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

Deep learning-based lip language recognition lip shape model library construction method

A technology of deep learning and model library, applied in character and pattern recognition, instruments, computer components, etc., can solve problems such as heavy workload and difficulty in ensuring comprehensiveness, achieve efficient technical means and improve construction efficiency

Inactive Publication Date: 2015-04-01
ANHUI COSWIT INFORMATION TECH
View PDF4 Cites 29 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the existing technology, the lip models are mostly established one by one manually, not only the workload is heavy, but also its comprehensiveness is difficult to guarantee

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 lip language recognition lip shape model library construction method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0015] In order to describe the present invention more specifically, the technical solutions of the present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0016] Such as figure 1 As shown in Fig. 1, first, a camera with a microphone is used to synchronously capture the lip video image and speech of the target person. When collecting lip video images and speech sounds, it is necessary to ensure the synchronization of the two to avoid errors in subsequent analysis due to sound delays. Then, the computer analyzes the lip video image according to the image analysis technology to obtain lip shape feature values, and the computer analyzes the speech sound according to the speech recognition technology to obtain text information corresponding to the speech sound. One-to-one correspondence between the lip shape feature values ​​and the text information is generated to generate a training database, and then the com...

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 deep learning-based lip language recognition lip shape model library construction method which comprises the following steps: automatically analyzing the lip image and the speaking voice by a computer, extracting the characteristic value of the lip shape and generating characters corresponding to the speaking voice to form a training database, and learning the training database by using a deep learning technology so as to construct the lip shape model library. Through the technical scheme, the construction efficiency of the lip shape model library is greatly improved.

Description

technical field [0001] The invention relates to the technical field of building a human-computer interaction model library, in particular to a method for building a lip shape model library for lip language recognition based on deep learning. Background technique [0002] With the development of artificial intelligence technology, people have begun to use computer video analysis technology for lip language recognition to solve the problem of on-site oral production instructions in noisy places such as production workshops. In the process of lip language recognition, a lip shape model library is needed, and its accuracy and comprehensiveness will directly determine the efficiency of lip language recognition. In the prior art, lip models are mostly built one by one manually, which not only has a large workload, but also is difficult to guarantee its comprehensiveness. [0003] In order to solve the above problems, the present invention provides a deep learning-based lip langua...

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): G06K9/00G06K9/62
CPCG06V40/20
Inventor 陈拥权李建中郑荣稳
Owner ANHUI COSWIT INFORMATION 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