A machine vision-based method for recognizing instrument numbers

A machine vision and recognition method technology, applied in character and pattern recognition, instruments, computer parts and other directions, can solve the problems of the influence of the number recognition of the meter, achieve strong robustness, reduce the difficulty of the number recognition, robustness strong effect

Active Publication Date: 2019-04-12
ZHEJIANG UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] Aiming at the deficiencies in the existing technology, the present invention proposes a machine vision-based instrument representation number recognition method, aiming to use machine learning methods to solve the problem of instrument representation number recognition under working conditions such as instrument image posture, scale, and illumination Impact

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
  • A machine vision-based method for recognizing instrument numbers
  • A machine vision-based method for recognizing instrument numbers
  • A machine vision-based method for recognizing instrument numbers

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0047] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0048] Such as figure 1 As shown, the present invention needs some preparatory work before the number recognition. First, collect N sample images of the target instrument at the industrial site, and then select one sample as a standard image, and mark more than 4 recurring marker points on each sample image, and the number of marker points is generally taken as a typical value of 8; all images are simulated Transform to the standard image posture, collect the image template of numbers 0 to 9; record the fan-shaped area where the pointer is located and the rectangular area where the number is located on the standard image at the same time;

[0049] Such as figure 2 As shown, the meter image to be recognized and displayed in the present invention:

[0050] (1) First, the affine transformation matrix between the instrument image and the standard instru...

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 machine vision-based instrument display number recognition method. The method specifically includes the following steps: (1) first regress the image of the instrument display number to be recognized through a cascaded pose regressor (Cascaded Pose Regression) The affine transformation matrix of the instrument image and the standard instrument image, so as to affine transform the instrument image to be recognized to the attitude of the standard instrument image, and realize the normalization of the instrument attitude; (2) use digital recognition based on geometric constraints The method is to carry out digital indication recognition on the attitude-normalized instrument image obtained in step (1); (3) use the pointer indication recognition method based on HOG feature to perform pointer recognition on the attitude-normalized instrument image obtained in step (1). Indication recognition. The digital display and pointer display recognition method proposed by the present invention solves the problem of posture and scale in the recognition of instrument display numbers, and greatly improves the accuracy of digital display recognition and pointer display recognition accuracy.

Description

technical field [0001] The invention belongs to the field of digital image processing and instrumentation number recognition, and in particular relates to a machine vision-based instrumentation number recognition method. Background technique [0002] In industrial fields such as chemical plants, substations, and oil refineries, a large number of on-site indicating instruments are installed. These instruments do not have remote transmission functions and require on-site readings to monitor the operating conditions of industrial sites. It is time-consuming, laborious and inefficient to record the number of on-site instruments by manual inspection. Therefore, the automatic recognition technology of instrument numbers based on machine vision has broad application prospects. [0003] The machine vision-based field instrument indication recognition problem is generally divided into two situations, one is pointer indication recognition, and the other is digital indication recogniti...

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 Patents(China)
IPC IPC(8): G06K9/46
CPCG06V10/443
Inventor 熊蓉方立王军南
Owner ZHEJIANG UNIV
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