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

Deep learning-based detection and identification method for numbers in video or picture

A deep learning, in-picture technology, applied in character and pattern recognition, instruments, computer parts, etc., to achieve the effect of improved recognition speed and strong robustness

Inactive Publication Date: 2018-09-21
哈尔滨哈船智控科技有限责任公司
View PDF1 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to solve the existing technical problems, the present invention proposes a method for detecting and identifying numbers in videos or pictures based on deep learning

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
  • Deep learning-based detection and identification method for numbers in video or picture
  • Deep learning-based detection and identification method for numbers in video or picture
  • Deep learning-based detection and identification method for numbers in video or picture

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0031] combine Figure 1-Figure 3 , the present invention proposes a method for detecting and identifying numbers in videos or pictures based on deep learning, the method comprising image data collection, training data calibration, generating training data and performing automatic calibration, deep learning model training and real-time detection five The purpose of identification is accomplished in one step, which specifically includes the followin...

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 deep learning-based detection and identification method for numbers in a video or a picture. Collected samples are processed, training data are produced, and an appropriate manner is selected to calibrate numbers in pictures; number features which may appear are simulated to increase a training set, transformation operations of the various features are carried out on the numbers, produced numbers samples are placed in the collected pictures, and automatic labeling is carried out; and after producing of the training data is completed, a faster-rcnn algorithm is employedto jointly train an rpn network and an identification network, and then the video or the picture collected in real time is identified by a trained model. According to the method, the rich training samples are obtained under various conditions of cases, illumination and the like, the numbers in the pictures and labels of the numbers are rationally designed, the very rich training samples with thedifferent features are also manually designed for network learning, cases of misidentification or non-identification are greatly reduced, and detection speed is very high.

Description

technical field [0001] The invention belongs to the technical field of pattern recognition and deep learning, in particular to a method for detecting and recognizing numbers in videos or pictures based on deep learning. Background technique [0002] With the continuous development of the inland river industry, the number of ships is increasing, the hull is also moving towards the direction of large-scale, and the draft of the ship is getting deeper and deeper, and shipping accidents occur from time to time, which not only poses a threat to the safety of shipping Threats, damage to shipping channels, but also affect the operational efficiency of shipping. Ship grounding is the most frequent occurrence of various accidents, and the causes are various, but the most common reason is that the ship exceeds the prescribed waterline. Among all kinds of ship traffic accidents, the accidents caused by exceeding the waterline account for a large proportion. [0003] At present, the d...

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): G06K9/20G06K9/62
CPCG06V10/22G06F18/214G06F18/24
Inventor 朱齐丹吕晓龙游锦成吴禹辰
Owner 哈尔滨哈船智控科技有限责任公司
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