• R. Shreya
• Dr. S. Ravi
• R. Jayasri

Accurate Human Activity Recognition (HAR) is very important activity in surveillance system and sports areas. Action classification is crucial part in HAR. Support vector machine (SVM) is one of the most powerful and robust algorithm in machine learning and it is commonly used for problems like classification, regression and pattern recognition. By separating the distinct class with a maximum possible wide gap, SVM tries to predict the respective class given a set of input data. Because of its higher prediction capabilities SVM has gained increasing attention in the remote sensing, image processing, robotics, pattern recognition and many others community. In this paper, the study and analysis is provided on human action recognition based on support vector machines by analyzing the advantages, disadvantages and accuracy. This survey will provide helping hand to the budding researchers who are started doing research in this field and that is the primary aim of this paper.

Human Action Recognition, Support Vector Machines, depth motion map

"Human Action Recognition based on Support Vector Machines", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 4, page no.158-162, April-2019, Available :http://www.jetir.org/papers/JETIR1904F30.pdf

"Human Action Recognition based on Support Vector Machines", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 4, page no. pp158-162, April-2019, Available at : http://www.jetir.org/papers/JETIR1904F30.pdf