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

A method for intelligent recognition of numerical values ​​of pointer instruments

An intelligent recognition and pointer-type technology, applied in character and pattern recognition, neural learning methods, instruments, etc., can solve the problems of limited use, weak model generalization ability, heavy collection workload, etc., and achieve cost saving and recognition speed Fast and easy transplantation

Active Publication Date: 2021-01-19
BEIJING UNIV OF CHEM TECH
View PDF11 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the process of training the model, all the data in this method are original data. On the one hand, the collection workload is large, and secondly, the generalization ability of the model is not strong; The initial position and split direction need to be consistent, which limits its practical use

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 method for intelligent recognition of numerical values ​​of pointer instruments
  • A method for intelligent recognition of numerical values ​​of pointer instruments
  • A method for intelligent recognition of numerical values ​​of pointer instruments

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] The object of the present invention is to provide a method and device for intelligent recognition of pointer instrument values ​​with strong operability, high recognition accuracy, fast speed and high robustness.

[0029] A major feature of the recognition device is that it has the function of self-adapting to the shooting angle, which can be self-corrected through the prefabricated cross positioning mark without manual adjustment. The set is attached figure 1 As shown, it is composed of a bracket (1), a program-controlled cloud platform (2), a video camera (3), a cross mark (5) and a computer. First place the bracket (1) in front of the dial (4) to be identified, then fix the program-controlled pan-tilt (2) fixedly connected to the camera (3) on the bracket (1), and there are two left and right cross marks on the dashboard Make a mark, then the camera takes an image to detect the position of the two cross marks, and judges the degree of deviation between the top, bott...

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 belongs to the field of machine vision, and relates to a method and a device for intelligently recognizing numerical values ​​of pointer instruments. The invention provides a model training method based on an adversarial sample using a convolutional neural network model, the training model intelligently recognizes the value of a pointer instrument, and a recognition method and device equipped with camera shooting angle self-adaptive adjustment technology. The device has a shooting angle adaptive function, which can self-correct the shooting angle, and does not need to be adjusted precisely before use. This method uses adversarial samples to train the convolutional neural network recognition model, which greatly reduces the workload of raw data collection, and can recognize multiple types of dashboard values ​​at the same time, making it unnecessary to use multiple cameras to shoot separately, saving costs. The invention has the characteristics of high robustness, high accuracy, fast recognition speed, strong operability, convenient transplantation and the like.

Description

technical field [0001] The invention belongs to the field of machine vision, and relates to a method and device for intelligently recognizing the value of a pointer instrument, in particular to a recognition method and device capable of self-correction by using adversarial samples to train a convolutional neural network recognition model. Background technique [0002] Due to its stability, reliability, easy maintenance, and ability to reflect the changing trend of the measured instrument, the pointer instrument is widely used in chemical industry, electric power, automobile and other industries. However, the identification of pointer instruments is mostly done by human eyes, which is not only time-consuming and laborious but also inefficient, and its readings are greatly affected by subjective factors. Therefore, it is necessary to develop a set of automatic identification devices for pointer instruments. [0003] At present, the recognition of pointer instruments mostly ado...

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): G06K9/20G06K9/32G06N3/04G06N3/08
CPCG06N3/08G06V10/147G06V20/62G06V2201/02G06N3/045
Inventor 马波蔡伟东江志农
Owner BEIJING UNIV OF CHEM TECH
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