A mean shift and Non-negative PCA based color image segmentation approach.

Conference Paper · January 2010with13 Reads
DOI: 10.1109/ISSPA.2010.5605433 · Source: DBLP
Conference: 10th International Conference on Information Sciences, Signal Processing and their Applications, ISSPA 2010, Kuala Lumpur, Malaysia, 10-13 May, 2010


    Image segmentation plays an important role in computer vision systems. An algorithm based on dimension reduction and the mean shift algorithm is used for the segmentation of color images. The Non negative matrix factorization is used for the transformation of the RGB components to a lower dimensional space. The mean shift algorithm is used to cluster the date in the reduced space and hence segment the image.