Kilowatt-hour meter image automatic identification method

Abstract

The invention relates to a kilowatt-hour meter image automatic identification method which comprises the following steps: 1. image preprocessing: detecting vertical texture of a panel image by using Sobel operator, preliminarily removing the background area by a projection method, extracting the area with abundant vertical texture by an expansion method, and carrying out binarization treatment on the image by a adaptive threshold segmentation method based on an integral projection method; 2. precise positioning of indicating value and bar code: by combining an intelligent judgment method on the basis of indicating value intervals and length-width ratio characteristic of numeric characters under the complex image background, adapting to precise positioning of indicating values of different types of kilowatt-hour meters on the basis of vertical edge detection of the Sobel operator and morphological treatment; carrying out horizontal scanning on the bar code area to extract the bar code characteristic area; 3. bar code identification: identifying different character bar codes by using a similar edge distance normalization method; and 4. indicating value identification: extracting the indicating value by a PCA (principal component analysis) method. By using the PCA character recognition method, various character indicating values can be precisely identified, including identification of half-character.

Description

technical field [0001] The invention relates to the technical field of automatic identification of electric energy meters, in particular to an automatic identification method for images of electric energy meters. Background technique [0002] Repurchase of electric energy meters, passing the verification, withdrawing from the use site, testing records and storage are the core steps of the life cycle management of electric energy meters in the electric power marketing system. value. The accuracy and correctness of the energy meter detection records determine whether the energy meter is used correctly during the working period and whether the energy meter count is recorded correctly, which can save a large amount of power loss for the power company. Therefore, improving and improving the method of automatically identifying the barcode and indication value of the electric energy meter is the most important problem that the electric power marketing system urgently needs to solv...

AI Technical Summary

Problems solved by technology

[0003] At present, the detection records of electric power withdrawal electric energy meters are carried out by means of manual visual recognition and manual entry. The problems and loopholes in this way are:

[0004] 1. The two operations of visual recognition and manual entry will cause mistakes or mistakes due to various objective factors and human factors, so that the final entered meter number is inconsistent with the count in the electric energy meter, resulting in inaccurate balance electricity;

[0005] 2. During the process of warehousing the electric energy meter, the naked eye can only check the appearance of the electric energy meter and identify the electric energy indication in real time, and cannot save the appearance of the electric energy meter and the photo of the electric energy indication, resulting in the complete appearance of the electric energy meter and the accuracy of the electric energy indication. audit verification;

[0006] 3. Due to the manual method, some power companies do not do any testing and recording of the electric energy meter, and store it directly in the warehouse until it is destroyed.

The general template matching method, statistical feature method and structural feature method are difficult to achieve ideal recognition results, so this puts forward more stringent requirements for image recognition.