We show a prototype of an offline image recognition engine, running on a tablet with Intel®Atom™ processor, searching within less than 250ms through thousands (5000+) of images. Moreover, the prototype still offers the advanced capabilities of recognising real world 3D objects, until now reserved only for cloud solutions. Until now image search within large collections of images could be performed only in the cloud, requiring mobile devices to have Internet connectivity. However, for many use cases the connectivity requirement is impractical, e.g. many museums have no network coverage, or do not want their visitors incurring expensive roaming charges. Existing commercial solutions are very limited in terms of searched collections sizes, often imposing a maximum limit of <100 reference images. Moreover, adding images typically affects the recognition speed and increases RAM requirements.

In this paper we propose a fast and memory efficient Dynamic Time Warping (MES-DTW) algorithm for the task of Query-by-Example Spoken Term Detection (QbE-STD). The proposed algorithm is based on the subsequence-DTW (S-DTW) algorithm, which allows the search for small spoken queries within a much bigger search collection of spoken documents by considering fixed start-end points in the query and discovering optimal matching subsequences along the search collection. The proposed algorithm applies some modifications to S-DTW that make it better suited for the QbE-STD task, including a way to perform the matching with virtually no system memory, optimal when querying large scale databases. We also describe the system used to perform QbE-STD, including an energy-based quantification for speech/non-speech detection and an overlap detector for putative matches. We test the system proposed using the Mediaeval 2012 spoken-web-search dataset and show that, in addition to the memory savings, the proposed algorithm brings an advantage in terms of matching accuracy (up to 0.235 absolute MTWV increase) and speed (around 25% faster) in comparison to the original S-DTW.