Correlation Filtering Theory

Vishnu Naresh Boddeti, Andres Rodriguez and B.V.K. Vijaya Kumar


Vishnu Naresh Boddeti (Contact)

Andres Rodriguez

Vijayakumar Bhagavatula



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.


Maximum Margin Vector Correlation Filters

Vishnu Naresh Boddeti and B.V.K. Vijaya Kumar

Zero-Aliasing Correlation Filters for Object Recognition

Joseph Fernandez, Andres Rodriguez, Vishnu Naresh Boddeti and B.V.K. Vijaya Kumar
IEEE Transactions on Pattern Analysis and Machine Intelligence (Under Review)

Advances in Correlation Filters: Vector Features, Structured Prediction and Shape Alignment

Vishnu Naresh Boddeti
Carnegie Mellon University 2012

Maximum Margin Correlation Filters

Andres Rodriguez
Carnegie Mellon University 2012

Maximum Margin Correlation Filter: A New Approach for Simultaneous Localization and Classification

Andres Rodriguez, Vishnu Naresh Boddeti, B.V.K Vijaya Kumar and Abhijit Mahalanobis
IEEE Transactions on Image Processing 2013

Correlation Pattern Recognition

B. V. K. Vijaya Kumar, A. Mahalanobis, and R. D. Juday
Cambridge Univ. Press, 2005