Abstract
As an essential stage of human ear recognition, Ear detection has a direct and important impact on final recognition performance. Traditional Adaboost algorithm based human ear detection method has some inherent drawbacks will lead to imperfect ear detection, such as the long time training, overly dependent on ear samples quality, etc. Therefore, to overcome such problems partially, the strategies of YCbCr skin-color filtering and multi-template matching are introduced to get more accurate ear location under occasions of insufficient training and bad initial ear position. The proposed method can eliminate most cases of false positing and multi-location or incomplete selection. Experimental results show the proposed method is robust and effective not only in static image but also under dynamic environments.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: 2010 3rd Intl Conference on Computer Science and Information Technology (ICCSIT)
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
