CapsNet Based Approach to Generate Image Annotation

Abstract

The people communicate through language, might be written or spoken. They often use this language to describe the visual world around them. Images, signs are another way of communication and understanding for the physically challenged people. The generation of descriptions from the image automatically in proper sentences is a difficult and challenging task, but it can help and have a great impact on visually impaired people for better understanding of the description of images on the web. Also, human can describe the image after having a quick knowledge about it. The important task of text summarization is selecting or generating an abstract for document. In problem of image captioning, for any image we would like to generate a caption which will describe various features of that image.