Title :
A two-stage binarizing algorithm for automatic 2D:4D finger ratio measurement of hands with non-separated fingers
Author :
Frode Eika Sandnes
Author_Institution :
Faculty of Technology Art and Design, Oslo and Akershus University College of Applied Sciences, Oslo, Norway
Abstract :
2D:4D finger ratios are commonly measured manually. Previous automatic methods have relied on the fingers being spread apart for successful detection. This study proposes an improved automatic finger-ratio measurement approach that does not require the fingers to be spread apart. The approach comprises a two-stage binarizing algorithm. First, the hand is separated from the background. Second, the various fingers are separated such that a unique outline of the hand can be obtained and thus the 2D:4D finger ratio can be measured. The algorithm achieves accurate results of 66% on a test-suite of flatbed scans of two-hand images. Automatic validation of measurement quality is also discussed.
Keywords :
"Thumb","Histograms","Brightness","Image color analysis","Technological innovation","Information technology"
Conference_Titel :
Innovations in Information Technology (IIT), 2015 11th International Conference on
Print_ISBN :
978-1-4673-8509-1
DOI :
10.1109/INNOVATIONS.2015.7381536