Abstract: With the rapid advances in the field of multimedia technologies the collection of numerous digital images are also on verge of increase. This has led to the research in the field of image annotation. Auto face annotation is playing an important role in many real-world applications. Face annotation task is part of face detection and recognition. Various pictures are uploaded on social sites daily but many of them are tagged with false name or improperly. It then becomes problematic in recognizing a person properly. Automatic image annotation is the process of automatically assigning semantic labels to images. This paper presents the survey on different approaches for auto face annotation and image based annotation retrieval and also it aims to cover the latent space and generative approaches for auto face annotation and includes a proposed methodology in short.

Keywords: Face Annotation, Search based face annotation clustering based approximation, unsupervised label refinement.