Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Method for detecting and positioning a character area in a financial industry image based on deep learning

A deep learning and text area technology, applied in the field of image processing, can solve problems such as low recognition rate, inaccuracy, and error-prone, and achieve the effect of enriching scenes, expanding training samples, and preventing model overfitting

Inactive Publication Date: 2019-03-19
SUNYARD SYST ENG CO LTD
View PDF3 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in the related art, in the existing OCR text recognition method, individual characters are cut, and then each word is recognized at the same time. Once a cutting error occurs in the single word cutting, the single word recognition is wrong, and it also affects other individual characters. word recognition
Thereby, the method of prior art OCR individual character segmentation positioning and then character recognition is inaccurate, error-prone, and recognition rate is low

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
  • Method for detecting and positioning a character area in a financial industry image based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] The present invention will be described in detail below according to the accompanying drawings and preferred embodiments, and the purpose and effect of the present invention will become clearer. The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

[0023] Such as figure 1 As shown, a method for detecting and locating text regions in financial industry images based on deep learning, the method includes the following steps:

[0024] S1: Select Chinese characters, phrases and compound words commonly used in the financial industry, generate Chinese character pictures of different font types, and form a training data set;

[0025] Select 3,816 commonly used Chinese characters and 312 common financial vocabulary, use different font types such as Song,...

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 a method for detecting and positioning a character area in a financial industry image based on deep learning, which comprises the following steps of: selecting Chinese characters; phrases and combined words commonly used in the financial industry, and forming a transformed data set by adding some processing; generating a text area candidate box, and calculating the score ofeach candidate text area; merging text category supervision information, merging multi-level regional down-sampling information, and inputting text features into the LSTM network model to form an end-to-end candidate text region generation network; and finally, correcting the positions of the candidate text areas, and filtering redundant candidate areas by using a candidate box. According to theinvention, rapid detection of texts at any angle can be realized.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a method for detecting and locating text regions in financial industry images based on deep learning. Background technique [0002] OCR-based text area detection, positioning and recognition technology in the financial field refers to the use of computers and other equipment to automatically extract and recognize valid information in paper materials using OCR technology (optical character recognition), and perform corresponding processing. It is one of the key technologies for computer automatic processing to realize paperless banking. [0003] In related technologies, the OCR text recognition method is divided into processes such as text line segmentation, single character segmentation, single character recognition, and language model decoding. After line segmentation is performed on an image, a single word is segmented, and then the single word obtained by segmentation...

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): G06K9/20G06K9/32G06K9/62G06N3/04G06N3/08
CPCG06N3/084G06V10/22G06V30/1478G06V30/287G06N3/045G06F18/214
Inventor 桂晓雷林路王慜骊安通鉴林康陈立强
Owner SUNYARD SYST ENG CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap 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