An Empirical Study of Object Category Recognition: Sequential Testing with Generalized Samples

Liang Lin, Shaowu Peng, Jake Porway, Song Chun Zhu, Yongtian Wang

Abstract: In this paper we present an empirical study of object category recognition using generalized samples and a set of sequential tests. We study 33 categories, each consisting of a small data set of 30 instances. To increase the amount of training data we have, we use a compositional object model to learn a representation for each category from which we select 30 additional templates with varied appearance from the training set. These samples better span the appearance space and form an augmented training set Ω <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">T</sub> of 1980 (60×33) training templates. To perform recognition on a testing image, we use a set of sequential tests to project Ω <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">T</sub> into different representation spaces to narrow the number of candidate matches in Ω <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">T</sub> . We use"graphlets"(structural elements), as our local features and model Omega <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">T</sub> at each stage using histograms of graphlets over categories, histograms of graphlets over object instances, histograms of pairs of graphlets over objects, shape context. Each test is increasingly computationally expensive, and by the end of the cascade we have a small candidate set remaining to use with our most powerful test, a top-down graph matching algorithm. We achieve an 81.4 % classification rate on classifying 800 testing images in 33 categories, 15.2% more accurate than a method without generalized samples.