MUMBAI, India, June 22 -- Intellectual Property India has published a patent application (202641070699 A) filed by Prince Shri Venkateshwara Padmavathy Engineering College; Prince Dr K Vasudevan College Of Engineering And Technology; Prince Shri Balaji Arts And Science College; and Prince Shri Venkateshwara Arts And Science College on June 06, 2026, for Improving Web Image Search By Attribute Based Approach.
Inventors include Prince Shri Venkateshwara Padmavathy Engineering; Prince Dr K Vasudevan College Of Engineering And; Prince Shri Balaji Arts And Science College; and Prince Shri Venkateshwara Arts And Science College.
The application for the patent was published on June 12, 2026, under issue no. 24/2026.
Abstract: Image search re-ranking methods usually fail to capture the user's intention when the query term is ambiguous. Therefore, re-ranking with user interactions, or active re- ranking, is highly demanded to effectively improve the search performance. The essential problem in active re-ranking is how to target the user's intention. To complete this goal, this paper presents a structural information based sample selection strategy to reduce the user's labelling efforts. Furthermore, to localize the user's intention in the visual feature space, a novel Latent Dirichlet Allocation algorithm is proposed. We let users to give their own attributes for any images if they think that can be mapped with that particular image. This increases the search efficiency of the images. We let admin to validate the contents or an attribute to be matched with the existing ones which helps in integrating the users’ intentions towards any image. This paper serves as a first attempt to include the attributes in reranking framework. We observe that semantic attributes are expected to narrow down the semantic gap between low-level visual features and high level semantic meanings.
Disclaimer: Curated by HT Syndication.
