A Caltech Library Service

Evaluation of features detectors and descriptors based on 3D objects

Moreels, Pierre and Perona, Pietro (2007) Evaluation of features detectors and descriptors based on 3D objects. International Journal of Computer Vision, 73 (3). pp. 263-284. ISSN 0920-5691. doi:10.1007/s11263-006-9967-1.

Full text is not posted in this repository. Consult Related URLs below.

Use this Persistent URL to link to this item:


We explore the performance of a number of popular feature detectors and descriptors in matching 3D object features across viewpoints and lighting conditions. To this end we design a method, based on intersecting epipolar constraints, for providing ground truth correspondence automatically. These correspondences are based purely on geometric information, and do not rely on the choice of a specific feature appearance descriptor. We test detector-descriptor combinations on a database of 100 objects viewed from 144 calibrated viewpoints under three different lighting conditions. We find that the combination of Hessian-affine feature finder and SIFT features is most robust to viewpoint change. Harris-affine combined with SIFT and Hessian-affine combined with shape context descriptors were best respectively for lighting change and change in camera focal length. We also find that no detector-descriptor combination performs well with viewpoint changes of more than 25-30 degrees.

Item Type:Article
Related URLs:
URLURL TypeDescription ReadCube access ItemConference Paper
Perona, Pietro0000-0002-7583-5809
Additional Information:© 2007 Springer Science + Business Media. Received February 3, 2006; Revised July 18, 2006; Accepted July 26, 2006. First online version published in September, 2006.
Subject Keywords:features detectors, features descriptors, object recognition
Issue or Number:3
Record Number:CaltechAUTHORS:20140730-101717121
Persistent URL:
Official Citation:Moreels, P. & Perona, P. Int J Comput Vision (2007) 73: 263.
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:47597
Deposited By: Caroline Murphy
Deposited On:25 Aug 2014 21:21
Last Modified:10 Nov 2021 17:48

Repository Staff Only: item control page