• English
    • français
    • português
    • العربية
  • English 
    • English
    • français
    • português
    • العربية
  • Login
View Item 
  •   NUB IR
  • Academic Bibliography - NUB
  • Bangladeshi Journal
  • View Item
  •   NUB IR
  • Academic Bibliography - NUB
  • Bangladeshi Journal
  • View Item
JavaScript is disabled for your browser. Some features of this site may not work without it.

Face detection using color and symmetry information

Thumbnail
View/Open
NUBJAS_1_Face Detection using Color and Symmetry.pdf (191.4Kb)
Date
2015
Author
Hoque, A. H. M. Sajedul
Bhuiyan, Md. Moynul Haque
Bhuiyan, Md. Al-Amin
Metadata
Show full item record
Abstract
The localization of human faces in digital images is a fundamental step in the process of face recognition. This paper presents a face detection method based on color, local symmetry and geometry information of human face. The algorithm first detects most likely face regions or ROIs (Region- Of-Interest) from the image using skin color model and face outline model and produces a face color similarity map. Then it performs local symmetry detection within these ROIs to obtain a local symmetry similarity map. These two maps are fused to obtain potential facial feature points. Finally similarity matching is performed to identify faces between the fusion map and face geometry model under affine transformation. The output results are the detected faces with confidence values. Experimental results demonstrate its validity and robustness to identify faces under certain variations.
URI
http://hdl.handle.net/123456789/834
Collections
  • Bangladeshi Journal [94]

copyright © 2023  Library and Information Department, Northern University Bangladesh
Contact Us | Send Feedback
Theme by 
Atmire NV
 

 

Browse

All of NUB IRCommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

My Account

LoginRegister

copyright © 2023  Library and Information Department, Northern University Bangladesh
Contact Us | Send Feedback
Theme by 
Atmire NV