Title :
Enhancing the Bayesian network approach to face detection
Author :
De Souza Coelho, Paulo Sérgio ; Esperança, Cláudio ; De Oliveira, Antonio Alberto Fernandes
Author_Institution :
Lab. de Comput. Grafica, Univ. Fed. do Rio de Janeiro, Brazil
Abstract :
This work presents some improvements to the Bayesian network approach to face detection. Feature selection is directed towards avoiding the problems caused by considering feature fragments as complete features. More selective criteria for grouping are applied, thus reducing the number of candidate groups that must be considered. Statistical measures dependent on the feature size are used to increase the detection reliability, especially in images of groups of people
Keywords :
belief networks; face recognition; feature extraction; statistical analysis; Bayesian network approach; candidate groups; detection reliability; face detection; feature fragments; feature selection; feature size; people; selective criteria; statistical measures; Bayesian methods; Control systems; Data security; Face detection; Face recognition; Image recognition; Lighting; Mouth; Size measurement; Statistics;
Conference_Titel :
Computer Science Society, 1999. Proceedings. SCCC '99. XIX International Conference of the Chilean
Conference_Location :
Talca
Print_ISBN :
0-7695-0296-2
DOI :
10.1109/SCCC.1999.810170