Mobile Computing, Applications, and Services. 9th International Conference, MobiCASE 2018, Osaka, Japan, February 28 – March 2, 2018, Proceedings

Research Article

GERMIC: Application of Gesture Recognition Model with Interactive Correction to Manual Grading Tasks

Download
206 downloads
  • @INPROCEEDINGS{10.1007/978-3-319-90740-6_6,
        author={Kohei Yamamoto and Fumiya Kan and Kazuya Murao and Masahiro Mochizuki and Nobuhiko Nishio},
        title={GERMIC: Application of Gesture Recognition Model with Interactive Correction to Manual Grading Tasks},
        proceedings={Mobile Computing, Applications, and Services. 9th International Conference, MobiCASE 2018,  Osaka, Japan, February 28 -- March 2, 2018, Proceedings},
        proceedings_a={MOBICASE},
        year={2018},
        month={5},
        keywords={Handwriting recognition Recognition error correction},
        doi={10.1007/978-3-319-90740-6_6}
    }
    
  • Kohei Yamamoto
    Fumiya Kan
    Kazuya Murao
    Masahiro Mochizuki
    Nobuhiko Nishio
    Year: 2018
    GERMIC: Application of Gesture Recognition Model with Interactive Correction to Manual Grading Tasks
    MOBICASE
    Springer
    DOI: 10.1007/978-3-319-90740-6_6
Kohei Yamamoto1,*, Fumiya Kan1,*, Kazuya Murao1,*, Masahiro Mochizuki1,*, Nobuhiko Nishio1,*
  • 1: Ritsumeikan University
*Contact email: moi@ubi.cs.ritsumei.ac.jp, fumiya@ubi.cs.ritsumei.ac.jp, murao@cs.ritsumei.ac.jp, moma@ubi.cs.ritsumei.ac.jp, nishio@cs.ritsumei.ac.jp

Abstract

Gesture-based recognition is one of the most intuitive methods for inputting information and is not subject to cumbersome operations. Recognition is performed on human’s consecutive motion without reference to retrial or alternation by user. We propose a gesture recognition model with a mechanism for correcting recognition errors that operates interactively and is practical. We applied the model to a setting involving a manual grading task in order to verify its effectiveness. Our system, named GERMIC, consists of two major modules, namely, handwritten recognition and interactive correction. Recognition is materialized with image feature extraction and convolutional neural network. A mechanism for interactive correction is called on-demand by a user-based trigger. GERMIC monitors, track, and stores information on the user’s grading task and generates output based on the recognition information collected. In contrast to conventional grading done manually, GERMIC significantly shortens the total time for completing the task by 24.7% and demonstrates the effectiveness of the model with interactive correction in two real world user environments.