Modified CRF algorithm for dynamic hand gesture recognition

Author

Liling Ma ; Jing Zhang ; Junzheng Wang

Author_Institution

Beijing Inst. of Technol., Beijing, China

fYear

2014

fDate

28-30 July 2014

Firstpage

4763

Lastpage

4767

Abstract

In this paper, a modified CRF algorithm is proposed for recognition of vision-based dynamic hand gestures. This algorithm abandons the condition necessary for Hidden Markov Models that the action sequences must be independent. And dynamic hand gestures are classified by some most representative segments (MRSs) rather than the full gestures themselves. First, the Longest Common Sequence (LCS) is employed to extract the most representative segments from dynamic gestures which are then used to train Conditional Random Fields (CRF). In a recognition stage, MRS of the unclassified trajectory is sent to CRF. Experiment results show that this algorithm (defined as MRS-CRF) has significant advantages over HMMs in accuracy and CRF itself in simplification.

Keywords

computer vision; feature extraction; gesture recognition; hidden Markov models; image classification; image sequences; HMM; LCS; MRS-CRF algorithm; action sequences; conditional random field training; dynamic hand gesture classification; hidden Markov models; longest common sequence; modified CRF algorithm; most-representative segment extraction; unclassified gesture trajectory; vision-based dynamic hand gesture recognition; Accuracy; Gesture recognition; Heuristic algorithms; Hidden Markov models; Tracking; Training; Trajectory; CRF; Dynamic hand gestures; Most representative segment (MRS);

fLanguage

English

Publisher

ieee

Conference_Titel

Control Conference (CCC), 2014 33rd Chinese

Conference_Location

Nanjing

Type

conf

DOI

10.1109/ChiCC.2014.6895744

Filename

6895744