A Survey on Automatic Image Annotation Methods

In the modern world a huge amount of data is being produced every second and a considerable percentage of them are images that need to be processed and analyzed. One of the critical challenges in this aspect is image recovery. The process of image recovery should be done automatically by the machines which is the process of recognition of images concepts and assigning homological labels to them. In order to discover the hidden concepts in the images, one should achieve high level concepts using the low-level features, which is a difficult task. A variety of techniques are proposed to solve this problem that usually use combination of different algorithms. In this paper we review and compare various popular and modern image annotation techniques.