Volume 10 Issue 3 - May 2018

  • 1. A social re-ranking system for tag-based image search with image’s relevance and diversity

    Authors : Dr.anita Harsoor, Shweta Hiremath

    Pages : 194-199

    DOI : http://dx.doi.org/10.21172/1.103.34

    Keywords : social websites, social re-ranking, image search, tag based image.

    Abstract :

    In modern life the digital media and also the social websites has been integral parts of the human life. Websites like flickers allow the user to exchange the information based on the tag associated with the digital data generally the image. Users are fetching the data based on the tag and are an rising trends in the online services. Making the relevant images top ranking and arranging is an important and challenging aspect. Hence we have proposed the social re-ranking model based on the tag in which image searching and retrieval is performed. Re-ranking of image has to be performed based on the of visual information semantic information social clues.. Usually each user contributes several images. First we sort these images by inter-user re-ranking. Users that have higher contribution to the given query rank higher. Then we sequentially implement intra -user re-ranking on the ranked user’s image set, and only the most relevant image from each user’s image set is selected. We have developed an inverted image index for re ranking of the image by using the image data. The Flickr data set has been used and experiment carried out on it which is efficient and effective.

    Citing this Journal Article :

    Dr.anita Harsoor, Shweta Hiremath, "A social re-ranking system for tag-based image search with image’s relevance and diversity", https://www.ijltet.org/journal_details.php?id=932&j_id=4624, Volume 10 Issue 3 - May 2018, 194-199, #ijltetorg