Image Captioning using CNN and RNN

Ever thought how a machine looks at the things? Is it the same as we do? Or is there a different perception? Machine reading the details of an image is made possible using Deep Learning techniques like the Neural Networks, Natural Language Processing and number of available relevant datasets. This article is going to discuss about one such model which is capable of generating captions to the images provided. The training of the model is done with Flickr_8k dataset which contains about 8091 images and their text stored in another similar dataset. LSTM (Long Short-Term Memory), one of the RNN types and Convolutional Neural Networks are used to train and evaluate the model.