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

Video human face identification and retrieval method based on on-line learning and Bayesian inference

A face recognition and face detection technology, which is applied in the field of face recognition technology, can solve problems such as not being able to fit spatial data distribution well, achieve accurate online training and recognition mechanism, improve automation, and improve accuracy Effect

Inactive Publication Date: 2009-06-24
BEIHANG UNIV
View PDF0 Cites 42 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

(2) K.C.Lee's method uses a fixed number of subspaces to represent the video face manifold, which does not fit the distribution of spatial data well

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
  • Video human face identification and retrieval method based on on-line learning and Bayesian inference
  • Video human face identification and retrieval method based on on-line learning and Bayesian inference
  • Video human face identification and retrieval method based on on-line learning and Bayesian inference

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0083] The training database of the embodiment is composed of videos of 28 people, and each sequence includes 100 to 510 frames of images. In these videos, the face includes various expressions and posture changes. The posture changes are mainly reflected in the two-dimensional plane rotation and the three-dimensional rotation of the face. The test database consists of a surveillance video of about 4 minutes, about 2013 frames of images, and contains a total of 3 target persons. The face detection algorithm detects 2305 face images, and all samples are normalized to 60×60 pixel images. Figure 6 with Figure 7 Sample samples of partial samples of the test database and training database are respectively shown.

[0084] Given the surveillance video and all target models in the embodiment, by calculating the probability that the current video face sample belongs to the target model, the recognition result is given based on the Bayesian inference accumulated historical recognition inf...

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 method for recognizing and retrieving video faces based on on-line study and Bayesian inference. The method comprises the following steps: step one: establishing an initialization model of a face recognition model, (i.e. the face recognition model adopts a GMM face recognition model); step two: establishing a face category model, (i.e. the model renewal of the initialization face model is performed by adopting an incremental learning manner); step three: recognizing and retrieving video faces. The test sequence and the category model are assigned, the sequence recognition information of the accumulation video in the Bayesian inference process is utilized, the probability density function of the identity is propagated according to information of a time axis, and the method provides recognition results of the video faces for users based on the MAP rules to obtain recognition scores. The invention establishes a model training frame based on non-supervised learning completely, according to spatial distribution of the training sequence, the initialization model is evolved for the category model in different modes, and the distribution of spatial data is better fitted through adjusting Gaussian mixture number of the face category model.

Description

Technical field [0001] The invention relates to a video face recognition and retrieval method based on online learning and Bayesian inference, which belongs to the intelligent monitoring technology in computer vision, especially the face recognition technology. Background technique [0002] With the widespread application of surveillance video technology, there is an increasing need for surveillance video systems to have a video face recognition function in order to be able to perform online and real-time video face retrieval. Its specific performance is: the surveillance video can realize the target person recognition frame by frame, and the recognition result and the corresponding image are saved in the form of index. When the user needs to understand the activity trajectory of a specific target, all relevant images are called out to the user to view, and the target behavior is understood in a manual way. [0003] However, because in surveillance video, there are some people wh...

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): G06K9/00G06K9/62
Inventor 李江伟苟高鹏王蕴红
Owner BEIHANG UNIV
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