Re-Ranking of Web Image Prediction Using Multimodal Sparse Code and Voting Strategy

Provided by: International Journal of Advanced Research in Computer Science and Software Engineering (IJARCSSE)
Topic: Developer
Format: PDF
In this paper, the authors give the information about the web image search using the multimodal sparse code and voting strategy. The performance of text-based image search which has been improved by using Image re-ranking. Existing re-ranking algorithms have two main drawbacks, first the textual meta-data associated with images is often mismatched with their actual visual content and second the extracted visual features do not accurately describe the semantic similarities between images. Pseudo-Relevance Feedback (PRF) tool is used in many existing re-ranking system. A critical problem for click-based methods is the lack of click data, so only a small number of web images have actually been clicked on by users.

Find By Topic