Challenges & approaches in multi-label image annotation

Multi-label image annotation has received significant attention in the research community over the past few years. Multi-label automatic image annotation assigns keywords to the image based on low level features automatically. In this paper, we present an extensive survey on the research work carried out in the area of multi-label image annotation by using statistical and machine learning approaches for natural images. Multi-label research work carried out in medical and spatial domain are also specified. Finally, paper is concluded towards challenges in multi-label image annotation for future research.