Computer vision has become omnipresent in our society, with uses in several fields. In this project, we specialize in one among the visually imparting recognition of images in computer vision, that is image captioning. The problem of generating language descriptions for images is still considered a problem which needs a resolution and this has been studied more regressively within the field of videos. From past few years more emphasis has been given to still images and their descriptions with human understandable natural language. The task of detecting scenes and object has become easier due studies that have taken place in last few years. The main motive of our project is to train convolutional neural networks and applying various hyper parameters with huge datasets of images like Flicker 8k and Resnet, and combining the results of these images and their classifiers with a recurrent neural and obtain the desired caption for the image. In this paper we would be presenting the detailed architecture of the image captioning model.

Keywords : Computer Vision, Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), Xception, Flicker 8K, LSTM, Preprocessing.