Tytuł artykułu
Autorzy
Identyfikatory
Warianty tytułu
Przegląd algorytmów map wyróżnień typu bottom-up
Języki publikacji
Abstrakty
Saliency map is a model of the conspicuity of the image locations. It is based on a number of feature maps extracted from the image, where both the feature list and the methods of extraction depend on the particular solution. The purpose of this paper is to collect and present the best-known methods of calculating saliency maps, with an emphasis on bottom-up methods that work without any previous assumptions of the content of processed images. The top-down methods that are designed to work with only a narrow class of images representing known objects are outside the scope of this review.
Mapa wyróżnień jest to model zróżnicowania lokalizacji obrazu. Bazuje na sekwencji map cech otrzymanych z obrazu, przy czym zarówno lista cech, jak i metody ich otrzymywania różnią się w zależności od konkretnego rozwiązania. Celem tego artykuły jest zgromadzenie i zaprezentowanie najbardziej znanych metod obliczania map wyróżnień, ze szczególnym uwzględnieniem algorytmów typu bottom-up, czyli takich, które pracują bez żadnych wcześniejszych założeń na temat zawartości opracowywanego obrazu. Metody typu top-down zaprojektowane do pracy z wąskimi klasami obrazów reprezentujących znane obiekty leżą poza zakresem tego artykułu.
Wydawca
Rocznik
Tom
Strony
53--57
Opis fizyczny
Bibliogr. 16 poz.
Twórcy
autor
- Instytut Maszyn Matematycznych, Warszawa
Bibliografia
- [1] C. Koch and S. Ullman, “Shifts in selective visual attention: towards the underlying neural circuitry.,” Human Neurobiology 4, pp. 219-227, 1985.
- [2] L. Itti, C. Koch and E. Niebur, “A model of saliency-based visual attention for rapid scene analysis.,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 20, p. 1254-1259, 11, 1998.
- [3] X. Hou and L. Zhang, “Dynamic Visual Attention: Searching for coding length increments,” in Advances in Neural Information Processing Systems, D. Koller, D. Schuurmans, Y. Bengio and L. Bottou, Eds., 2009, pp. 681-688.
- [4] L. Zhang, T. K. Marks and M. H. Tong, "SUN: A Bayesian Framework for Saliency Using Natural Statistics,” Journal of Vision, vol. 8, no. 7, pp. 1-20, December 2008.
- [5] A. G. Leventhal, Ed., The Neural Basis of Visual Function: Vision and Visual Dysfunction, vol. 4., Boca Raton, FI: CRC Press, 1991.
- [6] S. Engel, X. Zhang and B. Wandell, “Colour Tuning in Human Visual Cortex Measured With Functional Magnetic Resonance Imaging," Nature, vol. 388, no. 6, 637, p. 68-71, July 1997.
- [7] F. Liu and M. Gleicher, “Region enhanced scale-invariant saliency detection,” in ICME'06: Proceedings of IEEE international conference on multimedia and expo, 2006.
- [8] N. D. B. Bruce and J. K. Tsotsos, "Saliency, attention, and visual search: An information theoretic approach,” Journal of Vision, vol. 9, no. 3, pp. 1-24, March 2009.
- [9] J. Harel, C. Koch and P. Perona, “Graph-Based Visual Saliency,” Proceedings of Neural Information Processing Systems (NIPS)., 2006.
- [10] X. Hou, J. Harel and C. Koch, “Image Signature: Highlighting Sparse Salient Regions,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 34, no. 1, pp. 194-201, January 2012.
- [11] A. Oliva and A. Torralba, “Modeling the Shape of the Scene: A Holistic Representation of the Spatial Envelope,” International Journal of Computer Vision, vol. 42, no. 3, pp. 145-175, 2001.
- [12] X. Hou and L. Zhang, “Saliency Detection: A Spectral Residual Approach,” in IEEE Conference on Computer Vision and Pattern Recognition, 2007.
- [13] R. Achanta, F. Estrada, P. Wils and S. Susstrunk, “Salient region detection and segmentation.,” in International Conference on Computer Vision Systems, 2008.
- [14] R. Achanta, S. Hemami, F. Estrada and S. Susstrunk, “Frequency-tuned Salient Region Detection,” IEEE International Conference on Computer Vision and Pattern Recognition (CVPR 2009), pp. 1597-1604, 2009.
- [15] Y. Fang, Z. Chen, W. Lin and C.-W. Lin, “Saliency-based image retargeting in the compressed domain,” in Proceedings of the 19th ACM international conference on Multimedia, New York, 2011.
- [16] M.-M. Cheng, G.-X. Zhang, N. J. Mitra, X. Huang and S.-M. Hu, “Global contrast based salient region detection," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Washington, DC, 2011.
Typ dokumentu
Bibliografia
Identyfikator YADDA
bwmeta1.element.baztech-89d7d9d5-9b23-448a-9297-f2319111eaf0