Alpha-numeric hand gesture recognition based on fusion of spatial feature modelling and temporal feature modelling

• Published in: Electronics letters Vol. 52; no. 20; pp. 1679 - 1681
• Main Authors: Yang, C, Ku, B, Han, D.K, Ko, H
• Format: Journal Article
• Language: English
• Published: The Institution of Engineering and Technology 29.09.2016
• Subjects: Algorithms; alphabet; Alphabets; alpha‐numeric hand gesture recognition; computer vision; conditional random fields; convolution neural network; Electronics; feature extraction; Fields (mathematics); gesture recognition; handwriting style; handwritten character recognition; Image and vision processing and display technology; individualistic styles; Mathematical models; neural nets; Neural networks; numeric characters; performance evaluation; performance improvement; public database; spatial feature modelling; temporal‐feature‐state modelling; total‐trajectory‐shape modelling; user interface; Vision; vision based gesture recognition; vision enabled smart devices; total-trajectory-shape modelling; handwritten character recognition; conditional random fields; vision enabled smart devices; vision based gesture recognition; performance evaluation; alphabet; temporal-feature-state modelling; performance improvement; user interface; public database; gesture recognition; feature extraction; computer vision; individualistic styles; numeric characters; alpha-numeric hand gesture recognition; handwriting style; neural nets; spatial feature modelling; convolution neural network
• ISSN: 0013-5194; 1350-911X; 1350-911X
• DOI: 10.1049/el.2016.0841

Alpha-numeric gesture refers to writing in air of alphabet and numeric characters. With prevalent usage of vision enabled smart devices, these gestures are considered as an alternative user interface. As each individual has a unique handwriting style, it has been observed that alpha-numeric gesturing also exhibits different individualistic styles, posing a challenge to the vision based gesture recognition. In this Letter, a simple but effective method of modelling alpha-numeric hand gestures by fusing temporal-feature-state modelling and total-trajectory-shape modelling is proposed. The proposed method employs a convolution neural network that represents total-trajectory-shapes, and combines it with conventional conditional random fields based temporal-feature-state modelling. The proposed algorithm is evaluated in public database of both alphabet and numeric hand gestures. Experimental results show a performance improvement of the proposed algorithm compared with the state-of-the art methods.