It is well known that in many situations combining diverse classifiers can improve the performanc... more It is well known that in many situations combining diverse classifiers can improve the performance of a classification system. In this paper, a new histogram based lip segmentation technique is proposed considering local kernel histograms in different illumination invariant colour spaces. The histogram is computed in local areas using two Gaussian kernels; one in the colour space and the other in the spatial domain. Using the estimated histogram, the posterior probability associated to non-lip class is then computed for each pixel. This process is performed considering different colour spaces. A weighted averaging method is then used for fusing the posterior probability values. As the result a new score is obtained which is used for labelling the pixels as lip or non-lip. The advantage of the proposed method is that the segmentation process is totally unsupervised. So, the method is robust against different variations such as variation in lip shape, skin colour, facial hair, illumination, etc. Moreover, an improved performance is achieved by fusing colour information.
Abstract. In this paper, the problem of fusing colour information at the feature level using kern... more Abstract. In this paper, the problem of fusing colour information at the feature level using kernel based feature extraction techniques is con-sidered within the framework of a face verification system. A few statis-tical feature extraction algorithms including kernel based methods ...
International Conference on Digital Image …, Jan 1, 2009
In this work, a novel method of fusing colour information in feature level is proposed considerin... more In this work, a novel method of fusing colour information in feature level is proposed considering a face verification system. For this purpose, composite kernels which have been already used in Support Vector Machine classifier is ap-plied within the framework of the Generalised ...
It is well known that in many situations combining diverse classifiers can improve the performanc... more It is well known that in many situations combining diverse classifiers can improve the performance of a classification system. In this paper, a new histogram based lip segmentation technique is proposed considering local kernel histograms in different illumination invariant colour spaces. The histogram is computed in local areas using two Gaussian kernels; one in the colour space and the other in the spatial domain. Using the estimated histogram, the posterior probability associated to non-lip class is then computed for each pixel. This process is performed considering different colour spaces. A weighted averaging method is then used for fusing the posterior probability values. As the result a new score is obtained which is used for labelling the pixels as lip or non-lip. The advantage of the proposed method is that the segmentation process is totally unsupervised. So, the method is robust against different variations such as variation in lip shape, skin colour, facial hair, illumination, etc. Moreover, an improved performance is achieved by fusing colour information.
Abstract. In this paper, the problem of fusing colour information at the feature level using kern... more Abstract. In this paper, the problem of fusing colour information at the feature level using kernel based feature extraction techniques is con-sidered within the framework of a face verification system. A few statis-tical feature extraction algorithms including kernel based methods ...
International Conference on Digital Image …, Jan 1, 2009
In this work, a novel method of fusing colour information in feature level is proposed considerin... more In this work, a novel method of fusing colour information in feature level is proposed considering a face verification system. For this purpose, composite kernels which have been already used in Support Vector Machine classifier is ap-plied within the framework of the Generalised ...
Uploads
Papers by Fahimeh Salimi