Abstract

Many of the search engines deployed on the web retrieve images without analyzing their content, simply by matching their user queries against their collocated textual information.This limits the applicability of search engines, a great deal of work has focused on the development of generating descriptive words for an image automatically. Images are automatically captioned in two stages :Content selection and surface realization.Content selection suggests keywords for the image using image annotation model.whereas, surface realization technique uses extractive and abstractive methods to generate caption.the approach is to analyze the performance of captioned images using phrases rather than words.

Authors and Affiliations