Improved MaskR-CNN model-based pointer type instrument reading automatic identification method

An automatic identification and pointer-type technology, applied in character and pattern recognition, neural learning methods, biological neural network models, etc., can solve problems such as high image quality requirements, poor flexibility, and weak anti-interference ability

Pending Publication Date: 2022-05-27
CHENGDU UNIVERSITY OF TECHNOLOGY
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Traditional algorithms run fast, but have poor flexibility, weak anti-interference ability, and high requirements for image quality; algorithms based o

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
  • Improved MaskR-CNN model-based pointer type instrument reading automatic identification method
  • Improved MaskR-CNN model-based pointer type instrument reading automatic identification method
  • Improved MaskR-CNN model-based pointer type instrument reading automatic identification method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0013] In order to make the technical means, creation features, achievement goals and effects realized by the present invention easy to understand, the present invention will be further described below in conjunction with the specific embodiments.

[0014] A method for automatic identification of pointer-type instrument representation numbers based on the improved Mask R-CNN model, comprising the following steps:

[0015] Classify the input meter image and generate a binary mask image of the dial features;

[0016] Correct the dial mask image with the perspective transformation method based on Hough transform;

[0017] After the corrected image is fitted with the pointer line based on the SVD-based least squares method, it is combined with the classification results of Mask R-CNN to calculate the pointer representation number and output the final recognition result.

[0018] The perspective transform image correction algorithm based on Hough transform is to use Hough transfor...

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 provides an improved Mask R-CNN model-based pointer type instrument reading automatic identification method. The method comprises the following steps of classifying an input instrument image and generating a binary mask image of a dial feature; correcting the mask image of the dial plate by using a perspective transformation method based on Hough transformation; and fitting a pointer line from the corrected image through a least square method based on SVD (singular value decomposition), performing pointer instrument representation calculation in combination with a Mask R-CNN classification result, and outputting a final recognition result. According to the method, a deep learning model is combined with a traditional image processing technology, the pointer instrument under the severe environments of complex background noise, strong electromagnetic interference, uneven illumination and the like can be detected, and the method is verified to be high in flexibility, wide in application scene and stable in performance.

Description

technical field [0001] The invention designs an algorithm for automatic identification of pointer-type meter representation numbers, in particular to an automatic pointer-type meter representation number identification method based on an improved Mask R-CNN model. Background technique [0002] Due to its advantages of strong anti-interference ability and long service life, pointer-type instruments are widely used in various industrial places, especially in complex environments such as oil exploration with strong interference, changeable climate and multi-radiation. In this kind of working environment, the pointer meter is responsible for monitoring the working status of the on-site mechanical equipment. At present, the reading of the pointer meter is still mainly based on manual transcription. With the continuous improvement of industrial automation and intelligent requirements, some algorithms for automatic identification of pointer-type instrument numbers have been born on...

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): G06V10/75G06V10/40G06V10/82G06K9/62G06N3/04G06N3/08G06T3/00G06T7/11
CPCG06N3/08G06T3/0012G06T7/11G06T2207/20084G06N3/045
Inventor 赵伟
Owner CHENGDU UNIVERSITY OF TECHNOLOGY
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