Method for identifying characters in picture, computer equipment and storage medium

A recognition method and optical character recognition technology are applied in the fields of computer equipment and storage media, and the recognition method of characters in pictures, which can solve the problems such as the influence of the recognition accuracy of optical character recognition, and achieve the effect of facilitating subsequent recognition and improving the recognition accuracy.

Pending Publication Date: 2020-03-27
SHANGHAI XIAOI ROBOT TECH CO LTD
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

When the characters in the picture to be detected are tilted, distorted or have different backgrounds, the recognition accuracy of optical character recognition will be affected to a certain extent

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 identifying characters in picture, computer equipment and storage medium
  • Method for identifying characters in picture, computer equipment and storage medium
  • Method for identifying characters in picture, computer equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0066] Figure 1n It is a flow chart of a method for recognizing characters in pictures provided by Embodiment 1 of the present invention. This embodiment is applicable to character recognition in natural scenes, and generally can be integrated into computer equipment. Such as Figure 1n As shown, the method of this embodiment specifically includes:

[0067] Step 101. Input the picture to be processed into the optical character recognition model.

[0068] Wherein, the optical character recognition model is trained by using the training sample set in advance. After the OCR model learns appropriate and correct parameters, input the image to be processed into the OCR model. The pictures to be processed are pictures including characters.

[0069] Optionally, the optical character recognition model includes: a third convolutional layer connected in sequence, a first spatial transformation network, a dense convolutional network, a second spatial transformation network, a long-te...

Embodiment 2

[0099] figure 2 It is a flow chart of a method for recognizing characters in a picture provided by Embodiment 2 of the present invention. This embodiment can be combined with each optional solution in one or more of the above embodiments. In this embodiment, image feature extraction of the first depth is performed on the picture to be processed to obtain the first feature matrix, which may include: obtaining the image to be processed The pixel matrix of the picture; use the filter with the preset window size to perform convolution operation with the pixel matrix to obtain the first feature matrix.

[0100]And, performing the first space transformation process on the first feature matrix to obtain the first space transformation feature matrix may include: determining at least one parameter to be transformed according to the first feature matrix and a preset space transformation method; according to the parameter to be transformed , search to determine the mapping relationship...

Embodiment 3

[0133] image 3 It is a schematic structural diagram of a computer device provided by Embodiment 3 of the present invention. image 3 A block diagram of an exemplary computer device 12 suitable for implementing embodiments of the invention is shown. image 3 The computer device 12 shown is only an example, and should not impose any limitation on the functions and scope of use of the embodiments of the present invention.

[0134] Such as image 3 As shown, computer device 12 takes the form of a general purpose computer device. Components of computer device 12 may include, but are not limited to, one or more processors 16, memory 28, bus 18 connecting various system components including memory 28 and processor 16. Processor 16 includes, but is not limited to, an AI processor.

[0135] Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, or a local bus using ...

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 embodiment of the invention discloses a method for identifying characters in a picture, computer equipment and a storage medium. The method comprises the steps of inputting a to-be-processed picture into an optical character recognition model; performing image feature extraction of a first depth on the to-be-processed picture to obtain a first feature matrix; performing first spatial change processing on the first feature matrix to obtain a first spatial transformation feature matrix; carrying out image feature extraction of a second depth on the first spatial transformation feature matrixto obtain a second feature matrix, wherein the number of first convolution layers used for image feature extraction of the second depth is greater than the first depth; performing second spatial change processing on the second feature matrix to obtain a second spatial transformation feature matrix; and obtaining a recognition result of the characters included in the to-be-processed picture according to the second spatial transformation feature matrix. According to the embodiment of the invention, the image features of the to-be-processed picture can be corrected, and the recognition accuracyis improved.

Description

technical field [0001] The embodiments of the present invention relate to the technical field of computer vision, and in particular to a method for recognizing characters in pictures, computer equipment and storage media. Background technique [0002] Optical Character Recognition (OCR) based on computer vision has been widely used in the commercial field. Optical Character Recognition Detecting and recognizing text in natural scene images remains challenging. [0003] Pictures containing natural scenes will have many factors that affect text recognition. For example, lots of lighting changes, perspective distortions, picture quality, text fonts, different backgrounds, etc. When the characters in the picture to be detected are tilted, distorted or have different backgrounds, the recognition accuracy of OCR will be affected to a certain extent. Contents of the invention [0004] Embodiments of the present invention provide a method for recognizing characters in a picture...

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): G06K9/62G06N3/04
CPCG06V30/10G06N3/045G06F18/213
Inventor 茅心悦
Owner SHANGHAI XIAOI ROBOT TECH CO LTD
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
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap