Image Captioning Using Python

Abstract

In the last few years, the problem of recognizing the objects and the context of the image has gained a rising interest. Image Captioning is a task of recognizing the context of the image and then generating a caption for it with proper grammar structure. Generating captions automatically will be helpful for visually impaired people to understand the picture better. To achieve this task a hybrid model is defined in this paper which uses CNN (Convolutional Neural Network) and LSTM (Long Short-Term Memory). The model will be trained using Flickr8K data sets with containing 8000 images and 5 captions for each image.