Image Captioning- Bangladesh’s Heritage Perspective using Deep Learning

Abstract

Image captioning aims to make a textual short explanation of a given image. Despite the fact that it looks to be a straightforward task, for people, it is difficult for computers since it involves the ability to analyze the image (computer vision) and provide a human-like description (natural language understanding). Encoder Decoder architectures have recently reached advanced outcomes in the form of picture captioning. In the three model datasets: Flickr_data, Flickr8k_token.txt, we provide our model with the training with which it can create captions from the images which relate to Bangladeshi culture, tradition and historical places. Bangladesh is enriched with great culture; many heritage pictures and cultural programmes attract travelers to visit our country. We try to relate our culture, place, food, and many more with machine learning to reach them with appropriate captioning and spread knowledge a little more about our culture through pictures. Our image captioning tool can be very helpful for travel lovers who want to know more about Bangladesh.