A novel approach to posture recognition of ballet dance

Author

Banerjee, Adrish ; Saha, Simanto ; Basu, Sreetama ; Konar, Amit ; Janarthanan, R.

Author_Institution

Comput. Sci. & Eng. Dept., Jadavpur Univ., Kolkata, India

fYear

2014

fDate

6-7 Jan. 2014

Firstpage

1

Lastpage

5

Abstract

The objective of this work is to recognize 17 fundamental ballet postures using a single camera. The proposed 7-stage algorithm first performs skin color segmentation on raw images and then finds minimized skeletons which are further approximated by straight lines using chain code and sampling. From the stick figures, the angles the significant lines make with the abscissa in dominant quadrants are determined. Finally, the unknown posture is recognized as the one of the 17 forms with which it holds maximum similarity as calculated by a similarity operator with average 88.9% accuracy.

Keywords

approximation theory; gesture recognition; humanities; image colour analysis; image sampling; image segmentation; image sensors; image thinning; pose estimation; 7-stage skin color segmentation algorithm; ballet dance posture recognition; chain code; chain sampling; maximum similarity calculation; similarity operator; single camera; skeleton minimization finding; straight line approximation; Image segmentation; Indexes; Motion segmentation; Skeleton; Skin; chain code; sampling; skeleton; skin color segmentation; straight line approximation;

fLanguage

English

Publisher

ieee

Conference_Titel

Electronics, Computing and Communication Technologies (IEEE CONECCT), 2014 IEEE International Conference on

Conference_Location

Bangalore

Print_ISBN

978-1-4799-2318-2

Type

conf

DOI

10.1109/CONECCT.2014.6740183

Filename

6740183