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

Recognition error correcting system and method

A technology of recognition unit and algorithm model, which is applied in the field of text recognition, can solve the problems of low recognition rate of handwritten documents, achieve the effect of solving the low efficiency of manual entry, improving work efficiency and entry accuracy

Inactive Publication Date: 2018-08-17
SF TECH
View PDF4 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Aiming at the problem of low recognition rate of handwritten documents in OCR technology, the present invention provides a recognition and correction system and method, which improves the disadvantages of low accuracy rate of OCR technology in recognizing text sequences

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
  • Recognition error correcting system and method
  • Recognition error correcting system and method
  • Recognition error correcting system and method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0025] The present invention will be specifically described below in conjunction with specific examples, but is not limited to the specific examples.

[0026] The preferred embodiment of the present invention is the address identification and deviation correction of the express waybill. In the following embodiments, the present invention will be specifically described by using the address identification and deviation correction of the express waybill.

[0027] In this embodiment, through the comprehensive use of artificial intelligence, big data and geographic information, the paper waybill information is digitized in real time to realize real-time processing and application of the waybill data. Aiming at the problem of low recognition rate of handwritten waybills by OCR technology, the system and method for address recognition and deviation correction in this embodiment improves the disadvantage of low accuracy rate of character sequence recognition by OCR technology.

[0028...

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 recognition error correcting system and method, and the system and method are used for the data processing of paper bill information. The system comprises an image obtainingunit which is used for obtaining a paper bill image; a recognition unit which is used for recognizing characters in the bill image, and obtaining a recognition result data set of a bill; an information error correcting unit which is used for the error correcting of the recognition result data set, and obtaining the corrected bill information; and a data storage unit which is used for storing an information database, the bill image and the recognition result data set of the bill and the corrected bill information. The information database is the training data of the information error correcting unit. According to the invention, the system and method iron out the defect that the precision and accuracy of the OCR technology in recognizing a character sequence.

Description

technical field [0001] The invention relates to the technical field of character recognition, and is especially suitable for character recognition in a handwritten address area of ​​a logistics order. Background technique [0002] In recent years, with the rapid development of e-commerce, express shipments have shown explosive growth, and the address information entry of express waybills is mainly entered one by one by traditional manual methods. [0003] The traditional mode of manually entering the address of the courier bill is inefficient, and due to the complexity of handwritten courier waybills and the risk of incorrect or incomplete addresses on the courier bill itself, delivery is difficult. [0004] With the development of character recognition technology, the recognition of handwritten paper express waybills has also introduced OCR recognition technology, but OCR technology has stricter requirements for the normativeness of handwritten characters, and the recogniti...

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): G06K9/32G06K9/72
CPCG06V20/63G06V30/274G06V30/287
Inventor 王志成张玉双王亮高磊邝展豪刘志欣胡奉平
Owner SF TECH
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