Special Issue Article
Study On Tag Refinement And Tag Completion For Effective Image Retrieval
Online sharing of images is increasingly becoming popular, resulting in the availability of vast collections of user contributed images that have been annotated with user supplied tags. Many social image search engines are based on keyword/tag matching. It is because tag-based image retrieval (TBIR) is not only efficient but also effective. The performance of TBIR is highly dependent on the availability and quality of manual tags. Since many users tend to choose general and ambiguous tags in order to minimize their efforts in choosing appropriate tags, they are usually incomplete and insufficient to describe the whole semantic content of corresponding images resulting in unsatisfactory performances in tag related applications. This is a study on various techniques which are used to complete the missing tags and correct the noisy tags for given images thereby improving the retrieval performance.