Title :
Segmentation of the same object in different view
Author :
Han, Ying Li ; Ju, Hae Jin ; Park, Rae-Hong
Author_Institution :
Dept. of Electron. Eng., Sogang Univ., Seoul, South Korea
Abstract :
In this paper, we propose an object segmentation method to extract the same object from images that are captured from different views. Using matting method, the target object can be easily segmented with simple strokes given by a user to the desired object and background in the reference image. Then, homography is estimated after keypoint matching between the segmented object image and the target image, which is acquired from a different viewpoint, containing the same object. Using homography, the strokes are transformed to fit to a target image. Finally, the identical object is segmented from the target image using matting method with transformed strokes. The proposed method can be used to increase the accuracy of segmentation for extracting the same desired object from a target image.
Keywords :
feature extraction; image matching; image segmentation; object tracking; homography; image capturing; keypoint matching; matting method; object extraction; object image segmentation; reference image; stroke transformation; target image segmentation; target image transformation; target object; Computer vision; Educational institutions; Image color analysis; Image segmentation; Object segmentation; Transforms; SIFT; homography; image matting; object segmentation; stroke transformation;
Conference_Titel :
Signal Processing, Communication and Computing (ICSPCC), 2012 IEEE International Conference on
Conference_Location :
Hong Kong
Print_ISBN :
978-1-4673-2192-1
DOI :
10.1109/ICSPCC.2012.6335615