Please use this identifier to cite or link to this item:
https://hdl.handle.net/20.500.14279/2707
Title: | Enhancing the robustness of skin-based face detection schemes through a visual attention architecture | Authors: | Tsapatsoulis, Nicolas Rapantzikos, Konstantinos |
Major Field of Science: | Natural Sciences | Field Category: | Computer and Information Sciences | Keywords: | Image processing;Visualization;Computer architecture;Face--Identification | Issue Date: | 2005 | Source: | IEEE International Conference on Image Processing, 11-14 September 2005, Genova | Conference: | IEEE International Conference on Image Processing | Abstract: | Bottom up approaches to visual attention (VA) have been applied successfully in a variety of applications, where no domain information exists, e.g. general purpose image and video segmentation. In face detection, humans perform conscious search; therefore, bottom up approaches are not so efficient. In this paper we introduce the inclusion of two channels in the VA architecture proposed by Itti et al. (1998) to account for motion and conscious search in a scene. Increasing the channels in the architecture requires an efficient way of combining the various maps that are produced. We solve this problem by using an innovative committee machine scheme which allows for dynamically changing the committee members (maps) and weighting the maps according to the confidence level of their estimation. The overall VA architecture achieves significantly better results compared with the simple skin based face detection as shown in the experimental results | URI: | https://hdl.handle.net/20.500.14279/2707 | DOI: | 10.1109/ICIP.2005.1530301 | Rights: | © IEEE | Type: | Conference Papers | Affiliation : | National Technical University Of Athens University of Cyprus |
Appears in Collections: | Δημοσιεύσεις σε συνέδρια /Conference papers or poster or presentation |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Tsapatsoulis_Enhancing the Robustness of skin based.pdf | 231.8 kB | Adobe PDF | View/Open |
CORE Recommender
SCOPUSTM
Citations
50
5
checked on Nov 9, 2023
Page view(s) 20
470
Last Week
0
0
Last month
0
0
checked on Nov 7, 2024
Download(s) 50
308
checked on Nov 7, 2024
Google ScholarTM
Check
Altmetric
Items in KTISIS are protected by copyright, with all rights reserved, unless otherwise indicated.