1. A Universal Framework for Salient Object Detection
- Author
-
Weisi Lin, Patrick Le Callet, Bingren Wang, Chunping Hou, Lei Jianjun, Yuming Fang, Nam Ling, Tianjin University (TJU), Jiangxi University of Finance and Economics (JUFE), School of Computer Engineering [Singapore] (NTU), School of Computer Engineering, Nanyang Technological University, Institut de Recherche en Communications et en Cybernétique de Nantes (IRCCyN), Mines Nantes (Mines Nantes)-École Centrale de Nantes (ECN)-Ecole Polytechnique de l'Université de Nantes (EPUN), Université de Nantes (UN)-Université de Nantes (UN)-PRES Université Nantes Angers Le Mans (UNAM)-Centre National de la Recherche Scientifique (CNRS), and Santa Clara University
- Subjects
Computer science ,Feature extraction ,ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION ,02 engineering and technology ,Salience (neuroscience) ,0202 electrical engineering, electronic engineering, information engineering ,Media Technology ,Computer vision ,Saliency map ,Electrical and Electronic Engineering ,ComputingMilieux_MISCELLANEOUS ,Ground truth ,business.industry ,020206 networking & telecommunications ,Pattern recognition ,Object detection ,Computer Science Applications ,Weighting ,Visualization ,Kadir–Brady saliency detector ,Salient ,[INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV] ,Signal Processing ,020201 artificial intelligence & image processing ,Artificial intelligence ,business - Abstract
In this paper, we propose a novel universal framework for salient object detection, which aims to enhance the performance of any existing saliency detection method. First, rough salient regions are extracted from any existing saliency detection model with distance weighting, adaptive binarization, and morphological closing. With the superpixel segmentation, a Bayesian decision model is adopted to refine the rough saliency map to obtain a more accurate saliency map. An iterative optimization method is designed to obtain better saliency results by exploiting the characteristics of the output saliency map each time. Through the iterative optimization process, the rough saliency map is updated step by step with better and better performance until an optimal saliency map is obtained. Experimental results on the public salient object detection datasets with ground truth demonstrate the promising performance of the proposed universal framework subjectively and objectively.
- Published
- 2016
- Full Text
- View/download PDF