DocumentCode
3728109
Title
An Automatic Two-Hand 2D:4D Finger-Ratio Measurement Algorithm for Flatbed Scanned Images
Author
Frode Eika Sandnes
Author_Institution
Fac. of Technol. Art &
fYear
2015
Firstpage
1203
Lastpage
1208
Abstract
There is a vast body of research based on 2D:4D finger ratio measurements within the fields of medicine, physiology, and several other disciplines. There are well-known conventions for how such finger measures should be conducted, and all such measurements are to this date manual. Manual measurements are time consuming and prone to human error, different practices and subjective influences. This study proposes a novel algorithm for automatically computing the 2D:4D finger ratios using images of hand pairs. The algorithm is simple to implement and robust to image noise. Initial experimental assessments indicate that the algorithm successfully manages to accurately determine 2D:4D finger ratios. The proposed algorithm could help improve the research fields that make use of digit ratio measurements. Areas of algorithm improvements are also identified.
Keywords
"Thumb","Image color analysis","Indexes","Feature extraction","Algorithm design and analysis","Robustness"
Publisher
ieee
Conference_Titel
Systems, Man, and Cybernetics (SMC), 2015 IEEE International Conference on
Type
conf
DOI
10.1109/SMC.2015.215
Filename
7379347
Link To Document