Carved character recognition method and system and storage medium

A text recognition and text technology, applied in the field of text recognition, can solve the problems of low reliability of recognition, high labor costs in the working environment and staff, etc., to achieve the effect of improving reliability and work efficiency, reducing labor costs, and good significance

Active Publication Date: 2019-08-27
佛山缔乐视觉科技有限公司
View PDF6 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the harsh working environment, high labor costs, visual fatigue of the staff themselves, and subjective differences are all reasons for the low reliability of recognition.

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
  • Carved character recognition method and system and storage medium
  • Carved character recognition method and system and storage medium
  • Carved character recognition method and system and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0057] The present invention will be further explained and described below in conjunction with the accompanying drawings and specific embodiments of the description. For the step numbers in the embodiment of the present invention, it is only set for the convenience of explanation and description, and there is no limitation on the order of the steps. The execution order of each step in the embodiment can be carried out according to the understanding of those skilled in the art Adaptive adjustment.

[0058] At present, the text detection and recognition technology in the field of engraving has the following disadvantages:

[0059] (1) Traditional text recognition methods rely on manually defined features.

[0060] Although there is a lot of work on how to define a good set of text features, most of the practical features are not universal, and they are not robust to noise, and even fail to distinguish noise and text well. In extreme cases, many features are almost invalid or e...

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 carved character recognition method and system and a storage medium. The method comprises the following steps of: automatically acquiring an image of a measured object through a binocular camera; processing the acquired image through convolution operation and deconvolution operation to generate a depth map; extracting a character region in the depth map through a region recommendation network; and performing character recognition on the character area based on the bidirectional long-short-term memory network to obtain a recognition result of the engraved characters. Binocular stereoscopic vision technology and deep learning technology are combined. The significance of the character area is better by constructing the depth map, manual detection and recognition arenot needed. Labor cost is greatly reduced, the reliability and the working efficiency of engraved character recognition are improved, and the method can be widely applied to the technical field of character recognition.

Description

technical field [0001] The invention relates to the technical field of character recognition, in particular to a method, system and storage medium for recognizing engraved characters. Background technique [0002] Engraved text is often found on metal workpieces in the field of mechanical engineering and on plaster pipes for fluid filtration in the food and chemical industry. These engraved characters generally identify the specifications and attributes of different workpieces. Because the characters on the surface of these workpieces are concave characters formed by engraving, the color difference between these characters and the background is not obvious, so the image of the engraved characters can generally only be formed by the difference in surface reflection conditions between the text area and the background area, so its The requirements of the optical collection system are more stringent. In addition, limited by the lighting conditions and the reflective characteri...

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): G06K9/20G06K9/34G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V10/22G06V10/267G06N3/045G06F18/24
Inventor 林健发李飞洋邓学良肖盼
Owner 佛山缔乐视觉科技有限公司
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