A Dynamic Multi Label Image Classification based on Recurrent Neural Networks
Kalyanaraman B1, Kaushik G Viswanath2, M Balasaran3, Ragul SK4, Bryan John Samuel5

1Mr. Kalyanaraman B, Assistant professor of Information technology in SRM IST, Chennai, Tamil Nadu, India.
2M Balasaran, department of Information Technology, SRM IST, Chennai, Tamil Nadu, India.
3Kaushik G Vishwanath, department of Information Technology, SRM IST,Chennai, Tamil Nadu, India.
4Ragul SK,department of Information Technology,SRM IST, Chennai, Tamil Nadu, India.
5Bryan John Samuel,department of Information Technology, SRM IST, Chennai, Tamil Nadu, India.
Manuscript received on February 27, 2020. | Revised Manuscript received on March 14, 2020. | Manuscript published on March 30, 2020. | PP: 5093-5096 | Volume-8 Issue-6, March 2020. | Retrieval Number: F9817038620/2020©BEIESP | DOI: 10.35940/ijrte.F9817.038620

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: The traditional technique used for image recognition has complexity in the construction of algorithm and the training speed for the system to analyze algorithm is also too high so, the computation of the algorithm becomes very difficult in order to overcome this lack of computation. The proposed system is very efficient in both training as well as the computation speed required for the image recognition. Since, the proposed system uses the traditional LSTM algorithm which is one of the backbone factors of the RNN technique as it predicts the input on the basis of sequential analysis as it uses tanh function in order to remove the negative values of the matrix and it also predicts and removes the error in the input with the use of differential formulas in order to formulate the outcome desired for the image to be recognized. Because of this sequential analysis of the data increases the future scope of image recognition in the field of deep learning, and also because of its efficient use of the algorithm in comparison with the existing algorithm like ANN, CNN.
Keywords: CNN (Convolution Neural Networks), RNN (Recurrent Neural Networks), HSI (Hyper Spectral Images).
Scope of the Article: Classification.