Real-Time Object Recognition using Region based Convolution Neural Network and Recursive Neural Network
R. Priyatharshini1, Aswath Ram. A.S2, R. Shyam Sundar3, G. Nethaji Nirmal4
1Dr. R. Priyatharshini*, Department of Information Technology, Easwari Engineering College, Ramapuram, Chennai, India.
2Aswath Ram. A.S, Department of Electrical and Electronics, Easwari Engineering College, Ramapuram, Chennai,. India.
3R. Shyam Sundar, Department of Information Technology, Easwari Engineering College, Ramapuram, Chennai, India.
4G. Nethaji Nirmal, Department of Information Technology, Easwari Engineering College, Ramapuram, Chennai. India.
Manuscript received on November 22, 2019. | Revised Manuscript received on November 28, 2019. | Manuscript published on November 30, 2019. | PP: 2813-2818 | Volume-8 Issue-4, November 2019. | Retrieval Number: D8326118419/2019©BEIESP | DOI: 10.35940/ijrte.D8326.118419
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© 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: The recognition of real-world objects demands the recognition and characterization of digital image samples. Automated methods for the detection and recognition of entity types have many significant commercial and industrial applications. While deep convolution neural networks (CNN) and machine learning (ML) concepts have contributed to the classification of globe items, they cannot fully scale the reliance of powerful GPUs to classify the key attributes of images. By using a Recurrent Neural Network (RNN) we tend to resolve the issue arisen in the previous systems. In particular, a hybrid approach using R-CNN and RNN has been proposed that improve the accuracy of object recognition and learn structured image attributes and begin image analysis. Specifically, we applied the transfer learning approach to pass the load parameters which were pre-trained on the Image web dataset to the RNN portion and follow a custom loss feature for the model to train and test more rapidly with precise weight parameters. Experimental results show that in comparison to CNN models like Resent, origin V3, etc., our proposed model achieved improved accuracy in categorizing universe pictures.
Keywords: Real Time Object Recognition, Convolution Neural Network, Recurrent Neural Network, Transfer Learning.
Scope of the Article: Pattern Recognition.