Hand posture recognition using the intrinsic dimension

Author

Oprisescu, Serban ; Ciuc, Mihai ; Vasile, Irina

Author_Institution

Image Process. & Anal. Lab., Univ. Politeh. of Bucuresti, Bucharest, Romania

fYear

2014

fDate

22-24 May 2014

Firstpage

974

Lastpage

979

Abstract

This paper presents a hand posture recognition algorithm based on the intrinsic dimension (ID). Hand segmentation is reliable with cluttered background due to the use of the time-of-flight (ToF) range camera. The hand pose recognition is performed using an image indexing technique with a reference database of 360 images. The database and the query images consist of nine types of hand postures. The similarity measure used for finding the best match with the query image is the correlation between the 1D representations of the 2D ID hand contours. The average recognition rate is above 96%, which is satisfactory.

Keywords

image matching; image representation; image segmentation; object recognition; pose estimation; 1D representation; 2D ID hand contours; ToF range camera; cluttered background; hand pose recognition; hand posture recognition algorithm; hand segmentation; image indexing technique; intrinsic dimension; query image matching; similarity measure; time-of-flight range camera; Cameras; Correlation; Databases; Estimation; Gesture recognition; Image recognition; Vectors;

fLanguage

English

Publisher

ieee

Conference_Titel

Optimization of Electrical and Electronic Equipment (OPTIM), 2014 International Conference on

Conference_Location

Bran

Type

conf

DOI

10.1109/OPTIM.2014.6850920

Filename

6850920