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

Sign language recognition method based on deep belief network and multi-mode characteristics

A deep belief network and recognition method technology, applied in character and pattern recognition, biological neural network models, neural learning methods, etc., can solve problems such as information is not necessarily accurate, and a single feature cannot fully reflect image information, and achieve high recognition. rate effect

Inactive Publication Date: 2019-05-14
JINLING INST OF TECH
View PDF2 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Generally speaking, since a single feature cannot fully reflect the image information, the information obtained after each feature is processed by a classifier is not necessarily accurate.

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
  • Sign language recognition method based on deep belief network and multi-mode characteristics
  • Sign language recognition method based on deep belief network and multi-mode characteristics
  • Sign language recognition method based on deep belief network and multi-mode characteristics

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0021] Such as figure 1 As shown, the sign language image sample library is established, the sign language image is preprocessed, the sign language area is separated from the sign language image, a variety of characteristic parameters of the sign language area are extracted, and multi-modal feature information that can express the sign language is synthesized. The contrastive divergence algorithm is used to train each layer of RBM, and the parameters of the model are adjusted according to the given training samples, so that the probability distribution of visible layer nodes represented by the RBM is consistent with the training data as much as possible under the parameters. According to the model parameters obtained through training, the samples to be classified can be identified.

[0022] The present invention adopts following technical scheme:

[0023] A sign language recognition method based on a deep belief network and multi-modal features, the steps are as follows:

[...

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 sign language recognition method based on a deep belief network (DBN) and multi-mode characteristics, and relates to the field of image processing technology and machine learning. The method comprises the following steps of: obtaining a sample; inputting a sign language image or video; preprocessing the sign language image; extracting a Histogram of direction gradient histogram (HOG); Characteristics such as local binary patterns (Local Binding Patterns, LBP) and Zernike moments are used as characteristic parameters, and a deep belief network is used for training and identification. The method can identify sign language information in the image in real time, and has high identification accuracy.

Description

technical field [0001] The invention relates to a sign language recognition method based on a deep belief network (DeepBeliefNetwork, DBN) and multi-mode features, and belongs to the fields of image processing technology and machine learning. technical background [0002] Sign language refers to words with a certain meaning formed by simulating images or syllables with conventional gesture changes (or supplemented by expressions). It is an "important aid in spoken language," and for the hearing-impaired it is the primary communication tool. [0003] The purpose of sign language recognition is to provide an effective and accurate mechanism through the computer to translate sign language into text or voice to make communication between deaf and hearing people more convenient and faster. There are currently more than 20 million deaf people in our country. The research on sign language recognition will undoubtedly directly benefit this group, providing them with a more natural,...

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
IPC IPC(8): G06K9/00G06K9/38G06K9/46G06K9/62G06N3/04G06N3/08
Inventor 胡勇
Owner JINLING INST OF TECH
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