividing an image to be recognized into multiple parts and analyzing them will be described in detail below.

[0046] The inventors have found through research that characters are usually composed of lines, and in the process of forming characters, for aesthetic considerati...

no. 3 approach

[0060] The inventors have found that text images and icon images are significantly different in terms of texture features. Therefore, such texture features can be utilized to identify icons.

[0061] Texture features can be divided into binary texture features, grayscale texture features and color texture features. These texture features are described below.

[0062] Binary Texture Features

[0063] The inventors found that text images and icon images often have different texture complexities. Therefore, icons can be identified by utilizing this difference between text and icons.

[0064] Further research by the inventors revealed that one aspect of the texture is various edges. Therefore, in order to distinguish whether the texture is complex, the edge projection feature of the image to be recognized can be used for recognition. This is explained in detail below.

[0065] In order to obtain the edge projection features, it is necessary to obtain the edge pixels of the...

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 method and device for identifying icons. The method comprises the following steps of: acquiring foreground edge density characteristics of images to be identified; and classifying: classifying whether the images to be identified are icons or not according to the foreground edge density characteristics. The method disclosed by the invention can be realized by a corresponding icon identifying device.

Description

technical field [0001] The present invention generally relates to the field of information processing, and in particular to a method and device for identifying logos. Background technique [0002] In the current information age, more and more information needs to be stored and processed in the form of electronic information, so character recognition technology with high accuracy is required. However, in the case of mixed graphics and text, it is difficult to perform high-accuracy text recognition, because the icons contained in it will interfere with the recognition results. Currently there is no effective way to identify icons. Contents of the invention [0003] A brief overview of the invention is given below in order to provide a basic understanding of some aspects of the invention. It should be understood that this summary is not an exhaustive overview of the invention. It is not intended to identify key or critical parts of the invention nor to delineate the scope ...

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): G06K9/62G06K9/46
Inventor 朱远平孙俊皆川明洋堀田悦伸直井聪于浩
Owner FUJITSU LTD
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