A Comparison of Dense Region Detectors for Image Search and Fine-Grained Classification

DOI10.1109/TIP.2015.2423557zbMATH Open1408.94277arXiv1410.8151OpenAlexW2068562306WikidataQ87126064 ScholiaQ87126064MaRDI QIDQ4612901FDOQ4612901

Hervé Jégou, Philippe H. Gosselin, Giorgos Tolias, Ahmet Iscen

Publication date: 31 January 2019

Published in: IEEE Transactions on Image Processing (Search for Journal in Brave)

Abstract: We consider a pipeline for image classification or search based on coding approaches like Bag of Words or Fisher vectors. In this context, the most common approach is to extract the image patches regularly in a dense manner on several scales. This paper proposes and evaluates alternative choices to extract patches densely. Beyond simple strategies derived from regular interest region detectors, we propose approaches based on super-pixels, edges, and a bank of Zernike filters used as detectors. The different approaches are evaluated on recent image retrieval and fine-grain classification benchmarks. Our results show that the regular dense detector is outperformed by other methods in most situations, leading us to improve the state of the art in comparable setups on standard retrieval and fined-grain benchmarks. As a byproduct of our study, we show that existing methods for blob and super-pixel extraction achieve high accuracy if the patches are extracted along the edges and not around the detected regions.

Full work available at URL: https://arxiv.org/abs/1410.8151

Mathematics Subject Classification ID

Image processing (compression, reconstruction, etc.) in information and communication theory (94A08)

This page was built for publication: A Comparison of Dense Region Detectors for Image Search and Fine-Grained Classification

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4612901)