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

Intelligent recognition method for text data in power industry complex scene

A technology in the power industry and complex scenes, applied in character recognition, character and pattern recognition, instruments, etc., can solve problems affecting text data detection and recognition, text information recognition and digital reading detection difficulty, text data deformation, etc.

Active Publication Date: 2019-07-26
SHANDONG UNIV +2
View PDF5 Cites 18 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The difficulty of text information recognition and detection of digital readings increases and the real-time performance is poor. There are huge differences between text data and background, font size and various complex layouts.
[0011] (2) Complex lighting and weather conditions in natural scenes will interfere with text data detection and text recognition to a certain extent, such as backlight shooting, insufficient light or overexposure, and foggy weather will affect text data detection and recognition
[0012] (3) There are deformation problems in text data, and image text areas in the power industry may also produce deformation, rotation, distortion and other styles

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
  • Intelligent recognition method for text data in power industry complex scene
  • Intelligent recognition method for text data in power industry complex scene
  • Intelligent recognition method for text data in power industry complex scene

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0080] Such as Figure 1-4 shown.

[0081] An intelligent recognition method for text data in a complex scene in the electric power industry, comprising the following steps:

[0082] S1: Take frames from the video data collected and saved by the multi-source fusion video surveillance system of the electric power company, perform image enhancement and standardization on the acquired pictures, and then start the picture labeling work: label the text data position and text data content in the picture;

[0083] S2: the picture that step S1 collects label is used as data set and Reading Chinese Text in the Wild (RCTW-17) data set is combined to train text detection model, text recognition model;

[0084] S3: After the above two models are trained, first, capture the video stream of the multi-source fusion video surveillance system for real-time frame capture, and then use digital image processing technology to perform a series of preprocessing on the acquired pictures: including G...

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 an intelligent recognition method for text data in power industry complex scene. According to the method, a series of preprocessing is adopted before text detection, characterdata information in a frame taking picture is enhanced, irrelevant information is weakened, post-processing is carried out after recognition, and a CBOW model in the natural language processing fieldis adopted for post-processing, so that the detection and recognition effects are improved. The text data detection rate is 96%, the recognition accuracy rate is about 85%, the accuracy rate is high,the operation speed is high on a local server, and the requirement for real-time performance can be met. Meanwhile, the method is not only suitable for the distribution room environment, but also suitable for various complex scenes or even natural scenes in the electrical industry, and is wide in application.

Description

technical field [0001] The invention relates to an intelligent recognition method for character data in complex scenes in the electric power industry, and belongs to the technical field of artificial intelligence recognition in the electric power industry. Background technique [0002] Power resources are the foundation and lifeblood of the national economy. Power distribution is the link in the power system that is directly connected to users and distributes power to users. Whether the status of power distribution equipment is normal is directly related to the quality and safety of power consumption. Uptime is critical. [0003] The traditional monitoring method of power distribution equipment mainly adopts the manual inspection method, that is, the inspection personnel regularly read, record and interpret the manual data of power distribution equipment, instruments and other equipment. It takes a lot of time, manpower, material and financial resources to carry out manual ...

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): G06K9/34G06K9/46G06K9/62G06K9/00
CPCG06V20/41G06V30/153G06V10/50G06V30/10G06F18/214G06F18/241
Inventor 聂礼强甘甜张化祥许克姚一杨张玉卉
Owner SHANDONG UNIV
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com