Skip to main navigation Skip to search Skip to main content

Face Detection Model Based on Distance Measure of Regional Feature

  • Xi'an Jiaotong University

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

Abstract

This paper proposes a new model for face detection based on statistics by applying the mosaic method. The model is insensitive to illumination and can adapt to the distortion and slope of face in some degree. Moreover there is an extra good feature of this model, i.e. attention focusing capability. Firstly a distance measure, that is MD (Mahalanobis Distance), is presented, which is suitable for vector clustering. Secondly the standard deviation of gradient norm and direction angle in each mosaic block are selected as the regional features in the model. The tested images are detected as human faces when both the MDs of gradient norm and direction angle to the collectivity of human faces are small. Eventually, abundant experiments have been made under different conditions and the results of the experiments have reached the expectations.

Original languageEnglish
Title of host publicationInternational Conference on Signal Processing Proceedings, ICSP
EditorsYuan Baozong, Tang Xiaofang
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1479-1482
Number of pages4
ISBN (Electronic)0780357477
DOIs
StatePublished - 2000
Event5th International Conference on Signal Processing, ICSP 2000 - Beijing, China
Duration: 21 Aug 200025 Aug 2000

Publication series

NameInternational Conference on Signal Processing Proceedings, ICSP
Volume3
ISSN (Print)2164-5221
ISSN (Electronic)2164-523X

Conference

Conference5th International Conference on Signal Processing, ICSP 2000
Country/TerritoryChina
CityBeijing
Period21/08/0025/08/00

Keywords

  • distance measure
  • face detection
  • mosaic method
  • regional feature

Fingerprint

Dive into the research topics of 'Face Detection Model Based on Distance Measure of Regional Feature'. Together they form a unique fingerprint.

Cite this