Unlock instant, AI-driven research and patent intelligence for your innovation.

OCR (Optical Character Recognition) method applied to power enterprise

An enterprise and power technology, applied in the field of character recognition and classification in image recognition, to achieve the effect of strong recognition robustness, convenient processing and storage

Pending Publication Date: 2021-12-03
SHANGHAI MUNICIPAL ELECTRIC POWER CO
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, ordinary text recognition technology only extracts text information, and a small part extracts tables.

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
  • OCR (Optical Character Recognition) method applied to power enterprise
  • OCR (Optical Character Recognition) method applied to power enterprise
  • OCR (Optical Character Recognition) method applied to power enterprise

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0027] see Figure 1 to Figure 3 , the present invention discloses an OCR method applied to electric power enterprises, the difference is that the steps include:

[0028] (1) Preprocess the collected pictures to obtain the preprocessed pictures.

[0029] The input picture (image) may have problems such as shadows and skew. Therefore, first denoise the input image through Gaussian filtering to make the image smoother, using a one-dimensional Gaussian function...

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 relates to the field of character recognition and classification in image recognition, in particular to an OCR (Optical Character Recognition) method applied to a power enterprise, which is characterized by comprising the following steps of: (1) preprocessing a collected picture to obtain a preprocessed picture; (2) extracting character features and table features in the preprocessed picture by using a convolutional neural network; (3) carrying out character feature matching on the character features extracted in the step (2) through a text classification model, and identifying characters; (4) drawing a table through the table features extracted in the step (2); (5) synthesizing the characters recognized in the step (3) and the table drawn in the step (4) to obtain a recognition result containing the characters and the table; and (6) generating a word from the recognition result and storing the word. The invention improves the recognition rate, reduces the cost, and is more suitable for the use scene of a power enterprise.

Description

technical field [0001] The invention relates to the field of character recognition and classification in image recognition, in particular to an OCR method applied to electric power enterprises. Background technique [0002] OCR (Optical Character Recognition) is optical character recognition. Its technical concept was proposed by German scientists in 1929. Since the 1960s, countries have begun to further explore and research OCR technology. With the development of digital image processing technology, OCR technology has gradually developed to the stage of practical application, and has made great progress in the accuracy, recognition speed and stability of character recognition. Nowadays, with the development of computer technology, the requirements for office automation are getting higher and higher. In order to speed up the exchange and transmission of information, tabular data has become the main carrier of information. It not only plays an important role in information tr...

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 Applications(China)
IPC IPC(8): G06K9/00G06K9/32G06K9/46G06F40/18
CPCG06F40/18
Inventor 王治华高峰陈宏福
Owner SHANGHAI MUNICIPAL ELECTRIC POWER CO