An Approach to Automatic Detection and Extraction of Regions of Interest in Still Images
Localisation and extraction of a salient region in an image constitutes an important task in computer vision. It is a very challenging problem due to its ill-posed nature. Furthermore, it is not always evident even for humans. In this paper we present an approach for automatic detection and extraction of salient regions. The main core of the algorithm is based on Ullman and Koch’s model of the bottom-up attention, however their approach usually predicts only the place of a salient region. Therefore, in order to improve the achieved results a segmentation method based on k-means has been adopted. In addition, a few heuristic limitations are applied to the previous segmentation method in order to prevent it from creating inadequate segments. We show that our approach can render quite precise results in localisation and extraction tasks, taking into account the human point of view.
KeywordsSalient Region Salient Detection Gaussian Pyramid Primary Saliency Automate Object Recognition
Unable to display preview. Download preview PDF.
- 1.Anouncia, S.M., Joseph, J.G.: An Approach for Automated Object Recognition and Extraction from Images — a Study. Journal of Computing and Information Technology 17(4), 359–370 (2009)Google Scholar
- 2.Judd, T., Ehinger, K., Durand, F., Torralba, A.: Learning to Predcit Where Humans Look. In: IEEE Int. Conf. on Computer Vission, ICCV 2009 (2009)Google Scholar
- 6.Koch, C., Ullman, S.: Shifts in Selective Visual-Attention — Towards the Underlying Neural Circuitry. Human Neurobiology 4, 219–277 (1985)Google Scholar
- 8.Zhang, J., Zhuo, L., Shen, L.: Region of Interest Extraction Based on Visual Attention Model and Watershed Segmentation. In: IEEE International Conference on Neural Networks & Signal Processing, pp. 375–378 (2008)Google Scholar
- 9.Liu, T., Sun, J., Zheng, N.N., Tang, X., Shum, H.Y.: Learning to Detect A Salient Object. In: IEEE Conf. on Computer and Vision Pattern Recognition, pp. 1–8 (2007)Google Scholar
- 10.Larlus, D., Jurie, F.: Combining Appearance Models and Markov Random Fields for Category Level Object Segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR, pp. 1–7 (2008)Google Scholar
- 11.Aldavaret, D., Ramisa, A., Toledo, R., López de Mántaras, R.: Fast and Robust Object Segmentation with the Integral Linear Classifier. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR, pp. 1046–1053 (2010)Google Scholar
- 13.Marszalek, M., Schimd, C.: Semantic Hierarchies for Visual Object Recognition. In: IEEE Conf. on Computer Vision and Pattern Recogniton, pp. 1–7 (2007)Google Scholar
- 15.Athi Narayanan, S.: Homepage, http://sites.google.com/site/athisnarayanan/