Automatically creating the description or caption of an image using any language is a verychallenging task. It requires both methods from computer vision to understand the content ofthe image and a language model from the field of natural language processing to turn theunderstandingof theimageinto words in the right order. In Artificial Intelligence (AI), the contents of an image are generated automatically whichinvolves computer vision and NLP (Natural Language Processing). It depends on computervision and machine translation. Our project aims to implement an Image caption generatorthat responds to the user to get the captions for a provided image. This model is used togenerate natural sentences which eventually describes the image. This model consists ofConvolutional Neural Network (CNN) as well as LSTM. TheCNN is used for feature extraction from image and LSTM is used for sentence generation. Themodel is trained in such a way that if input image is given to model it generates captionswhich nearly describes the image. The accuracy of model and smoothness or command of language model learns from image descriptions is tested on different datasets. We can use this in image indexing, for visually impaired persons, for social media, and several othernaturallanguageprocessing applications. The basic idea behind this is that users will get automated captions when we use or implementit on social media oron anyapplications.

Automatically creating the description or caption of an image using any language is a verychallenging task.