Voronoi-Based Compact Image Descriptors: Efficient Region-of-Interest Retrieval With VLAD and Deep-Learning-Based Descriptors

Advanced search
Browse by:

Department | Year

UCL Theses | Latest

Deposit your research

Voronoi-Based Compact Image Descriptors: Efficient Region-of-Interest Retrieval With VLAD and Deep-Learning-Based Descriptors

Chadha, A; Andreopoulos, Y; (2017) Voronoi-Based Compact Image Descriptors: Efficient Region-of-Interest Retrieval With VLAD and Deep-Learning-Based Descriptors. IEEE Transactions on Multimedia , 19 (7) pp. 1596-1608. 10.1109/TMM.2017.2673415. Green open access

Preview

Text
bare_jrnl_28.pdf - Accepted Version
Download (2MB) | Preview

Abstract

We investigate the problem of image retrieval based on visual queries when the latter comprise arbitrary regionsof- interest (ROI) rather than entire images. Our proposal is a compact image descriptor that combines the state-of-the-art in content-based descriptor extraction with a multi-level, Voronoibased spatial partitioning of each dataset image. The proposed multi-level Voronoi-based encoding uses a spatial hierarchical K-means over interest-point locations, and computes a contentbased descriptor over each cell. In order to reduce the matching complexity with minimal or no sacrifice in retrieval performance: (i) we utilize the tree structure of the spatial hierarchical Kmeans to perform a top-to-bottom pruning for local similarity maxima; (ii) we propose a new image similarity score that combines relevant information from all partition levels into a single measure for similarity; (iii) we combine our proposal with a novel and efficient approach for optimal bit allocation within quantized descriptor representations. By deriving both a Voronoi-based VLAD descriptor (termed as Fast-VVLAD) and a Voronoi-based deep convolutional neural network (CNN) descriptor (termed as Fast-VDCNN), we demonstrate that our Voronoi-based framework is agnostic to the descriptor basis, and can easily be slotted into existing frameworks. Via a range of ROI queries in two standard datasets, it is shown that the Voronoibased descriptors achieve comparable or higher mean Average Precision against conventional grid-based spatial search, while offering more than two-fold reduction in complexity. Finally, beyond ROI queries, we show that Voronoi partitioning improves the geometric invariance of compact CNN descriptors, thereby resulting in competitive performance to the current state-of-theart on whole image retrieval.

Type:	Article
Title:	Voronoi-Based Compact Image Descriptors: Efficient Region-of-Interest Retrieval With VLAD and Deep-Learning-Based Descriptors
Open access status:	An open access version is available from UCL Discovery
DOI:	10.1109/TMM.2017.2673415
Publisher version:	http://doi.org/10.1109/TMM.2017.2673415
Language:	English
Additional information:	© 2017 IEEE. This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions.
Keywords:	Visualization, Complexity theory, Image coding, Quantization (signal), Image retrieval, Proposals, Encoding
UCL classification:	UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Electronic and Electrical Eng
URI:	https://discovery.ucl.ac.uk/id/eprint/1546433