Probabilistic Deformation Models for Image Matching

Jonathon Smereka, Vishnu Naresh Boddeti and B.V.K. Vijaya Kumar

People

Jonathon Smereka (Contact)

Vishnu Naresh Boddeti (Contact)

Vijayakumar Bhagavatula

Code

Abstract

Matching of deformed patterns is an important and difficult task in biometric recognition. Moreover, recognition becomes considerably more difficult in 1 : 1 matching schemes where only a single probe and a single gallery sample are available to determine a match. Referred to as Probabilistic Deformation Models (PDMs), an approach originally proposed by Thornton et al. for matching iris images reduces the image matching problem to matching local image regions, where iris distortions are approximated by local independent spatial translations and then related by a Gaussian Markov Random Field (GMRF). Building on Thornton’s method, this paper demonstrates the drawbacks of using too simple of a model to capture biometric deformations when restricted to 1 : 1 matching schemes. In this paper we propose several improvements, both from a computational as well as a performance point of view, to the basic framework. The new model, which extends PDM (referred to as ‘ePDM’), allows us to capture a more varied set of valid pattern deformations for authentic matches that are present in biometric signatures captured in 1 : 1 matching environments. We demonstrate the effectiveness of this model via extensive numerical results on multiple biometric databases while comparing to other state-of-the-art 1 : 1 matching algorithms.

Overview

Probabilistic Deformation Models Overview 

System overview for determining a match. The probe, textbf{I}, and gallery, textbf{G}, images are each divided into non-overlapping patches where the corresponding probe and gallery patches are compared via template matching. The outputs from template matching are then used as inputs into the GMRF model that is trained to capture the relationship between the deformations of the image patches for authentic matches. The final match score (emph{M}) is the summation of the marginal posterior probabilities.

Contributions

  • Introduce several algorithmic improvements to the original PDM model to improve deformation tolerance in different biometric modalities and 1 : 1 matching schemes.

  • Improve the memory and computational complexity of both the training and testing procedures proposing a computationally efficient classifier design.

  • A comprehensive comparison to several other methods on periocular datasets demonstrating the need for deformation estimation in 1 : 1 matching schemes as well as the efficacy of PDM. We achieve state-of-the-art results on multiple databases for periocular verification of varying difficulty.

References

Probabilistic Deformation Models for Biometric Image Matching

Jonathon M. Smereka, Vishnu Naresh Boddeti and B.V.K. Vijaya Kumar
IEEE Transactions on Pattern Analysis and Maching Intelligence (Under Review)

What is a 'Good’ Periocular Region for Recognition?

Jonathon M. Smereka and B.V.K. Vijaya Kumar
IEEE CVPR Workshop on Biometrics, June 2013

Matching Highly Non-Ideal Ocular Images: An Information Fusion Approach

Arun Ross, Raghavender Jillela, Jonathon M. Smereka, Vishnu Naresh Boddeti, B. V. K. Vijaya Kumar, Ryan Barnard, Xiaofei Hu, Paul Pauca, Robert Plemmons
5th IAPR International Conference on Biometrics, 2012 (oral)

Improved Iris Segmentation Based on Local Texture Statistics

Vishnu Naresh Boddeti, B.V.K. Vijaya Kumar and Krishnan Ramkumar
45th Asilomar Conference on Signals, Systems and Computers, 2011 (oral, invited paper)

A comparative evaluation of iris and ocular recognition methods on challenging ocular images

Vishnu Naresh Boddeti, Jonathon M. Smereka and B.V.K. Vijaya Kumar
International Joint Conference on Biometrics, 2011. (oral)

A Bayesian Approach to Deformed Pattern Matching of Iris Images

Jason Thornton, Marios Savvides and B.V.K. Vijaya Kumar
IEEE Transactions on Pattern Analysis and Maching Intelligence, 2007