Mobile Multi-View Object Image Search
This work addresses the need for more accurate object image search on mobile devices, though it is incremental as it builds on existing fusion methods.
The paper tackled the problem of improving mobile visual search accuracy by using multiple views of an object from different angles and scales, and found that multi-view search significantly outperforms single-view search in retrieval accuracy.
High user interaction capability of mobile devices can help improve the accuracy of mobile visual search systems. At query time, it is possible to capture multiple views of an object from different viewing angles and at different scales with the mobile device camera to obtain richer information about the object compared to a single view and hence return more accurate results. Motivated by this, we developed a mobile multi-view object image search system, using a client-server architecture. Multi-view images of objects acquired by the mobile clients are processed and local features are sent to the server, which combines the query image representations with early/late fusion methods based on bag-of-visual-words and sends back the query results. We performed a comprehensive analysis of early and late fusion approaches using various similarity functions, on an existing single view and a new multi-view object image database. The experimental results show that multi-view search provides significantly better retrieval accuracy compared to single view search.