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

Metal reflection image identification technology based on edge point self-similarity, and TEDS system

A self-similarity, image recognition technology, applied in image enhancement, image analysis, image data processing and other directions, can solve the problem of high false positive rate, and achieve the effect of improving accuracy and solving high false positive rate.

Active Publication Date: 2017-05-10
南京鑫和汇通电子科技有限公司
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The invention proposes a metal reflective image recognition based on self-similarity of edge points, which can recognize the metal reflective image in the background image and improve the accuracy of image comparison and recognition; applied in the TEDS system, it solves the misjudgment rate in the fault detection of motor vehicles high problem

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
  • Metal reflection image identification technology based on edge point self-similarity, and TEDS system
  • Metal reflection image identification technology based on edge point self-similarity, and TEDS system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0037] Embodiment 1: a metal reflective image recognition based on edge point self-similarity applied on the TEDS system, comprising the following steps:

[0038] Step 1: Input the EMU image to be detected in the computer, such as figure 1 For the image shown, use the canny edge detection algorithm to obtain all the edge points of the image; the specific process is as follows:

[0039] 1. Process the EMU image into a grayscale image on the computer;

[0040] 2. Perform Gaussian blur on the grayscale image to reduce the interference of image noise;

[0041] 3. Calculate the gradient value and direction of each pixel in the denoised image;

[0042] 4. Perform non-maximum suppression on the gradient value of each pixel, and initially obtain a set of image edge points; 5. Use a double-threshold method to connect edges, eliminate false edges, fill in edge gaps, and obtain a more accurate set of edge points .

[0043] Step 2: Classify all edge points, the same kind of edge point...

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 brings forward a metal reflection image identification technology based on edge point self-similarity. Edge points of an image to be detected are obtained, reference directions are distributed to the edge points, and feature vectors are calculated and are normalized; local and overall self-similarity values of each edge point are calculated, and a weight combination of the local and overall self-similarity values are taken as a final self-similarity value of the corresponding edge point; an edge point set with high self-similarity is obtained, and irregular edge points with lower self-similarity are screened and marked from the set according to a predetermined mode; a pixel intensity difference and greatest pixel intensity of each irregular edge point in a local neighborhood in horizontal and vertical directions are calculated; and irregular edge points whose pixel intensity differences in the neighborhood are greater than a pixel intensity difference threshold whose greatest pixel intensities are greater than a greatest pixel intensity threshold are marked as a metal reflection image. The invention further brings forward a TEDS system applying the metal reflection image identification technology. A metal reflection phenomenon on a motor train unit is effectively identified, and the misjudgement rate is reduced.

Description

technical field [0001] The invention relates to the field of computer image detection and recognition, in particular to a metal reflective image recognition based on edge point self-similarity and a TEDS system using the recognition method. Background technique [0002] At present, the metal reflective image based on the background image is usually a kind of interference image in the field of image recognition, which has a certain impact on the recognition of specific technical features in image retrieval and image recognition, especially in the fault detection of EMUs, using The dynamic image detection system (TEDS system) for EMU operation faults is easy to detect the metal reflective image as the fault part, which increases the complexity and interference of fault repair work. [0003] The existing detection and recognition technology for metal reflective images focuses on the visual detection of metal reflective surfaces, and does not target the recognition of metal refl...

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): G06T7/13
CPCG06T7/0008G06T2207/10004G06T2207/30164
Inventor 汪辉任昌
Owner 南京鑫和汇通电子科技有限公司
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