Skin Region Segmentation based on the Average Preprocessed Image of Multicolor Face Image Sequence  

Oleh:

Jiao, Fangyuan ; He, Xianbo ; Li, Wei

Jenis: Article from Journal - ilmiah nasional - terakreditasi DIKTI
Dalam koleksi: Journal of Engineering and Technological Sciences vol. 46 no. 04 (2014), page 381-393.
Topik: face detection; image sequence; multicolor; preprocessing; skin region
Fulltext: 378-3108-2-PB.pdf (962.0KB)

Isi artikel

Abstract. This paper proposes a method for skin region segmentation for face images with unbalanced color and light based on preprocessing of a multicolor face image sequence. In this method, multicolor face images from a sequence are preprocessed in order to remove color offset and uneven brightness. Then the color data from the preprocessed face images are used for taking the average in order to remove noise and smoothen the face image. Finally, skin region segmentation for the average preprocessed face image is realized based on the established ellipse skin model. Experiments have shown that this method has good performance.

Opini Anda

Klik untuk menuliskan opini Anda tentang koleksi ini!

Kembali