loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Paper Unlock

Authors: Hong Pan 1 ; Søren Olsen 2 and Yaping Zhu 2

Affiliations: 1 University of Copenhagen and Southeast University, Denmark ; 2 University of Copenhagen, Denmark

Keyword(s): Context Kernel Descriptors, Cauchy-Schwarz Quadratic Mutual Information, Feature Extraction and Learning, Object Recognition and Detection.

Related Ontology Subjects/Areas/Topics: Applications ; Classification ; Computer Vision, Visualization and Computer Graphics ; Feature Selection and Extraction ; Image Understanding ; Object Recognition ; Pattern Recognition ; Software Engineering ; Theory and Methods

Abstract: Feature extraction and learning is critical for object recognition and detection. By embedding context cue of image attributes into the kernel descriptors, we propose a set of novel kernel descriptors called context kernel descriptors (CKD). The motivation of CKD is to use the spatial consistency of image attributes or features defined within a neighboring region to improve the robustness of descriptor matching in kernel space. For feature learning, we develop a novel codebook learning method, based on the Cauchy-Schwarz Quadratic Mutual Information (CSQMI) measure, to learn a compact and discriminative CKD codebook from a rich and redundant CKD dictionary. Projecting the original full-dimensional CKD onto the codebook, we reduce the dimensionality of CKD without losing its discriminability. CSQMI derived from Rényi quadratic entropy can be efficiently estimated using a Parzen window estimator even in high-dimensional space. In addition, the latent connection between Rényi quadratic entropy and the mapping data in kernel feature space further facilitates us to capture the geometric structure as well as the information about the underlying labels of the CKD using CSQMI. Thus the resulting codebook and reduced CKD are discriminative. We report superior performance of our algorithm for object recognition on benchmark datasets like Caltech-101 and CIFAR-10, as well as for detection on a challenging chicken feet dataset. (More)

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 34.201.28.181

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Pan, H.; Olsen, S. and Zhu, Y. (2015). Discriminative Kernel Feature Extraction and Learning for Object Recognition and Detection. In Proceedings of the International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM; ISBN 978-989-758-076-5; ISSN 2184-4313, SciTePress, pages 99-109. DOI: 10.5220/0005212900990109

@conference{icpram15,
author={Hong Pan. and Søren Olsen. and Yaping Zhu.},
title={Discriminative Kernel Feature Extraction and Learning for Object Recognition and Detection},
booktitle={Proceedings of the International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM},
year={2015},
pages={99-109},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005212900990109},
isbn={978-989-758-076-5},
issn={2184-4313},
}

TY - CONF

JO - Proceedings of the International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM
TI - Discriminative Kernel Feature Extraction and Learning for Object Recognition and Detection
SN - 978-989-758-076-5
IS - 2184-4313
AU - Pan, H.
AU - Olsen, S.
AU - Zhu, Y.
PY - 2015
SP - 99
EP - 109
DO - 10.5220/0005212900990109
PB - SciTePress