Real-time face detection in color video

Szu-Hao Huang*, Shang Hong Lai

*Corresponding author for this work

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

4 Scopus citations

Abstract

In this paper, we propose a novel and fast face detection algorithm for detecting face in color video sequences. This algorithm can be integrated into a real-time surveillance or a video retrieval or indexing system. We focus on both speed and accuracy in the design of the algorithm. A set of multi-resolution Haar wavelet coefficients pairs is selected by the proposed learning algorithm to determine if a particular region is a face. We apply an ID3-like balanced decision tree for the wavelet coefficients quantization, to reduce the quantization error. For each pairs of quantized features, we estimate the associated conditional joint probability density function from a large set of face and non-face training data. Then, we compute the Kullback Leibler (KL) distance to measure the discrimination between the face and non-face conditional density functions for each feature pair. The feature pairs with larger KL-distance are selected as the feature candidates. It is an effective feature dimension reduction method and helps to speedup the Adaboost training algorithm when considering the spatial relationship between all coefficient pairs. Aided by an automatic skin color judgment method and a Gaussian face location model both in tepmporal and spatial domain, the experiments show that the proposed algorithm runs faster than 4 times the video rate with good detection accuracy.

Original languageEnglish
Title of host publicationProceedings - 10th International Multimedia Modelling Conference, MMM 2004
EditorsY.-P.P. Chen
Pages338-345
Number of pages8
DOIs
StatePublished - 14 Jul 2004
EventProceedings - 10th International Multimedia Modelling Conference, MMM 2004 - Brisbana, Australia
Duration: 5 Jan 20047 Jan 2004

Publication series

NameProceedings - 10th International Multimedia Modelling Conference, MMM 2004

Conference

ConferenceProceedings - 10th International Multimedia Modelling Conference, MMM 2004
CountryAustralia
CityBrisbana
Period5/01/047/01/04

Fingerprint Dive into the research topics of 'Real-time face detection in color video'. Together they form a unique fingerprint.

Cite this