Master of Science in Computer Science


Department of Computer Science

Faculty / School

Faculty of Computer Sciences (FCS)

Date of Submission



Dr. Muhammad Sarim, Visiting Faculty, Department of Computer Science

Document type

MSCS Survey Report


In recent years, researchers have been working to explore the association between words and pictures for a number of tasks that includes facial recognition in newspaper photos with labelled captions, finding relationships between tags and image components and to identify attributes after object recognition in images. Generating descriptions for pictures using English sentences or natural language is quite a challenging task for Computer Vision practitioners. It demands expertise in both the fields of Image Processing and Natural Language Processing. This research basically focuses on different models that have been used for Image processing and creating captions using natural English language sentences. We have reviewed the models developed in recent years that has advanced the object recognition and classification process resulting in improved accuracy for the task of Image Captioning.

The full text of this document is only accessible to authorized users.