Title :
Rotation-invariant face detection using angular projections
Author :
Kim, H.I. ; Lee, S.H. ; Cho, N.I.
Author_Institution :
Sch. of Electr. Eng. & Comput. Sci., Seoul Nat. Univ., South Korea
fDate :
6/10/2004 12:00:00 AM
Abstract :
A rotation-invariant face detection algorithm is proposed using angular projections in the feature space. The angular projections are applied to the extracted skin colour region, and the pattern of the projections for all angular directions is compared with a template to detect the frontal faces. Experimental results show that the proposed algorithm has a good detection rate and reduces the false positives regardless of the rotation of the faces.
Keywords :
face recognition; feature extraction; image colour analysis; angular projections; rotation-invariant face detection; skin colour region extraction;
Journal_Title :
Electronics Letters
DOI :
10.1049/el:20040477
