Open AccessGray Scale Image Captioning Using CNN and LSTM
Author(s) -
V. Varshith Reddy,
Y. Shiva Krishna,
U. Varun Kumar Reddy,
Shubhangi Mahule
Publication year - 2022
Publication title -
international journal for research in applied science and engineering technology
Language(s) - English
Resource type - Journals
ISSN - 2321-9653
DOI - 10.22214/ijraset.2022.41589
Subject(s) - closed captioning , computer science , convolutional neural network , artificial intelligence , python (programming language) , recurrent neural network , deep learning , image (mathematics) , grayscale , computer vision , artificial neural network , pattern recognition (psychology) , operating system
The objective of the project is to generate caption of an image. The process of generating a description of an image is called image captioning. It requires recognizing the important objects, their attributes, and the relationships among the objects in an image. With the advancement in Deep learning techniques and availability of huge datasets and computer power, we can build models that can generate captions for an image. This is what we have implemented in this Python based project where we have used the deep learning techniques of CNN (Convolutional Neural Networks) and LSTM (Long short term memory) which is a type of RNN (Recurrent Neural Network) together so that using computer vision computer can recognize the context of an image and display it in natural language like English. Gray Scale Image captioning can give captions for both monochrome and color images. Keywords: Image, Caption, Convolutional Neural Networks, Long Short Term Memory, Recurrent Neural Network