Feature Based Image Reranking Using Fusion Weights

: Search reranking is considered as a best and common way to improves retrieval precision. The images are retrieved using the associated textual information, such as surrounding text from the web page. The performance of such systems mainly relies on the relevance between the text and the images. However, they may not always match well enough, which causes noisy ranking results. For instance, visually similar images may have very different ranks. So reranking has been proposed to solve the problem. Image re-ranking, as an effective way to improve the results of web-based image search however the problem is not trivial especially when we are considering multiple features or modalities for search in image and video retrieval. This paper suggests a new kind of reranking algorithm, that supports the mutual exchange of information across multiple modalities for improving search performance and follows the philosophy of strong performing modality could learn from weaker ones.