In this paper we propose a probabilistic approach for the automatic organization of collected pictures aiming at more eﬀective representation in personal photo albums. Images are analyzed and described in two representation spaces, namely, faces and background. Faces are automatically detected, rectiﬁed and represented pro jecting the face itself in a common low dimensional eigenspace. Backgrounds are represented with low-level visual features based on RGB histogram and Gabor ﬁlter energy. Face and background information of each image in the collection is automatically organized by mean-shift clustering technique. Given the particular domain of personal photo libraries, where most of the pictures contain faces of a relatively small number of diﬀerent individuals, clusters tend to be semantically signiﬁcant beyond containing visually similar data. We report experimental results based on a dataset of about 1000 images where automatic detection and rectiﬁcation of faces lead to approximately 300 faces. Signiﬁcance of clustering has been evaluated and results are very encouraging.
|Numero di pagine||15|
|Stato di pubblicazione||Published - 2008|