Abstract : RELEVANCE RESPONSE APPROACH FOR IMAGE RETRIEVAL USING DYNAMIC FUSION

Abstract

                  We propose a relevance response for Image retrieval. Our project shows advantage over traditional relevance response mechanisms in the following three aspects. First, during the relevance response process, both textual feature and visual feature are used in a sequential way. To seamlessly combine textual feature and visual feature, Dynamic Fusion strategy is automatically learned. Second, the textual feature mechanism employs an effective Fuzzy Clustering algorithm to obtain salient phrases, based on which we could construct an accurate and low-dimensional textual space for the resulting Images. Last, a new user interface (UI) is proposed to support implicit relevance response. On the one hand, unlike traditional relevance response UI which enforces users to make explicit judgment on the results, the new UI regards the users’ click-through data as implicit relevance feedback in order to release burden from the users.

contact: 9894924562
for all type of computer science project and ieee papers