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

Character recognition method and device

A character and technology to be recognized, applied in the field of image recognition, can solve the problems of low character recognition accuracy and limited number of acquisitions, and achieve the effects of reducing labor costs, improving efficiency, and improving accuracy

Inactive Publication Date: 2019-11-05
DEEPBLUE TECH (SHANGHAI) CO LTD
View PDF8 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the training data of KEYENCE's handheld terminal is obtained by manual marking, and the number of acquisitions is limited. Especially in real application scenarios, the three-dimensional shape of the surface of the object to which the character is attached will vary due to the camera angle, light intensity, and Influenced by factors such as rules, the accuracy of character recognition 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
  • Character recognition method and device
  • Character recognition method and device
  • Character recognition method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0078] In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0079] In the following, some terms used in the embodiments of the present application are explained, so as to facilitate the understanding of those skilled in the art.

[0080] 1. Region of interest (Region of interest, ROI) refers to machine vision and image processing, which outlines the area to be processed from the processed image in the form of boxes, circles, ellipses, irregular polygons, etc.

[0081] 2. "Multiple" in the embodiment of the present application refers to two or more than two, in view of this, "multiple" in the embodiment of the present application can also be understood as "at least two". "And / or" describes the association relationshi...

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 provides a character recognition method and device, which are used for improving the accuracy of character recognition. The character recognition method comprises the steps of obtaininga to-be-recognized image, wherein the to-be-recognized image comprises a plurality of characters; inputting the to-be-identified image into a convolutional neural network, and identifying and obtaining a plurality of characters included in the to-be-identified image, wherein the training data of the convolutional neural network is a plurality of training sample images, the plurality of training sample images are generated after image processing is performed on any one training sample image, the image processing is one or more of shape transformation, color difference adjustment and illumination intensity adjustment, and any one training sample image comprises a plurality of characters.

Description

technical field [0001] The embodiments of the present application relate to the field of image recognition, and in particular to a character recognition method and device. Background technique [0002] Character detection refers to the detection of confirmation, identification, and judgment of characters printed on parts or products. It is used in various occasions, such as the marking of products on automated production lines, the warehousing of warehousing systems, and the production of food and drugs. Packaging and so on. [0003] The current character recognition, such as Keyence's handheld terminal, is recognized by constructing a mathematical model of features. As an example, the circle algorithm is expressed as Hough circle transform. However, the training data of KEYENCE's handheld terminal is obtained by manual marking, and the number of acquisitions is limited. Especially in real application scenarios, the three-dimensional shape of the surface of the object to wh...

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): G06K9/34G06K9/32G06N3/04G06N3/08G06K9/36
CPCG06N3/08G06V10/25G06V30/153G06V10/20G06N3/045
Inventor 陈海波
Owner DEEPBLUE TECH (SHANGHAI) CO LTD