Region-of-Interest Extraction in Low Depth of Field Images
This document provides the segmentation results of more than 200 low depth of field (DOF) images. The low DOF images have been selected from the Corel dataset [1]-[2] and the Web [3].
The following is an example of experimental results including image description obtained from the proposed approach.
|
Original Color Image
|
Gray-scale Image
|
Block-based
Interest Region |
Region Saliency Map
(RSM) |
Estimated Mask
|
Region of Interest
(Gray-scale) |
Region of Interest
(Color) |
|
|
|
|
|
|
|
|
Image References:
[1] J. Li and J. Z. Wang, "Automatic Linguistic Indexing of Pictures by a statistical modeling approach," Pattern Analysis and Machine Intelligence, IEEE Transactions on, vol. 25, pp. 1075-1088, 2003.
[2] J. Z. Wang, J. Li, and G. Wiederhold, "SIMPLIcity: semantics-sensitive integrated matching for picture libraries," Pattern Analysis and Machine Intelligence, IEEE Transactions on, vol. 23, pp. 947-963, 2001.
[3] H. Li and K. N. Ngan, "Learning to Extract Focused Objects from Low DOF Images," Circuits and Systems for Video Technology, IEEE Transactions on, vol. 21, pp. 1571-1580, 2011.
|
