Human segmentation is an important task in digital cameras. In this study, we present a framework of non-parametric human segmentation based on SVM. By exploiting spatial and color features of training images, the framework achieves noticeably better human segmentation results than GrabCut in terms of the overlap ratio with ground-truth.
|Title of host publication||2016 IEEE International Conference on Consumer Electronics, ICCE 2016|
|Editors||Francisco J. Bellido, Daniel Diaz-Sanchez, Nicholas C. H. Vun, Carsten Dolar, Wing-Kuen Ling|
|Publisher||Institute of Electrical and Electronics Engineers Inc.|
|Number of pages||2|
|Publication status||Published - 2016 Mar 10|
|Event||IEEE International Conference on Consumer Electronics, ICCE 2016 - Las Vegas, United States|
Duration: 2016 Jan 7 → 2016 Jan 11
|Name||2016 IEEE International Conference on Consumer Electronics, ICCE 2016|
|Other||IEEE International Conference on Consumer Electronics, ICCE 2016|
|Period||16/1/7 → 16/1/11|
Bibliographical notePublisher Copyright:
© 2016 IEEE.
All Science Journal Classification (ASJC) codes
- Computer Networks and Communications
- Electrical and Electronic Engineering