A GibbsBoost Face Detector and its Application to Facial Occlusion Spotting
-
- Matsui Atsushi
- NHK Science and Technical Research Laboratories Faculty of Science and Engineering, Waseda University
-
- Goto Yu
- Faculty of Science and Engineering, Waseda University
-
- Kimura Akio
- Faculty of Science and Engineering, Waseda University
-
- Nakada Yohei
- Faculty of Science and Engineering, Waseda University
-
- Matsumoto Takashi
- Faculty of Science and Engineering, Waseda University
-
- Clippingdale Simon
- NHK Science and Technical Research Laboratories
-
- Fujii Mahito
- NHK Science and Technical Research Laboratories
-
- Yagi Nobuyuki
- NHK Science and Technical Research Laboratories
Bibliographic Information
- Other Title
-
- ＧｉｂｂｓＢｏｏｓｔ顔検出と映像監視業務への応用
- GibbsBoost カオ ケンシュツ ト エイゾウ カンシ ギョウム エノ オウヨウ
Search this article
Abstract
We propose non-deterministic methods for automatically detecting occlusions of people's faces by superimposed symbols. We trained a face detector using an ensemble-learning algorithm (GibbsBoost) that is based on the sequential Monte Carlo method. We implemented an occlusion detector using a mixture of two discriminant functions that were related to the size of the detected face region and the occluded face area. One realization of this detector achieved a true positive detection rate of 90%. We present experimental results and discuss possibilities for further improvements.
Journal
-
- The Journal of The Institute of Image Information and Television Engineers
-
The Journal of The Institute of Image Information and Television Engineers 62 (3), 408-413, 2008
The Institute of Image Information and Television Engineers
- Tweet
Keywords
Details 詳細情報について
-
- CRID
- 1390001205097135360
-
- NII Article ID
- 110006855160
- 40016191264
-
- NII Book ID
- AN10164169
-
- ISSN
- 09156755
- 18816908
- 13426907
-
- Text Lang
- ja
-
- Data Source
-
- JaLC
- NDL
- Crossref
- CiNii Articles
- KAKEN
-
- Abstract License Flag
- Disallowed
