Abstract : A simple and effective method for visual saliency detection in colour images is presented. The method is based on the common observation that local salient regions exhibit distinct geometric and and texture patterns from neighbouring regions. We model the colour distribution of local image patches with a Gaussian density and measure the saliency of each patch as the statistical distance from that density. Experimental results with public datasets and comparison with other state-of-the-art methods show the effectiveness of our method.
https://hal-univ-bourgogne.archives-ouvertes.fr/hal-01426990 Contributeur : Désiré SidibéConnectez-vous pour contacter le contributeur Soumis le : jeudi 5 janvier 2017 - 11:07:38 Dernière modification le : dimanche 26 juin 2022 - 00:45:37 Archivage à long terme le : : jeudi 6 avril 2017 - 12:33:27
Désiré Sidibé, F Mériaudeau. Visual saliency detection in colour images based on density estimation. Electronics Letters, IET, 2017, 53, pp.24 - 25. ⟨10.1049/el.2016.2156⟩. ⟨hal-01426990⟩