A Deep Learning for the Generation of Textual Story Corresponding to a Sequence of Images
B Venkat Raman1, Nagaratna P Hegde2, Nenavath Venkatesh Naik3, Allu Siva Kishore Reddy4

1B Venkat Raman, Research Scholar, Assistant Professor, Department of CSE, Osmania University, Hyderabad and RGUKT, Basar (Telangana), India.
2Nagaratna P Hegde, Professor, Vasavi College of Engineering, Hyderabad (Telangana), India.
3Nenavath Venkatesh Naik, UG Scholar, Department of Computer Science & Engineering, RGUKT Basar (Telangana), India.
4Allu Siva Kishore Reddy, UG Scholar, Department of Computer Science & Engineering, RGUKT Basar (Telangana), India.
Manuscript received on 15 October 2019 | Revised Manuscript received on 24 October 2019 | Manuscript Published on 02 November 2019 | PP: 2419-2422 | Volume-8 Issue-2S11 September 2019 | Retrieval Number: B12790982S1119/2019©BEIESP | DOI: 10.35940/ijrte.B1279.0982S1119
Open Access | Editorial and Publishing 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: Generating a short story for a sequence of images is much more interesting than generating a single line textual description for an image. Story generation involves relating the meaning of the previous image and the current image and continuing this through out the sequence of images. This can be helpful for better understanding of the situation. In this paper we present our idea of generating story using a CNN model which is pre trained on MSCOCO dataset that can detect objects and concepts of language modelling and NLP text pre-processing techniques . We used a custom stories dataset in which we manually labelled every sentence in every story. Number of sentences in the generated story is equal to the number of images. The results are quite accurate in many cases for a small custom stories dataset and the performance is expected to increase with a bigger dataset.
Keywords: Image Classification, Convolution Neural Network, Long Short Term Memory, Language Modelling, Text Pre-Processing.
Scope of the Article: Deep Learning