Recognition method for verification temperature character of glass thermometer

A glass thermometer, character recognition technology, applied in character recognition, character and pattern recognition, calculation and other directions, can solve the problems of boring, manual readings are greatly affected by the test personnel, reduce the test accuracy and efficiency, etc., to improve the work. The effect of efficiency

Inactive Publication Date: 2019-04-09
SOUTH CHINA UNIV OF TECH
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

These tasks are not only boring, but more importantly, the accuracy and efficiency of the verification are seriously reduced, and the manual readings are greatly affected by the verification personnel, and the personal quality requirements of the verification personnel are relatively high.
Moreover, the existing fuzzy image recognition technology does not achieve satisfactory results in the recognition of the verification temperature of the glass thermometer.

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
  • Recognition method for verification temperature character of glass thermometer
  • Recognition method for verification temperature character of glass thermometer
  • Recognition method for verification temperature character of glass thermometer

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0103] When the present invention collects the blurred image of the thermometer, the signal noise generated in the process of collecting the blurred image can be solved by the corresponding digital filtering algorithm and other signal processing algorithms; and the distortion caused by the change of the viewing angle when collecting the image mainly comes from Due to the parallax of the camera imaging, the distance between the thermometer scale lines in the blurred image is uneven. In addition, the thermometer itself is not a plane, and the characters on the thermometer are bound to be distorted during the imaging process. The thermometers submitted for inspection are usually thermometers used by customers, so the lines on the thermometer to be inspected are often missing, such as missing tick marks, missing characters, etc., causing the problem of "occlusion". In the actual verification process, the most important problem is the "occlusion" problem. In some extreme cases, 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 proposes a verification temperature character recognition method for a glass thermometer, the steps are as follows: obtain a blurred image of the glass thermometer, perform edge detection on the blurred image; perform contour tracking on the blurred image after edge detection; ; Calculate the distance distribution matrix and angle distribution matrix of all contour fuzzy feature recognition method point pairs; calculate the fuzzy closeness histogram of all contour fuzzy feature recognition method points to form a fuzzy closeness matrix; calculate any two points between two fuzzy images The difference of fuzzy closeness degree is used as the cost matrix, and the template character with the minimum value in the minimum matching cost is selected as the recognition result. The method adopts the theory of fuzzy mathematics to repair the incomplete numbers with fuzzy closeness, the recognition rate is about 96%, and the accuracy rate of thermometer readings reaches 95%.

Description

technical field [0001] The invention relates to a verification and identification method of a standard thermostatic bath thermometer, in particular to a verification temperature character recognition method of a glass thermometer. Background technique [0002] Character recognition is an important branch in the field of pattern recognition. It is the application of pattern recognition technology in the field of fuzzy image processing, and is a combination of fuzzy image processing technology and pattern recognition technology. In 1929, German scientist Tausheck first proposed the concept of OCR (Optical Character Recognition, Optical Character Recognition), which is for printed characters, using optical methods to convert documents into blurred image files of original black and white dot matrix, and then A system technology that converts the text in the blurred image into text format through recognition software, so that the word processing software can further edit and proc...

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): G06K9/00G06K9/46
CPCG06V10/44G06V30/10G06F18/00
Inventor 钟汉如
Owner SOUTH CHINA UNIV OF 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