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

Robust industrial electric meter digital number recognition method

A technology for digital recognition and electric meters, applied in character and pattern recognition, image data processing, image analysis, etc., can solve problems such as unrobustness, low recognition rate, limitations, etc., achieve algorithm robustness, improve algorithm efficiency, and digital Identify the exact effect

Inactive Publication Date: 2017-05-31
NANJING UNIV OF SCI & TECH
View PDF2 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the need to replace the original old-fashioned meters with new ones is often limited by the economy, so such meters have not been widely used
[0003] Some existing digital recognition algorithms in industrial meters have shortcomings such as low recognition rate and unrobustness

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
  • Robust industrial electric meter digital number recognition method
  • Robust industrial electric meter digital number recognition method
  • Robust industrial electric meter digital number recognition method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0053] The present invention first detects the digital edge in the industrial electric surface panel through the canny operator, and can effectively locate and cut out the digital area; then, based on the numbers in the training set, a classifier is constructed through the KNN algorithm to classify the numbers to be recognized. Specific steps are as follows:

[0054] Step 1. First, the collected industrial meter image I_rgb, such as figure 1 As shown, convert to a grayscale image I_gray, use mean filtering on the grayscale image, and perform preliminary denoising, such as figure 2 shown. The mean filter kernel is: The process of mean filtering is the convolution calculation process:

[0055]

[0056] Step 2, use the Canny operator to extract the edge of the industrial ammeter image for the grayscale image I_noise that has removed the noise, such as image 3 shown. Canny operator for edge detection can effectively suppress the noise, and at the same time can accuratel...

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 robust industrial electric meter digital number recognition method, and belongs to the technical fields of image processing and pattern recognition. The robust industrial electric meter digital number recognition method mainly comprises two parts such as digital number segmentation and digital number recognition. Firstly, digital number edges in an industrial electric meter panel are detected through a Canny operator; then a digital number region can be effectively positioned and cut through a projection method; and finally, a classifier is constructed through a KNN algorithm based on digital numbers in a training set, and classification is performed on digital numbers to be recognized. According to the industrial electric meter digital number recognition method, a noise region and the digital number region can be effectively differentiated through Canny edge detection, so that the algorithm is enabled to be more robust. Meanwhile, the KNN algorithm is adopted when digital numbers are recognized, thereby not only being capable of effectively improving the efficiency of the algorithm, but also being capable of enabling digital number recognition to be more accurate.

Description

technical field [0001] The invention belongs to the technical field of digital image processing and pattern recognition, in particular to a robust digital recognition method for industrial electric meters. Background technique [0002] From the generation of electricity in the 19th century, and the widespread use of electricity in the 20th century. In the industrial world, the electric meter is used as an important tool to display various data of the production department in the enterprise. Especially in the electric power industry, in order to count the electricity consumption data of each instrument, the electric power department often arranges special personnel to carry out meter reading work. Among the large number of electric meters in existence, many are located in remote, inconvenient, and high-risk locations. This just needs to expend a large amount of manpower and material resources to arrange worker's meter reading, and because the long-term work of worker is pro...

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): G06K9/34G06T7/00G06T7/11G06T7/13G06T7/136
CPCG06T7/0004G06T2207/10004G06V30/153
Inventor 李剑钱建军杨健
Owner NANJING UNIV OF SCI & 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