Saliency has been widely applied to detecting the most attractive object in an image. This paper presents a novel method based on saliency map for object localization in an image. We regard saliency map computation as a preprocessing step, which is obtained using a discriminative regional feature integration approach. Then, the saliency map is processed to highlight more saliency contour and remove some subordinately salient points using region-grow segmentation algorithm. Finally, saliency object is located with efficient sub-window search algorithm (ESS) in the binarized saliency map. This approach is able to identify the exact location and roughly the size of saliency object in an image. The performance evaluation using MSRA-B dataset demonstrates our approach performs well in object localization in images.
CITATION STYLE
Wang, Y., Yang, J., Yang, F., & Zhang, G. (2017). A novel object localization method in image based on saliency map. In Advances in Intelligent Systems and Computing (Vol. 455, pp. 31–41). Springer Verlag. https://doi.org/10.1007/978-3-319-38771-0_4
Mendeley helps you to discover research relevant for your work.