Unconstrained Object Segmentation Using GrabCut Based on Automatic Generation of Initial Boundary
2
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
Foreground estimation in object segmentation has been an important issue for last few decades. In this paper we propose a GrabCut based automatic foreground estimation method using block clustering. GrabCut is one of popular algorithms for image segmentation in 2D image. However GrabCut is semi-automatic algorithm. So it requires the user input a rough boundary for foreground and background. Typically, the user draws a rectangle around the object of interest manually. The goal of proposed method is to generate an initial rectangle automatically. In order to create initial rectangle, we use Gabor filter and Saliency map and then we use 4 features (amount of area, variance, amount of class with boundary area, amount of class with saliency map) to categorize foreground and background. From the experimental results, our proposed algorithm can achieve satisfactory accuracy in object segmentation without any prior information by the user.
Abstract
Foreground estimation in object segmentation has been an important issue for last few decades. In this paper we propose a GrabCut based automatic foreground estimation method using block clustering. GrabCut is one of popular algorithms for image segmentation in 2D image. However GrabCut is semi-automatic algorithm. So it requires the user input a rough boundary for foreground and background. Typically, the user draws a rectangle around the object of interest manually. The goal of proposed method is to generate an initial rectangle automatically. In order to create initial rectangle, we use Gabor filter and Saliency map and then we use 4 features (amount of area, variance, amount of class with boundary area, amount of class with saliency map) to categorize foreground and background. From the experimental results, our proposed algorithm can achieve satisfactory accuracy in object segmentation without any prior information by the user.
참고문헌 (13)
- Nilsback, M. E., "A Visual Vocabulary for flower Classification", Proceedings of Computer Vision and Pattern Recognition, 2, pp.1447~1454 (2006)
- Boykov, Y.Y., "Interactive graph cuts for optimal boundary and region segmentation of objects in N-D imagaes", Proc. ICCV, 2, pp.105~112 (2011)
- Bowman, M., "Delving into the whorl of flower segmentation", BMVC (2007)
- Kang Han Oh, "Flower Segmentation in Natural Scene Images", The Proc. 1st International Advanced Information Technology and Sensor Application (2012)
- A Shokoufandeh, "View-based object recognition using saliency maps", Image and Computing, 17, pp.445~460 (1999)
- L. Bertelli, "Kernelized Structural SVM Learning for Supervised Object Segmentation", CVPR (2011)
- V. Levesque, "Texture segmentation using Gabor filters", Center for Intelligent Machines Journal (2000)
- Moosmann, F., "Learning saliency maps for object categorization", European Conference in Computer Vision (ECCV), Inter- national Workshop on The Representation and Use of Prior Knowledge in Vision 2006 (2006)
- C. Rother, "GrabCut: Interactive Foreground Extraction using Iterated Graph Guts", SCM Transaction on Graphics (TOG), pp.1~6 (2004)
- Y. Boycov, "Interactive graph cuts for optimal boundary and region segmentation of objects in N-D images", Proc. IEEE Int. Conf. on Computer Vision, In ICCV, pp.105~112 (2001)
- Tomas Malmer, "Image segmentation using GrabCut", ~ (2010)
- R. Achanta, "Freauency-tuned salient region detection", CVPR, pp.1597~1604 (2009)
- Kang Han Oh, "Flower Segmentation in Natural Scene Images", ~