In the last few years, large-scale image retrieval has attracted a lot of attention from the multimedia community. Usual approaches addressing this task first generate an initial ranking of the reference images using fast approximations that do not take into consideration the spatial arrangement of local features in the image (e.g., the bag-of-words paradigm). The top positions of the rankings are then re-estimated with verification methods that deal with more complex information, such as the geometric layout of the image. This verification step allows pruning of many false positives at the expense of an increase in the computational complexity, which may prevent its application to large-scale retrieval problems. This paper describes a geometric method known as neighborhood matching (NM), which revisits the keypoint matching process by considering a neighborhood around each keypoint and improves the efficiency of a geometric verification step in the image search system. Multiple strategies are proposed and compared to incorporate NM into a large-scale image retrieval framework. A detailed analysis and comparison of these strategies and baseline methods have been investigated. The experiments show that the proposed method not only improves the computational efficiency, but also increases the retrieval performance and outperforms state-of-the-art methods in standard datasets, such as the Oxford 5 k and 105 k datasets, for which the spatial verification step has a significant impact on the system performance.

This paper proposes a novel method for semi-supervised image segmentation that is particularly targeted for interaction on mobile devices with touchscreen. In order to extract an object from a complicated scene with minimal user input, superpixels are first grouped into overlapping regions based on their visual similarity and the groups belonging to the object are then selected via user scribbles. By moving the user interaction to the end of the whole process, users' idle time is minimized hence an engaging user experience is achieved. The proposed method can effortlessly handle imprecise and inaccurate scribbles and is inherently suitable for touchscreen devices since it eliminates the necessity of a separate brush for marking the background as majority of state-of-the-art methods do. A novel fine-tuning method is also proposed where both foreground and background corrections are possible without entailing the user to change the brush. Experimental results prove that successful results are achieved with a slick and pleasant user experience.