Please use this identifier to cite or link to this item:
logo share SHARE BASE
Visualizar otros formatos: MARC | Dublin Core | RDF | ORE | MODS | METS | DIDL | DATACITE

Fast and Robust Object Segmentation with the Integral Linear Classifier

AuthorsAldavert, David; Ramisa, Arnau CSIC ORCID; Toledo, Ricardo; López de Mántaras, Ramón CSIC ORCID
KeywordsComputer vision
Pattern recognition
Bag of features
Image classification
Issue Date2010
PublisherInstitute of Electrical and Electronics Engineers
CitationProceedings 23d IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2010), San Francisco, California, June 13-18: 1046-1053 (2010)
AbstractWe propose an efficient method, built on the popular Bag of Features approach, that obtains robust multiclass pixellevel object segmentation of an image in less than 500ms, with results comparable or better than most state of the art methods. We introduce the Integral Linear Classifier (ILC), that can readily obtain the classification score for any image sub-window with only 6 additions and 1 product by fusing the accumulation and classification steps in a single operation. In order to design a method as efficient as possible, our building blocks are carefully selected from the quickest in the state of the art. More precisely, we evaluate the performance of three popular local descriptors, that can be very efficiently computed using integral images, and two fast quantization methods: the Hierarchical K-Means, and the Extremely Randomized Forest. Finally, we explore the utility of adding spatial bins to the Bag of Features histograms and that of cascade classifiers to improve the obtained segmentation. Our method is compared to the state of the art in the difficult Graz-02 and PASCAL 2007 Segmentation Challenge datasets.
Publisher version (URL)
Appears in Collections:(IIIA) Comunicaciones congresos

Files in This Item:
File Description SizeFormat
CVPR 2010.pdf2,65 MBAdobe PDFThumbnail
Show full item record
Review this work

Page view(s)

checked on May 20, 2022


checked on May 20, 2022

Google ScholarTM




WARNING: Items in Digital.CSIC are protected by copyright, with all rights reserved, unless otherwise indicated.