Date of Publication :23rd March 2023

Abstract: The process of creating descriptions for what’s happening in an image is known as image captioning. Image captioning is used to provide explanations that provide context for the pictures.The analysis of huge quantity of unidentified images, the detection of unknown patterns for applications of machine learning used to drive autonomous cars, and the creation of soft- ware that aids the blind are just a few examples of the many areas where image captioning is incredibly beneficial. Deep Learning Models can be used for this image captioning.Development in Deep learning field and NLP have made it simpler than ever to create descriptions for the provided photos. Neural networks will be used in this paper’s picture captioning.In order to access picture features, RESNET is utilised as an encoder, while Long Short Term Memory(LSTM)as decoder. Using built-in language and the image features, LSTM creates captions for the images.

Reference :