Real Time Image Captaioning
Asha G1, R. Hema Sumanth2, A. China Venkat Chowdary3, A. Shashank4, T. Sravan5
1Asha G*, Master in Computer Science and Engineering from VTU Belgaum, Karnataka.
2R. Hema Sumanth, Master in Computer Science and Engineering from VTU Belgaum, Karnataka.
3A. China Venkat Chowdary, Pursuing Final Year B. Tech Degree in Computer Science and Engineering from GITAM University, Bengaluru.
4A. Shashank, Pursuing Final Year B. Tech Degree in Computer Science and Engineering from GITAM University, Bengaluru.
5T. Sravan, Pursuing Final year B. Tech Degree in Computer Science and Engineering from GITAM University, Bengaluru.
Manuscript received on March 15, 2020. | Revised Manuscript received on March 28, 2020. | Manuscript published on April 10, 2020. | PP: 1707-1709 | Volume-9 Issue-6, April 2020. | Retrieval Number: F4566049620/2020©BEIESP | DOI: 10.35940/ijitee.F4566.049620
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: Image caption generator means it will generate a description for the images. It will predict what is happing in the images. We make our model using a hybrid CNN-RNN model in which in the CNN part of the model we use inception model for transfer learning and RNN is majorly used for language modeling. We use Flickr8k Dataset for training and testing the model. We use LSTM model in RNN to avoid the problem of vanishing or exploding gradient in the training phase.
Keywords: CNN-RNN Architecture, LSTM, SOFTMAX, Image caption generator.
Scope of the Article: Computer Architecture and VLSI