Abstract
This paper presents a novel dynamic threshold approach to discriminate skin pixels and non-skin pixels in color images.Fixed decision boundaries (or fixed threshold) classification approaches are successfully applied to segment human skin.These fixed thresholds mostly failed in two situations as they only search for a certain skin color range: 1) any non-skin object may be classified as skin if non-skin objects’s color values belong to fixed threshold range. 2) any true skin may be mistakenly classified as non-skin if that skin color values do not belong to fixed threshold range. Therefore in this paper, instead of predefined fixed thresholds, novel online learned dynamic thresholds are used to overcome the above drawbacks.The experimental results show that our method is robust in overcoming these drawbacks.
Original language | English |
---|---|
Title of host publication | Unknown Host Publication |
Publisher | IEEE Signal Processing Society |
Pages | 2225-2228 |
Number of pages | 4 |
ISBN (Print) | 978-1-4244-7994-8 |
DOIs | |
Publication status | Published (in print/issue) - 3 Dec 2010 |
Event | Proc. of the IEEE 17th International Conference on Image Processing (ICIP-10) - Hong Kong Convention and Exhibition Centre, Hong Kong, China Duration: 3 Dec 2010 → … |
Conference
Conference | Proc. of the IEEE 17th International Conference on Image Processing (ICIP-10) |
---|---|
Period | 3/12/10 → … |