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

Character recognition method, device, apparatus, and storage medium

A character recognition and character technology, applied in the field of character recognition, can solve the problems of poor recognition effect, cutting multiple characters into single characters, etc., and achieve accurate recognition effect

Inactive Publication Date: 2019-01-25
摩佰尔(天津)大数据科技有限公司
View PDF4 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In view of this, the object of the present invention is to overcome the problem in the prior art that when multiple characters overlap, multiple characters cannot be cut into single characters, resulting in poor recognition effect, and provide a character recognition method and device , equipment and storage media

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
  • Character recognition method, device, apparatus, and storage medium
  • Character recognition method, device, apparatus, and storage medium
  • Character recognition method, device, apparatus, and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0049] figure 1 It is the character recognition method provided by Embodiment 1 of the present invention. Such as figure 1 As shown, this embodiment provides a character recognition method, including:

[0050] Step 101, acquiring an image to be recognized; the image to be recognized contains characters to be recognized;

[0051] Step 102, using a pre-trained character recognition model to extract the image feature vector from the image to be recognized as a whole, and identify the character to be recognized on the image to be recognized according to the image feature vector;

[0052] Step 103, acquiring the recognized characters recognized by the character recognition model.

[0053] In this embodiment, the pre-trained character recognition model can be used to extract the image feature vector from the acquired image to be recognized as a whole, and the character to be recognized on the acquired image to be recognized can be identified through the image feature vector, ther...

Embodiment 2

[0055] Based on the above embodiments, Embodiment 2 of the present invention provides another embodiment of a character recognition method, combining figure 1 , figure 2 , the method includes:

[0056] Step 101, acquiring an image to be recognized; the image to be recognized contains characters to be recognized;

[0057] Step 102, using a pre-trained character recognition model to extract the image feature vector from the image to be recognized as a whole, and identify the character to be recognized on the image to be recognized according to the image feature vector;

[0058] In this step, the pre-trained character recognition model can extract the image feature vector from the obtained image to be recognized as a whole, and the character to be recognized on the image to be recognized can be recognized through the image feature vector,

[0059] Specifically, the method for pre-training the character recognition model includes the following steps:

[0060] Step 201. Obtain ...

Embodiment 3

[0103] image 3 It is a schematic structural diagram of a character recognition device provided by an embodiment of the present application. refer to image 3 , the embodiment of the present application provides a character recognition device, including:

[0104] The first acquiring module 301 is configured to acquire an image to be recognized; the image to be recognized contains characters to be recognized;

[0105] The extraction module 302 is used to extract the image feature vector from the image to be recognized as a whole by using a pre-trained character recognition model;

[0106] Recognition module 303, for recognizing the character to be recognized on the image to be recognized according to the image feature vector;

[0107] The second acquiring module 304 is configured to acquire the recognized characters recognized by the character recognition model.

[0108] Optionally, also include:

[0109] The third obtaining module is used to obtain the training image unit...

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 character recognition method, a device, an apparatus and a storage medium, which are applied to the technical field of character recognition, and solves the problem that when a plurality of characters are overlapped, the plurality of characters can not be cut into a single character, resulting in poor recognition effect in the related art. The character recognition method comprises the following steps: acquiring an image to be recognized, wherein the image to be recognized contains characters to be recognized, extracting image feature vectors from the image to be recognized as a whole by using a character recognition model trained in advance, recognizing characters to be recognized on the image to be recognized according to the image feature vectors, and acquiring the recognized characters recognized by the character recognition model. The method is mainly used in character recognition.

Description

technical field [0001] The invention relates to the technical field of character recognition, in particular to a character recognition method, device, equipment and storage medium. Background technique [0002] With the development of information technology, character recognition technology is often needed in daily life. Characters are often stored in pictures. Traditionally, ordinary character images rely on scanners or digital cameras for recognition. The method usually requires character segmentation in pictures containing characters, and then uses templates for matching. However, when multiple characters overlap , this method cannot cut multiple characters into a single character, and thus cannot accurately recognize the characters. Contents of the invention [0003] In view of this, the object of the present invention is to overcome the problem in the prior art that when multiple characters overlap, multiple characters cannot be cut into single characters, resulting ...

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): G06K9/46G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V10/44G06V30/10G06N3/045G06F18/2414
Inventor 熊兴发孔令晏
Owner 摩佰尔(天津)大数据科技有限公司