Survey on Algorithm for Image Ranking Using Learning and Training

Computer Engineering

With the prevalence of social networking and digital photography in recent years, number of images has been posted to various photos sharing web site. One of the important research topic is image annotation due to its application is image matching and retrieval. Multi-label learning is useful in visual object recognition when several objects are present in an image. The important thing of this approach is required large number of training images with clean and complete annotation to learn a reliable Model of tag prediction. system under the experiment solve the problem of image annotation using image tag ranking method and also address problem of noisy and incomplete tags by using that is crowdsourcing. We perform extensive experiments on image tagging data sets. In all empirical results, our tag ranking method shows better tagging results than the state-of-the-art approaches.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.