CaltechAUTHORS
  A Caltech Library Service

Scaling object recognition: Benchmark of current state of the art techniques

Aly, Mohamed and Welinder, Peter and Munich, Mario and Perona, Pietro (2009) Scaling object recognition: Benchmark of current state of the art techniques. In: IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops. IEEE , Piscataway, NJ, pp. 2117-2124. ISBN 978-1-4244-4442-7. https://resolver.caltech.edu/CaltechAUTHORS:20170327-170102099

[img] PDF - Published Version
See Usage Policy.

1352Kb

Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20170327-170102099

Abstract

Scaling from hundreds to millions of objects is the next challenge in visual recognition. We investigate and benchmark the scalability properties (memory requirements, runtime, recognition performance) of the state-of-the-art object recognition techniques: the forest of k-d trees, the locality sensitive hashing (LSH) method, and the approximate clustering procedure with the tf-idf inverted index. The characterization of the images was performed with SIFT features. We conduct experiments on two new datasets of more than 100,000 images each, and quantify the performance using artificial and natural deformations. We analyze the results and point out the pitfalls of each of the compared methodologies suggesting potential new research avenues for the field.


Item Type:Book Section
Related URLs:
URLURL TypeDescription
http://dx.doi.org/10.1109/ICCVW.2009.5457542DOIArticle
http://ieeexplore.ieee.org/document/5457542/PublisherArticle
ORCID:
AuthorORCID
Munich, Mario0000-0002-6665-7473
Perona, Pietro0000-0002-7583-5809
Additional Information:© 2009 IEEE.
Record Number:CaltechAUTHORS:20170327-170102099
Persistent URL:https://resolver.caltech.edu/CaltechAUTHORS:20170327-170102099
Official Citation:M. Aly, P. Welinder, M. Munich and P. Perona, "Scaling object recognition: Benchmark of current state of the art techniques," 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops, Kyoto, 2009, pp. 2117-2124. doi: 10.1109/ICCVW.2009.5457542
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:75452
Collection:CaltechAUTHORS
Deposited By: Kristin Buxton
Deposited On:28 Mar 2017 01:34
Last Modified:03 Oct 2019 16:50

Repository Staff Only: item control page