Modified GrabCut for Human Face Segmentation

Khattab, Dina; Theobalt, Christian; Hussein, Ashraf S.; Tolba, Mohamed F.

doi:10.1016/j.asej.2014.04.012

Item

ITEM ACTIONSEXPORT

Add to Basket

Local TagsRelease HistoryDetailsSummary

Released

Journal Article

Modified GrabCut for Human Face Segmentation

MPS-Authors

/persons/resource/persons44772

Khattab, Dina
Computer Graphics, MPI for Informatics, Max Planck Society;

/persons/resource/persons45610

Theobalt, Christian
Computer Graphics, MPI for Informatics, Max Planck Society;

External Resource

Link
(Any fulltext)

Fulltext (restricted access)

There are currently no full texts shared for your IP range.

Fulltext (public)

There are no public fulltexts stored in PuRe

Supplementary Material (public)

There is no public supplementary material available

Citation

Khattab, D., Theobalt, C., Hussein, A. S., & Tolba, M. F. (2014). Modified GrabCut for Human Face Segmentation. Ain Shams Engineering Journal, 5(4), 1083-1091. doi:10.1016/j.asej.2014.04.012.

Cite as: https://hdl.handle.net/11858/00-001M-0000-0024-AF83-F

Abstract

Abstract GrabCut is a segmentation technique for 2D still color images, which is mainly based on an iterative energy minimization. The energy function of the GrabCut optimization algorithm is based mainly on a probabilistic model for pixel color distribution. Therefore, GrabCut may introduce unacceptable results in the cases of low contrast between foreground and background colors. In this manner, this paper presents a modified GrabCut technique for the segmentation of human faces from images of full humans. The modified technique introduces a new face location model for the energy minimization function of the GrabCut, in addition to the existing color one. This location model considers the distance distribution of the pixels from the silhouette boundary of a fitted head, of a 3D morphable model, to the image. The experimental results of the modified GrabCut have demonstrated better segmentation robustness and accuracy compared to the original GrabCut for human face segmentation.