Composite Feature Vector Assisted Human Action Recognition through Supervised Learning
K. Ruben Raju1, Yogesh Kumar Sharma2, Birru Devender3
1K. Ruben Raju, Research Scholar, Dept. of Computer Science Engineering, JJT University, Rajasthan India.
2Dr. Yogesh Kumar Sharma, Head & Associate Professor, Dept. of Computer Science Engineering, JJT University, Rajasthan India.
3Dr. Birru Devender, Associate Professor, Dept. of Computer Science Engineering, Holy Mary Institute of Technology & Science, Hyderabad, India.
Manuscript received on February 10, 2020. | Revised Manuscript received on February 20, 2020. | Manuscript published on March 30, 2020. | PP: 1556-1566 | Volume-8 Issue-6, March 2020. | Retrieval Number: F7337038620/2020©BEIESP | DOI: 10.35940/ijrte.F7337.038620
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Human Action Recognition is a key research direction and also a trending topic in several fields like machine learning, computer vision and other fields. The main objective of this research is to recognize the human action in image of video. However, the existing approaches have many limitations like low recognition accuracy and non-robustness. Hence, this paper focused to develop a novel and robust Human Action Recognition framework. In this framework, we proposed a new feature extraction technique based on the Gabor Transform and Dual Tree Complex Wavelet Transform. These two feature extraction techniques helps in the extraction of perfect discriminative features by which the actions present in the image or video are correctly recognized. Later, the proposed framework accomplished the Support Vector Machine algorithm as a classifier. Simulation experiments are conducted over two standard datasets such as KTH and Weizmann. Experimental results reveal that the proposed framework achieves better performance compared to state-of-art recognition methods.
Keywords: Action Recognition, Gabor, Wavelet, KTH, Weizmann, Accuracy.
Scope of the Article: Deep learning.