Abstract
The social networking sites, such as flicker allows users to upload images and annotate it with descriptive labels known as tags. Personalized image searching is the way to searching images according to intension of users and that personalized image result is relevant to the individual user. Personalized web search takes an advantage of information about an individual that tagging to an image for identifying the most relevant image result for that person. The main challenge for personalization lies in collecting user profiles which describes information about the user. The user preferences and fired query are used to obtained relevant image result. The proposed system contains three components: A Ranking based multi-correlation tensor factorization (RMTF) model is proposed to perform annotation prediction, which is considered as user’s preference according to annotating or tagging to an image. Corpus is used to analyze users, their annotating images and users tags for each image to find users specific topics .The proposed algorithm perform topic modeling which is used to generate user specific topics. The single word query selection is used for searching relevant image result. The query mapping or query relevance and topic sensitive user preferences (TSUP) are integrated into final ranked result of relevant images.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
