Study and Development of Image Caption Generation using Various Encoders for Different Image Categories

Abstract

Images can act as the source of information or way of communication. Captioning an image by machines in a manner such that it conveys the true meaning is considered the most difficult task. It is indeed a process of deep analysis and most researched area. This paper presents a comparative analysis of different deep learning models such as Inception V3, Resnet50 and VGG16 based on a novel image captioning methodology applied on different picture categories. The hybrid approach is developed to get high BLEU score for each input images. The data set generation, implementation of hybrid approach, and the challenges along with the future work are discussed.