Voronoi-based Compact Image Descriptors: Efficient Region-of-interest Retrieval With VLAD And Deep-learning-based Descriptors

Abstract

We investigate the problem of image retrieval based on visual queries when the latter comprise arbitrary regions-of-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, Voronoi-based 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 content-based 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 K-means 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

Stats

• citations27
• S2 citations—
• github stars0
• HF likes0
• heat score10.85
• arxiv keychadha2016voronoi

Related papers

• A Dense-depth Representation For VLAD Descriptors In Content-based Image Retrieval (2018)5.24
• Aggregated Deep Local Features For Remote Sensing Image Retrieval (2019)14.11
• Local Feature Detectors, Descriptors, And Image Representations: A Survey (2016)0.00
• Deep Image Retrieval: Learning Global Representations For Image Search (2016)19.67
• From Selective Deep Convolutional Features To Compact Binary Representations For Image Retrieval (2018)10.35
• Compact Hash Codes For Efficient Visual Descriptors Retrieval In Large Scale Databases (2016)11.76
• Exploiting Local Indexing And Deep Feature Confidence Scores For Fast Image-to-video Search (2018)2.26
• Challenging Deep Image Descriptors For Retrieval In Heterogeneous Iconographic Collections (2019)5.84