Detection and Recognition of Object for Image Captioning

Abstract

As one of the most intelligent beings on the planet, we are equipped with the most powerful visual and language system as it is easy for us to extract visual information from a given image and transform it into proper linguistic description. Image Caption Generator deals with generating captions for a given image. The capturing mechanism involves a tiring task that collaborates both computer vision and image processing. The mechanism must detect and establish relationships between objects, people, and animals. The aim of this paper is to detect, recognize and generate worthwhile captions for a given image. We use transfer learning CNN on sentences, and extract image representation with Neural Networks.