Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

A text detection and recognition method, system and computer equipment

A text detection and recognition method technology, applied in the field of text recognition, can solve problems such as low detection efficiency and difficult text detection, and achieve the effects of improving training efficiency, reducing training difficulty time, and improving text detection and recognition efficiency.

Active Publication Date: 2020-09-08
中邮消费金融有限公司
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Based on this, it is necessary to provide a text detection and recognition method, system and computer equipment to solve the technical problems of text distribution and text form diversification in the prior art, which lead to difficult text detection and low detection efficiency

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
  • A text detection and recognition method, system and computer equipment
  • A text detection and recognition method, system and computer equipment
  • A text detection and recognition method, system and computer equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0045]The technical solution of the present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments, so that those skilled in the art can better understand the present invention and implement it, but the examples given are not intended to limit the present invention.

[0046] Such as figure 1 As shown, the embodiment of the present invention provides a text detection and recognition method, including the following steps:

[0047] S1. Collect sample images from different angles to construct a sample image set, and preprocess the sample images in the sample image set;

[0048] S2. Train the classification model based on the sample image set to obtain an angle correction model;

[0049] S3, uniformly adjust the sample image to a standard angle, mark the real text box of the sample image, use the K-means clustering algorithm to calculate the anchor frame of the sample image set, and combine the sample image and th...

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 a text detection and recognition method, system and computer equipment. The method includes the following steps: collecting sample images from different angles to construct a sample image set; training a classification model based on the sample image set to obtain an angle correction model; unifying the sample images Adjust to the standard angle, mark the real text box of the sample image, use the K-means clustering algorithm to calculate the anchor box of the sample image set, input the sample image, real text box and anchor box into the yolo V3 network for training, and obtain the text box detection model ; Train the CRNN network based on the sample image marked with the text box to obtain the text recognition model; perform text detection and recognition on the text image to be tested according to the angle correction model, the text box detection model and the text recognition model. The invention reduces the difficulty of low-end training of the yolo V3 network, thereby improving the efficiency of text detection and recognition.

Description

technical field [0001] The invention relates to the technical field of text recognition, in particular to a text detection and recognition method, system and computer equipment. Background technique [0002] Text detection refers to the technology of accurately detecting the location of text from a picture. Text recognition, as the name implies, is a technology that recognizes text in a picture from a fixed position in the picture. At present, text detection and text recognition technologies are applied to various fields. For example, in licensed consumer financial institutions, a large number of certificate reviews and content reviews are carried out every day. The certificate pictures are mainly recognized by human eyes. Using text detection and recognition technology for document review can greatly improve work efficiency. In recent years, with the development of computer vision technology, text positioning and recognition in natural scenes has attracted great attention...

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 Patents(China)
IPC IPC(8): G06K9/32G06K9/62
CPCG06V20/62G06V10/243G06F18/23213
Inventor 钟龙申潘伟王珏廖健祝大裕
Owner 中邮消费金融有限公司
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
Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com