A Survey on Search Based Face Annotation Using Weakly Labelled Facial Images

Face recognition/detection presents a challenging problem in the field of image analysis and computer vision, and it is becoming more popular day by day because of its applications in various domain areas. Face annotation is one of the ways for recognizing face images. Auto face annotation is playing important role in many real-world applications. Face annotation task is part of face detection and recognition. Now a day’s research interest in mining weakly-labelled facial images on the internet for resolving research challenge in computer vision and image understanding is growing. A content-based image retrieval (CBIR) system needs users to query images by their low quality visual content. This process not only makes it difficult for users to formulate queries, but also can lead to unsatisfied results of image retrieval. To tackle this problem, Image annotation technique is used. The main aim of image annotation process is to automatically assign associate label to images, so image retrieving users are able to query images by labels and automatically detect human faces from a photo image and further name the faces with the corresponding human names. This paper provides various techniques or methods that are used for mining facial images from internet and annotating facial images. Keywords— Face annotation, Search based face annotation, unsupervised label refinement, web facial images, and