Flow image recognition method

A technology of image recognition and flow chart, applied in the field of image recognition, can solve the problem of low efficiency of process image recognition and achieve fast and effective recognition

Active Publication Date: 2018-07-13
SHAANXI UNIV OF SCI & TECH
View PDF8 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Due to the fact that the flow charts in the existing documents are stuck and broken, the efficiency of process image recognition is not high. Therefore, a new process image recognition method is needed to solve the above problems.

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
  • Flow image recognition method
  • Flow image recognition method
  • Flow image recognition method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0044] In order to make the object, technical scheme and advantages of the present invention clearer, the present invention will be further described below in conjunction with embodiment, accompanying drawing. Apparently, the described embodiments are only some of the embodiments of the present invention, but not all of them. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0045] Such as figure 1 As shown, the steps of the identification method of the present invention include:

[0046] S1 establishes a corner-based flow chart structure model (CBSM), defines the corner combination rules and corner combination constraints describing the flow chart structural elements;

[0047] S2 extracts the flowchart structure;

[0048] S3 performs corner detection and screening on the flowchart structure;

[0049] S4 obtains ...

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 flow image recognition method. The flow image recognition method is characterized by including creating a flow chart structure model (CBSM) based on angular points, and defining various angular point types, combination rules and constraints for describing flow chart structure elements formally; extracting flow chart structures through text and image separation, detecting the angular points of the flow chart structures, extracting gridding characteristics and peripheral characteristics of neighborhoods of the angular points, and performing angular point classification by an SVM (support vector machine) classifier; recognizing the flow chart structures based on the CBSM; outputting flow image recognition results in a text form. The flow image recognition method has the advantages that the flow chart structure elements are recognized based on angular point characteristics, and accordingly, the problems of adhesion between texts and images and edge breakage, whichcannot be handled by existing flow image recognition techniques, can be solved; a new method is provided for flow image recognition.

Description

technical field [0001] The invention belongs to the technical field of image recognition, in particular to a process image recognition method. Background technique [0002] Existing computer information retrieval systems mainly use retrieval technology based on text matching, but documents in the fields of chemical industry, pharmaceuticals, machinery, and information technology often contain a large number of process images, which contain rich information and are crucial for retrieval and novelty retrieval. important. [0003] A flow chart can intuitively describe the specific steps of a work process and has important semantics. The process image recognition efficiency is not high due to the flow charts in the existing documents, such as text and image sticking and broken edges. Therefore, a new process image recognition method is needed to solve the above problems. Contents of the invention [0004] The object of the present invention is to provide a process image reco...

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): G06K9/00G06K9/46G06K9/62
CPCG06V30/422G06V10/44G06F18/2411G06F18/214
Inventor 孙连山侯涛张沙沙
Owner SHAANXI UNIV OF SCI & TECH
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