Visitors: 1383

  MAZEDAN DIGITAL LIBRARY    

  JOURNAL MANAGEMENT SYSTEM

MDL
JMS  
MAZEDAN DIGITAL LIBRARY

Implementation of Template Matching Algorithm for Hand Gesture Recognition

JOURNAL:MAZEDAN COMPUTER ENGINEERING TRANSACTIONS

Download pdf
# Authors First Online DOI Downloads Citations
1. Pooja S. Korde*, Sneha U. Bohra 25 Jun 2021 MCET0201005 5 0
Abstract

Humans can quickly identify body and sign language, thanks to a combination of eyesight and synaptic connections. Some challenges must be overcome before this talent can be replicated in computers, such as how to segregate items of interest in photographs and which image capture technology and classification approach are most suited, among others. Normal people do not comprehend deaf people's signs because they do not know what they signify. The solution presented here addresses this problem. This technology collects various hand gestures using a camera. Following that, the image is processed using a variety of approaches. Hand Gesture Recognition has been successfully substituted for Speech Recognition using the proposed system. Methodologies for recognizing gestures are typically classified into two categories: static and dynamic. The advantage of this strategy is the lower computing cost. Static gestures only need the analysis of a single picture at the input of the classifier. Image sequence processing and more complicated gesture detection algorithms are required for dynamic gestures. Finally, OpenCV, which will act as the system's Eye, capturing and processing Real-time Hand Gestures and predicting their outcomes, and finally, The Deep Learning Techniques which is known as Convolutional Neural Network that has been used to aid with Image Recognition by transforming photos into a matrix that the model can understand and making it Classifier ready. The concepts employed include Deep Learning, Convolutional Neural Networks, Tensor Flow, openCV and Python Modules. The hand motions are recorded by a camera and then analyzed.

Keywords

TensorFlow, Convolutional Neural Network, Machine Learning, Image Recognition, Sign Language

References

  1. [1]    R. Issac and A. Narayanan, 2018. VPA stands for Virtual Personal Assistant. Volume 8 (Issue 10, October) of the Journal of Network Communications and Emerging Technologies (JNCET) (2018).

    [2]    C. Lee, G. Park and J. Kim, “Real-Time Recognition System of KSL based on Elementary Components,” Journal of the Korea Institute of Telematics and Electronics, vol. 35, no.6, pp.76-87, 1998. http://ezinearticles.com/?A-History-of-BritishSign-Language Id=920959 (Accessed on 10 Feb 2011)

    [3]    E. Stergiopoulou and N. Papamarkos, “A New Technique for Hand Gesture Recognition,” Proc. of the IEEE International Conference on Image Processing, 2006, pp. 2657-2660.

    [4]    Zeshan, U., Vasishta, M. M., and Sethna, M., “Implementation of Indian Sign Language in Educational Settings”, Asia Pacific Disability Rehabilitation Journal, Pages 16-40, No. 1, 2005.

    [5]    http://www.nad.org/issues/american-signlanguage/position-statement-americansign language-2008 (Accessed on 10 Feb 2011)