Unlock instant, AI-driven research and patent intelligence for your innovation.

Face recognition from a temporal sequence of face images

A time sequence, image technology, applied in image analysis, image data processing, image data processing and other directions, can solve problems such as information waste

Inactive Publication Date: 2005-07-06
KONINKLIJKE PHILIPS ELECTRONICS NV
View PDF3 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

A lot of time information is wasted due to using only one face image or each image by itself

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
  • Face recognition from a temporal sequence of face images
  • Face recognition from a temporal sequence of face images
  • Face recognition from a temporal sequence of face images

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019] figure 2 A classifier 10' proposed by the present invention is illustrated which enables simultaneous use of multiple probe images 40 from the same individual in a sequence of images. It should be understood that for purposes of illustration a RBF network 10' may be used, but any classification method / device may be implemented.

[0020] The benefit of using several probe images simultaneously is the ability to create a single high quality and / or high resolution probe image which is then used by the facial recognition system to yield better recognition rates. First, based on the principles of the invention described in co-pending U.S. Patent Application Serial No. 09 / 966406 [Attorney Docket 702053, Attorney Docket 14901], entitled "Face recognition through warping," the probe map The images are slightly distorted relative to each other to align them, the content and disclosure of this patent application is hereby incorporated by reference. That is, the orientation of ...

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

A system and method for classifying facial images based on a temporal sequence of images, comprising the steps of: training a classifier device for recognizing facial images, the classifier device being trained using input data associated with complete facial images obtaining multiple probe images in temporal order of images; aligning the probe images with each other; combining these images to form a high resolution image; and classifying the probe images according to a classification method performed by a trained classifier device Classification of high-resolution images described above.

Description

technical field [0001] The present invention relates to facial recognition systems, and more particularly, to a system and method for performing facial recognition using time sequences of facial images for improving the robustness of recognition. Background technique [0002] Facial recognition is an important research area in human-computer interaction, and many algorithms and classifier devices for recognizing faces have been proposed. Typically, a facial recognition system stores a complete facial template obtained from multiple instances of a subject's face during the training of a classifier device, and compares a single probe (test) image to this stored template in order to identify individual. [0003] figure 1 A conventional classifier apparatus 10 is illustrated comprising, for example, a radial basis function (RBF) network having an input node layer 12, a hidden layer 14 comprising radial basis functions, and an output layer 18 for providing classes. A descripti...

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): G06T1/00G06K9/00G06T7/00G06T7/20
CPCG06V40/172G06V10/774G06V10/26
Inventor V·菲尔洛明M·特拉科维S·V·R·古特塔
Owner KONINKLIJKE PHILIPS ELECTRONICS NV