%0 Conference Proceedings
%4 sid.inpe.br/sibgrapi/2015/07.23.04.57
%2 sid.inpe.br/sibgrapi/2015/07.23.04.57.25
%T Eyebrow segmentation and characterization using energy estimation and K-Means clustering
%D 2015
%A Ramesh, Aditya,
%A Gopalakrishnan, Anand,
%A Chaturvedi, Ashvini,
%@affiliation National Institute of Technology Karnataka, Surathkal, India
%@affiliation National Institute of Technology Karnataka, Surathkal, India
%@affiliation National Institute of Technology Karnataka, Surathkal, India
%E Vieira, Thales Miranda de Almeida,
%E Mello, Vinicius Moreira,
%B Conference on Graphics, Patterns and Images, 28 (SIBGRAPI)
%C Salvador, BA, Brazil
%8 26-29 Aug. 2015
%I Sociedade Brasileira de Computação
%J Porto Alegre
%S Proceedings
%K eyebrow parameters, segmentation, K-means, biometric, facial expression.
%X The eyebrow is an important feature point in a facial image. The data from a segmented eyebrow can be used as a cue for gender determination, mood analysis, facial expression recognition, non-verbal communication and biometric purposes. In this paper, we present a novel method to segment the eyebrow and characterize the state of the eyebrow based on the evaluation of a few key parameters such as thickness and archness of the eyebrow and distance of the eyebrow from the eye. Our technique involves obtaining a box containing the eye and eye brow region using Viola-Jones algorithm. We then segment out the skin region in this box by using the fact that the skin is abundant in its red component as compared to the eye and eyebrows. Further, we perform energy based thresholding to detect the darker regions in this box and then perform K-means clustering to obtain the best possible segmentation for the eyebrow.
%@language en
%3 Sibgrapi_AR_cam_ready.pdf