期刊名称：Indian Journal of Innovations and Developments
印刷版ISSN：2277-5382
电子版ISSN：2277-5390
出版年度：2014
卷号：3
期号：4
页码：85-92
语种：English
出版社：Indian Society for Education and Environment
摘要：Objective: The main objective of this method is to retrieve the image contents from the web server accurately as per the user requirement. This is done by introducing the web page re-ranking mechanism which aims to retrieve the contents content with the knowledge of semantic meaning along with textual information Method: A novel image re-ranking framework that applies incremental SVM learning algorithm and locality sensitive hashing algorithm is proposed in this work to overcome the problem resides in the existing methodology and retrieve the accurate contents as per the user requirement. This approach is based on the knowledge of universal visual semantic space for highly diverse images. Results: The performance evaluation of the proposed methodology is done by comparing it with the existing approaches to prove the improvement of proposed approach. The comparison is done by using the performance metrics called the precision, accuracy and recall from which it is proved that the proposed method provides better result than the existing approach. Conclusion: The finding of this work concludes that the novel re-ranking mechanism retrieves the accurate results than the existing approach with higher accuracy, precision and recall rate.
关键词：Search Retrieval, Keyword Query, High Diverse Images.
