Electrical Engineering
      and Computer Sciences

Electrical Engineering and Computer Sciences

COLLEGE OF ENGINEERING

UC Berkeley

Informative Feature Selection for Object Recognition via Sparse PCA

Nikhil Naikal, Allen Yang and S. Shankar Sastry

EECS Department
University of California, Berkeley
Technical Report No. UCB/EECS-2011-27
April 7, 2011

http://www.eecs.berkeley.edu/Pubs/TechRpts/2011/EECS-2011-27.pdf

Bag-of-words (BoW) methods are a popular class of object recognition methods that use image features (\eg, SIFT) to form visual dictionaries and subsequent histogram vectors to represent object images in the recognition process. The accuracy of the BoW classifiers, however, is often limited by the presence of uninformative features extracted from the background or irrelevant image segments. Most existing solutions to prune out uninformative features rely on enforcing pairwise epipolar geometry via an expensive structure-from-motion (SfM) procedure. Such solutions are known to break down easily when the camera transformation is large or when the features are extracted from low-resolution, low-quality images. In this paper, we propose a novel method to select informative object features using a more efficient algorithm called Sparse PCA. First, we show that using a large-scale multiple-view object database, informative features can be reliably identified from a high-dimensional visual dictionary by applying Sparse PCA on the histograms of each object category. Our experiment shows that the new algorithm improves recognition accuracy compared to the traditional BoW methods and SfM methods. Second, we present a new solution to Sparse PCA as a semidefinite programming problem using Augmented Lagrange Multiplier methods. The new solver outperforms the state of the art for estimating sparse principal vectors as a basis for a low-dimensional subspace model. The source code of our algorithms will be made public on our website.


BibTeX citation:

@techreport{Naikal:EECS-2011-27,
    Author = {Naikal, Nikhil and Yang, Allen and Sastry, S. Shankar},
    Title = {Informative Feature Selection for Object Recognition via Sparse PCA},
    Institution = {EECS Department, University of California, Berkeley},
    Year = {2011},
    Month = {Apr},
    URL = {http://www.eecs.berkeley.edu/Pubs/TechRpts/2011/EECS-2011-27.html},
    Number = {UCB/EECS-2011-27},
    Abstract = {Bag-of-words (BoW) methods are a popular class of object recognition methods that use image features (\eg, SIFT) to form visual dictionaries and subsequent histogram vectors to represent object images in the recognition process. The accuracy of the BoW classifiers, however, is often limited by the presence of uninformative features extracted from the background or irrelevant image segments. Most existing solutions to prune out uninformative features rely on enforcing pairwise epipolar geometry via an expensive structure-from-motion (SfM) procedure. Such solutions are known to break down easily when the camera transformation is large or when the features are extracted from low-resolution, low-quality images. In this paper, we propose a novel method to select informative object features using a more efficient algorithm called Sparse PCA. First, we show that using a large-scale multiple-view object database, informative features can be reliably identified from a high-dimensional visual dictionary by applying Sparse PCA on the histograms of each object category. Our experiment shows that the new algorithm improves recognition accuracy compared to the traditional BoW methods and SfM methods. Second, we present a new solution to Sparse PCA as a semidefinite programming problem using Augmented Lagrange Multiplier methods. The new solver outperforms the state of the art for estimating sparse principal vectors as a basis for a low-dimensional subspace model. The source code of our algorithms will be made public on our website.}
}

EndNote citation:

%0 Report
%A Naikal, Nikhil
%A Yang, Allen
%A Sastry, S. Shankar
%T Informative Feature Selection for Object Recognition via Sparse PCA
%I EECS Department, University of California, Berkeley
%D 2011
%8 April 7
%@ UCB/EECS-2011-27
%U http://www.eecs.berkeley.edu/Pubs/TechRpts/2011/EECS-2011-27.html
%F Naikal:EECS-2011-27