Handwritten Character Recognition Using Depth Information by Kinect

Abstract:

t is quite constrained for us to use some other input devices to communicate with computers. In this paper, we integrate human-computer interaction technologies with handwritten Chinese character recognition strategies using depth image information provided by Kinect sensor to realize an unconstrained handwritten character recognition system, which only uses our hand as input device. We predefine several hand gestures as instructions, and for the recognition of these hand gestures, we calculate the contour and fingertips of the hand used for writing using depth image taken by Kinect. By mimicking the functionalities of the computer mouse only using our hands, we can write freely in the air and get the original character image. After Gaussian blurring and normalization, we adopt some classic handwritten character recognition schemes to accomplish the recognition task. Experiments show that the system gives a good result.

• Periodical: Applied Mechanics and Materials (Volumes 333-335)
• Pages: 883-887
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.333-335.883
• Online since: July 2013
• Authors: Yong Xia, Zhi Bo Yang, Kuan Quan Wang
• Keywords: Hand Gesture Recognition, Handwritten Character Recognition, Human-Computer Interaction (HCI), Kinect Sensor

References

[1] CHEN Q.: Real-Time Vision-Based Hand Tracking and Gesture Recognition, PhD thesis, (2008).

[2] Raheja, Jagdish Lal: Tracking of Fingertips and Centers of Palm Using KINECT, the Third International Conference on Computational Intelligence, Modelling and Simulation, 2011, pp.249-252.

DOI: 10.1109/cimsim.2011.51

[3] Thiago R. Trigo and Sergio Roberto M. Pellegrino.: An Analysis of Features for Hand-Gesture Classification, 17th International Conference on Systems, Signals and Image Processing, 2010, pp.412-415.

[4] Cheng-Lin Liu, Katsumi Marukawa.: Pseudo two-dimensional shape normalization methods for handwritten Chinese character recognition, Pattern Recognition, 2005, vol. 38, pp.2242-2255.

DOI: 10.1016/j.patcog.2005.04.019

[5] Cheng-Lin Liu.: Normalization-Cooperated Gradient Feature Extraction for Handwritten Character Recognition, IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007, Vol. 29, No. 8, pp.1465-1469.

DOI: 10.1109/tpami.2007.1090

[6] Fumitaka Kimura, Kenji Takashina, Shinji Tsuruoka, Yasuji Miyake.: Modified Quadratic Discriminant Functions and the Application to Chinese Character Recognition, Int. Workshop on Neural Networks and Learning in Document Analysis and Recognition, Seoul, 2005, pp.149-153.

DOI: 10.1109/tpami.1987.4767881