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

Seven-segment nixie tube liquid crystal display screen identification method and system based on deep learning

A liquid crystal display and deep learning technology, applied in the field of computer vision, can solve the problems of easy loss of data workload, high cost, etc., and achieve the effect of increasing generalization performance, reducing workload, accuracy and speed.

Pending Publication Date: 2022-05-20
HENAN UNIVERSITY
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In the case of manual monitoring and recording of display screen data, the present invention is not only easy to lose data but also has a large workload and high cost and cannot achieve real-time collection, and proposes a seven-segment digital tube liquid crystal display recognition method based on deep learning and The system can realize the identification of numbers in various seven-segment digital tube LCD screens, especially the accuracy and speed of identification of smart meters, water meters and other related instruments have been greatly improved

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
  • Seven-segment nixie tube liquid crystal display screen identification method and system based on deep learning
  • Seven-segment nixie tube liquid crystal display screen identification method and system based on deep learning
  • Seven-segment nixie tube liquid crystal display screen identification method and system based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0074] The present invention will be further explained below in conjunction with accompanying drawing and specific embodiment:

[0075] like figure 1 As shown, a seven-segment digital tube liquid crystal display recognition method based on deep learning, including:

[0076] Step S101: Convert the image into a single-channel grayscale image represented by 255 grayscale values ​​using the weighted average normalization method, and then denoise the image through bilateral Gaussian filtering to remove as much noise as possible in the image. And through fixed threshold binarization to increase the discrimination of image foreground and background information. Specifically, because the amount of data carried in the color image (RGB image) is too much, the RGB image is first converted into an HSV image in the process of processing to reduce the amount of information in the picture, and then the HSV is separated to separate H, S, V image;

[0077] Step S102: Use YOLOv3 to locate th...

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 a system for identifying a seven-segment nixie tube liquid crystal display screen based on deep learning. The method comprises the following steps of: (1) preprocessing an identified image: carrying out a series of operations such as normalization, graying, Gaussian filtering, adaptive threshold segmentation and image denoising on an input image; (2) positioning operation of seven sections of nixie tubes in the liquid crystal display screen: performing regional positioning on the nixie tubes in the liquid crystal display screen by using YOLOv3; (3) image enhancement operation: carrying out corrosion and expansion operation on the image to reduce interference areas in the image, enable front and back backgrounds to be more separated and eliminate holes between nixie tubes; and (4) image identification operation: carrying out numeric character segmentation operation on the processed region of interest, independently segmenting each number into a picture, and then carrying out identification by using a threading method. According to the invention, related contents in the seven-segment nixie tube liquid crystal display screen can be read more accurately.

Description

technical field [0001] The invention belongs to the technical field of computer vision, and in particular relates to a recognition method and system of a seven-segment digital tube liquid crystal display based on deep learning. Background technique [0002] The seven-segment digital tube display is widely used in real life due to its advantages of cheap price, simple use, and high precision. However, in some environments, staff are required to monitor and record the contents of the display. In the manual situation, not only is it easy to lose data, but also the workload is heavy and the cost is high, so real-time collection cannot be achieved. How to use computer vision-related technologies to solve such problems is a difficult problem commonly faced by all walks of life. Contents of the invention [0003] In the case of manual monitoring and recording of display screen data, not only is it easy to lose data, but also the workload is large, the cost is high and real-time ...

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): G06T7/00G06T7/136G06T5/00G06T5/30
CPCG06T7/0002G06T7/136G06T5/30G06T2207/10004G06T2207/20021G06T2207/20104G06T5/70
Inventor 何欣刘红阳陈永超于俊洋王光辉
Owner HENAN UNIVERSITY
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