Abstract
Support vector machine (SVM) classifiers are popular in many computer vision tasks. In most of them, the SVM classifier assumes that the object to be classified is centered in the query image which might not always be valid, e.g., when locating and classifying a particular class of vehicles in a large scene. In this paper we introduce a new classifier called Maximum Margin Correlation Filter (MMCF), which while exhibiting the good generalization capabilities of SVM classifiers is also capable of localizing objects of interest, thereby avoiding the need for image centering as is usually required in SVM classifiers. In other words, MMCF can simultaneously localize and classify objects of interest. We test the efficacy of the proposed classifier on three different tasks: vehicle recognition, eye localization, and face classification. We demonstrate that MMCF outperforms SVM classifiers and also well-known correlation filters.
Overview
Application of a correlation filter to a query image.
A Mind Map of various Linear Correlation Filter designs proposed in the literature.
Contributions
- Introduced a new correlation filter design for combing the localization properties of correlation filters and the margin maximizing properties of SVMs [3,8].
- Introduced multi-channel correlation filters for object part localization with applications to object alignment [4].
- Introduced correlation filter designs for predicting structured outputs (binary bit information) with applications to biometric key-binding [7].
- Introduced a method for learning a discriminatively reduced ensemble of exemplar correlation filters with applications to 3D pose estimation of vehicles.
- Historically correlation filter designs formulated in the Fourier domain suffer from aliasing effects due to circular correlation. We introduce aliasing free for all previously proposed correlation filter designs [1].
References
-
Jonathon M. Smereka, Vishnu Naresh Boddeti, B.V.K. Vijaya Kumar and Andres Rodriguez, Stacked Correlation Filters for Biometric Verification, IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2016)
-
Hironori Hattori, Vishnu Naresh Boddeti, Kris Kitani and Takeo Kanade, Learning Scene-Specific Pedestrian Detectors without Real Data (Supplementary Material), CVPR, 2015
-
Joseph Fernandez, Vishnu Naresh Boddeti, Andres Rodriguez and B.V.K. Vijaya Kumar, Zero-Aliasing Correlation Filters for Object Recognition, IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015
-
Yair Movshovitz-Attias, Vishnu Naresh Boddeti, Zijun Wei and Yaser Sheikh, 3D Pose-by-Detection of Vehicles via Discriminatively Reduced Ensembles of Correlation Filters (Supplementary Material), BMVC, 2014
-
Vishnu Naresh Boddeti and B.V.K. Vijaya Kumar, “Maximum Margin Vector Correlation Filter,” Arxiv 1404.6031 (April 2014)
-
Vishnu Naresh Boddeti, Takeo Kanade and B.V.K. Vijaya Kumar, Correlation Filters for Object Alignment (Supplementary Material), CVPR, 2013
-
Vishnu Naresh Boddeti, Advances in Correlation Filters: Vector Features, Structured Prediction and Shape Alignment, Carnegie Mellon University, 2012
-
Andres Rodriguez, Maximum Margin Correlation Filters, Carnegie Mellon University, 2012
-
Vishnu Naresh Boddeti and B.V.K Vijaya Kumar, A Framework for Binding and Retrieving Class-Specific Information to and from Image Patterns using Correlation Filters, IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013
-
Andres Rodriguez, Vishnu Naresh Boddeti, B.V.K Vijaya Kumar and Abhijit Mahalanobis, Maximum Margin Correlation Filter: A New Approach for Simultaneous Localization and Classification IEEE Transactions on Image Processing, 2013
-
B. V. K. Vijaya Kumar, A. Mahalanobis, and R. D. Juday, Correlation Pattern Recognition, Cambridge Univ. Press, 2005