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

Lip detection and reading method based on cascade feature extraction

A feature extraction and cascading technology, applied in cross-fields, achieves the effect of reducing useless redundant data, improving speed and accuracy, and avoiding huge calculations

Active Publication Date: 2018-10-26
NANJING UNIV OF POSTS & TELECOMM
View PDF10 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] So far, most domestic related research is still in the laboratory stage, and a lot of research work is still needed for the detection and identification of the lip area.

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
  • Lip detection and reading method based on cascade feature extraction
  • Lip detection and reading method based on cascade feature extraction
  • Lip detection and reading method based on cascade feature extraction

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0041] The technical scheme of the present invention will be further described in detail below in conjunction with the accompanying drawings:

[0042] figure 1 It is a lip detection and reading method process based on cascading feature extraction. First input a video, and the video is grayed frame by frame and the size is normalized, which is equivalent to preprocessing, which is conducive to subsequent detection. The lip region is detected on the preprocessed video image by the Viola Jones method, that is, the integral map of the input image is calculated first, and then the Haar feature is quickly calculated according to the integral map to obtain the weak classifier, and the discrete adaptive advance algorithm These weak classifiers are cascaded to form a strong classifier to achieve detection. The classifier cascade structure is as follows figure 2 Shown.

[0043] Then, multi-level feature extraction is performed on the lip region image. First, threshold binarization of the...

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 lip detection and reading method based on cascade feature extraction. The method of the invention comprises firstly detecting the lip region of the input video, and realizingthe lip region detection through a Viola-Jones method based on a Hall classifier and an adaptive advancing algorithm; secondly, according to the color feature of the lip region, performing thresholdbinarization on the detected area to extract the lip region, performing discrete cosine transformation on the image of the lip region to concentrate the information of the video image in a certain area of the data matrix, and extracting the data by an appropriate screening method; then, the dimension of the eigenvalues with large contribution value is extracted by a principal component analysis algorithm, so that the dimension of the data can be further reduced; according to a certain scale of data samples, a sequence dictionary tree is established for recognition, and Levinstein distance is used for similarity analysis and fuzzy matching of sequence, finally, the static characteristics of each frame and the dynamic characteristics of the video are combined to query the dynamic sequence tocomplete the reading of the lip region. The invention can improve the speed and accuracy of lip reading and has good practicability and robustness through multi-level extraction and dimension reduction of lip region image features.

Description

Technical field [0001] The invention relates to a lip detection and reading method based on cascade feature extraction, which belongs to the cross-technology fields of computer vision, image processing, human-computer interaction and the like. With the development of my country's economy and society and the advancement of science and technology, the detection and recognition method of lips in video images has become an important content in the fields of social science and natural science. It has a wide range of applications in many fields such as smart cities, human-computer interaction, assisted speech recognition, and life and health, and is of greater significance for people with noisy environments or hearing impairments. Background technique [0002] Computer lip reading recognition refers to the use of a computer to analyze the visual information of the speaker's lips to identify the content of his speech, and can be combined with auditory recognition to further improve the ...

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
CPCG06V40/20G06F18/211G06F18/24
Inventor 王洲杰陈志岳文静刘玲于涛刘真
Owner NANJING UNIV OF POSTS & TELECOMM
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