USA flag logo/image

An Official Website of the United States Government

A Machine Learning Approach to Assessment of Image Quality through Prediction…

Award Information

Agency:
Department of Homeland Security
Branch:
N/A
Award ID:
Program Year/Program:
2011 / SBIR
Agency Tracking Number:
DHS SBIR-2011.2-H-SB011.2-005-0011-I
Solicitation Year:
2011
Solicitation Topic Code:
H-SB011.2-005
Solicitation Number:
N/A
Small Business Information
Neya Systems, LLC (formerly Rhobotika, LLC)
12330 Perry Hwy Wexford, PA 15090-8319
View profile »
Woman-Owned: No
Minority-Owned: No
HUBZone-Owned: No
 
Phase 1
Fiscal Year: 2011
Title: A Machine Learning Approach to Assessment of Image Quality through Prediction of Iris Recognition Success
Agency: DHS
Contract: D11PC20252
Award Amount: $99,366.66
 

Abstract:

It is clear from prior research that quality metrics can predict and improve recognition performance. As we add new quality metrics, however, determining a weighting scheme using simple rules for their combination becomes infeasible. This argues for a machine learning approach that will automatically determine the optimal weighting. We propose to develop a large set of quality metrics based on requirements set down in the IREX II/IQCE evaluation. These metrics will form a feature vector supplied to a novel manifold-learning algorithm developed recently for function approximation, which will be trained to predict the performance of stages in various iris recognition algorithms as well the algorithms' final recognition performance. Applying standard feature selection techniques, our system will also automatically determine a weighting for the features to be used, identifying features that contribute little and can be eliminated. The final quality metrics will be combinations of the outputs of the feature extractor associated with the metrics and their weighting as determined by our system. Such a flexible image quality assessment system would have application beyond iris recognition to other areas in biometrics, such as face recognition, but also to domains such as stereovision, visual odometry, and general object recognition. Image quality metrics are largely at the level of proof-of-concept demonstration on available datasets. Our work will take this technology from TRL 3 to TRL 4 by integrating the metrics with recognition algorithms by acting as a front-end predicting performance and so indicating whether an image is adequate to the task.

Principal Investigator:

Michael Happold
happ@rhobotika.com

Business Contact:

Michael Happold
happ@rhobotika.com
Small Business Information at Submission:

Rhobotika, LLC
145 Pine Rd Evans City, PA 16033-3323

EIN/Tax ID: 272089057
DUNS: N/A
Number of Employees:
Woman-Owned: No
Minority-Owned: No
HUBZone-Owned: No