키넥트를 이용한 수화 인식 = Sign Language Recognition Using Kinect

다국어 초록 (Multilingual Abstract)

Sign language is a visual language expressed by facial expressions and body gestures, etc. The instances of signs vary in both motion and shape in three-dimensional (3D) space. In this research, 3D depth information is generated from Microsoft’s Kinect sensor and then a hierarchical conditional random field (CRF) that segments hand signs using 3D hand motions. A Boost Map embedding method is used to verify the hand shapes of the segmented signs. Experiments demonstrated that the proposed method could recognize signs at a rate of 90.4%.

참고문헌 (Reference)

1 Lahamy, H., "Towards real-time and rotation-invariant American Sign Language alphabet recognition using a range camera" 12 : 14416-14441, 2012

2 Yang, H.-D., "Simultaneous spotting of signs and fingerspellings based on hierarchical conditional random fields and boostmap embeddings" 43 : 2858-2870, 2010

3 Yang, H.-D., "Sign language spotting with a threshold model based on conditional random fields" 31 : 1264-1277, 2009

4 Yang, H.-D., "Sign language recognition with the Kinect sensor based on conditional random fields" 15 (15): 135-147, 2015

5 Chai, X., "Sign language recognition and translation with kinect" 22-26, 2013

6 Yang, H.-D., "Robust sign language recognition by combining manual and non-manual features based on conditional random field and support vector machine" 34 : 2051-2056, 2013

7 Ren, Z., "Robust part-based hand gesture recognition using kinect sensor" 15 : 1110-1120, 2013

8 Fischler, M.A., "Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography" 24 : 381-395, 1981

9 Zhang, S., "Low-Cost interactive whiteboard using the Kinect" 1-5, 2012

10 Palacios, J., "Human-computer interaction based on hand gestures using RGB-D sensors" 13 : 11842-11860, 2013

11 Moreira Almeida, S., "Extraction in Brazilian sign language recognition based on phonological structure and using RGB-D. sensors" 41 : 7259-7271, 2014

12 Athitsos, V., "BoostMap: An embedding method for efficient nearest neighbor retrieval" 30 (30): 89-104, 2008

13 Zafrulla, Z., "American sign language recognition with the kinect" 279-286, 2011

14 Chang, Y.J., "A Kinect-based system for physical rehabilitation:A pilot study for young adults with motor disabilities" 32 : 2566-2570, 2011