Abstract: Image captioning aims to automatically generate a sentence description for an image. Our project model will take an image as input and generate an English sentence as output, describing the contents of the image. It has attractedmuch research attention in cognitive computing in the recent years. The task is rather complex, as the concepts of both computer vision andnatural language processing domains are combined together. We have developed a model using the concepts of a Convolutional Neural Network (CNN) and LongShort Term Memory (LSTM) model and build aworking model of Image caption generator by implementing CNN with LSTM.The CNN works as encoder to extract features from images and LSTM works as decoder to generates words describing image. After the captiongeneration phase, weuse BLEU Scoresto evaluate the efficiency of our model. Thus, our system helpsthe user to get descriptive caption for the given input image.
Read full abstract