Open AccessImage Caption Generator Using Neural Networks
Author(s) -
Sudhish Kumar Shukla,
Saurabh Dubey,
Aniket Kumar Pandey,
Vineet Mishra,
Mayank Awasthi,
Vinay Bhardwaj
Publication year - 2021
Publication title -
international journal of scientific research in computer science, engineering and information technology
Language(s) - English
Resource type - Journals
ISSN - 2456-3307
DOI - 10.32628/cseit21736
Subject(s) - closed captioning , computer science , convolutional neural network , focus (optics) , artificial intelligence , generator (circuit theory) , image (mathematics) , recurrent neural network , computer vision , deep learning , process (computing) , long short term memory , artificial neural network , speech recognition , power (physics) , physics , quantum mechanics , optics , operating system
In this paper, we focus on one of the visual recognition facets of computer vision, i.e. imagecaptioning. This model’s goal is to come up with captions for an image. Using deep learning techniques,image captioning aims to generate captions for an image automatically. Initially, a Convolutional NeuralNetwork is used to detect the objects in the image (InceptionV3). Recurrent Neural Networks (RNN) andLong Short Term Memory (LSTM) with attention mechanism are used to generate a syntactically andsemantically correct caption for the image based on the detected objects. In our project, we're workingwith a traffic sign dataset that has been captioned using the process described above. This model isextremely useful for visually impaired people who need to cross roads safely.