文章基本信息

标题：Skin Colour Segmentation Using Finite Bivariate Pearsonian Type-Iib Mixture Model and K-Means
本地全文：下载
作者：B. N. Jagadesh ; K. Srinivasa Rao ; Ch. Satyanarayana 等
期刊名称：Signal & Image Processing : An International Journal (SIPIJ)
印刷版ISSN：2229-3922
电子版ISSN：0976-710X
出版年度：2012
卷号：3
期号：4
页码：37
出版社：Academy & Industry Research Collaboration Center (AIRCC)
摘要：Skin colour segmentation plays an important role in computer vision, face detection and human relatedsystems. Much work has been reported in literature regarding skin colour detection using Gaussianmixture model. The Gaussian mixture model has certain limitations regarding the assumptions like pixelsin each component are mesokurtic, having negative range and it doesn’t adequately represent the varianceof the skin distribution under illumination conditions. In this paper we develop and analyze a new skincolour segmentation based on HSI colour space using bivariate Pearsonian type-IIb mixture model. Themodel parameters are estimated by deriving the updated equation of EM-Algorithm. The initialization ofthe model parameters is done through K-means algorithm and method of moments. The segmentationalgorithm is obtained using component maximum likelihood under Bayes frame. The experimental resultsusing hue and saturation as feature vector revealed that the developed method perform better with respectto segmentation performance metrics than that of Gaussian mixture model. This method is useful in facedetection and medical diagnostics.
关键词：Skin segmentation; bivariate Pearsonian type-IIb mixture model; EM-Algorithm; HSI Colour space.