Publications:Hand Detection and Gesture Recognition Using Symmetric Patterns

From ISLAB/CAISR
Revision as of 00:53, 26 October 2016 by Slawek (Talk | contribs)

(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)

Do not edit this section

Keep all hand-made modifications below

Title Hand Detection and Gesture Recognition Using Symmetric Patterns
Author Hassan Mashad Nemati and Yuantao Fan and Fernando Alonso-Fernandez
Year 2016
PublicationType Journal Paper
Journal Studies in Computational Intelligence
HostPublication
Conference 8th Asian Conference on Intelligent Information and Database Systems (ACIIDS 2016), Da Nang, Vietnam, 14–16 March, 2016
DOI http://dx.doi.org/10.1007/978-3-319-31277-4_32
Diva url http://hh.diva-portal.org/smash/record.jsf?searchId=1&pid=diva2:914141
Abstract Hand detection and gesture recognition is one of the challenging issues in human-robot interaction. In this paper we proposed a novel method to detect human hands and recognize gestures from video stream by utilizing a family of symmetric patterns: log-spiral codes. In this case, several log-family spirals mounted on a hand glove were extracted and utilized for positioning the palm and fingers. The proposed method can be applied in real time and even on a low quality camera stream. The experiments are implemented in different conditions to evaluatethe illumination, scale, and rotation invariance of the proposed method. The results show that using the proposed technique we can have a precise and reliable detection and tracking of the hand and fingers with accuracy about 98 %.