Abstract
In this paper, a comparison between feature extraction methods (Radon Cosine Method, Canny Contour Method, Fourier Transform, SIFT descriptor, and Hough Lines Method) and Convolutional Neural Networks (proposed CNN and pre-trained AlexNet) is presented. For the evaluation of these methods, depth maps were used. The tested data were obtained by Microsoft Kinect camera (IR depth sensor). The feature vectors were classified by the Support Vector Machine (SVM). The confusion matrix for the evaluation of experimental results was used. The row of confusion matrix represents target class of tested data and the column represents predicted class. From the experimental results, it is evident that the best results were achieved by proposed CNN (97.4%). On the other hand, the pre-trained AlexNet scored 93.7%.
Highlights
Hand gestures can be seen from multiple points of view
The overall time of prediction is the last measured time. This parameter represents the time needed for feature vector extraction and prediction of Support Vector Machines (SVM) model onto that vector
We performed a comparison between Convolutional Neural Networks ( AlexNet and proposed CNN) and feature extraction methods, such as Radon Cosine Method, Canny Contour Method, Fourier Transform Method, Scale-Invariant Feature Transform (SIFT) descriptor and Hough Lines Method
Summary
Hand gestures can be seen from multiple points of view. They can be represented by the motion of the hand. They can be represented by the shape of the hand (position of fingers). The shape of the hand is determined by the position of fingertips relative to the palm. One finger straight up and others folded into fist is a simple gesture for number one. Two straight fingers represent number two, etc. Orientation of hand in picture is detected by calculating simple ration between width and height of hand region. Centroid and fingertip position using Euclidean distance is calculated. The comparison of feature extraction methods and deep learning framework for depth map recognition is described in [1] and [2]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
