Image Averaging for Improved Iris Recognition

Hollingsworth, Karen; Bowyer, Kevin W.; Flynn, Patrick J.

doi:10.1007/978-3-642-01793-3_112

Cited by 14 publications

(12 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, two conference papers using MBGC iris videos were published in the most recent International Conference in Biometrics. The first paper was our initial version of this research [1]. The second paper, by Lee et al [13], presented methods to detect eyes in the MBGC portal videos and measure the quality of the extracted eye images.…”

Section: A Videomentioning

confidence: 98%

Iris Recognition Using Signal-Level Fusion of Frames From Video

Hollingsworth

Peters

Bowyer

et al. 2009

IEEE Trans.Inform.Forensic Secur.

View full text Add to dashboard Cite

We take advantage of the temporal continuity in an iris video to improve matching performance using signal-level fusion. From multiple frames of a frontal iris video, we create a single average image. For comparison, we reimplement three score-level fusion methods (Ma et al., Krichen et al., and Schmid et al.). We find that our signal-level fusion of images performs better than Ma's or Krichen's score-level fusion methods of Hamming distance scores. Our signal-level fusion performs comparably to Schmid's log-likelihood method of score-level fusion, and our method achieves this performance using less computation time. We compare our signal fusion method with another new method: a multigallery, multiprobe method involving score-level fusion of 2 Hamming distances. The multigallery, multiprobe score fusion has slightly better recognition performance, while the signal fusion has significant advantages in memory and computation requirements. No published prior work has shown any advantage of the use of video over still images in iris biometrics.

show abstract

Section: A Videomentioning

confidence: 98%

Iris Recognition Using Signal-Level Fusion of Frames From Video

Hollingsworth

Peters

Bowyer

et al. 2009

IEEE Trans.Inform.Forensic Secur.

View full text Add to dashboard Cite

show abstract

“…Though research in iris recognition has been extremely active in the past decade, most of the existing results are based on recognition from still iris images [17]. Multiple iris images have been used in the past to improve performance.…”

Section: B Iris Recognition From Videosmentioning

confidence: 99%

“…So by efficiently combining the different frames in the video, the performance could be improved. Temporal continuity in iris videos was used for improving the performance by Hollingsworth et al [17]. The authors introduced a feature level fusion by averaging the corresponding iris pixels and a score level fusion algorithm combining all the pairwise matching scores.…”

Section: B Iris Recognition From Videosmentioning

confidence: 99%

Secure and Robust Iris Recognition Using Random Projections and Sparse Representations

Pillai

Patel

Chellappa

et al. 2011

IEEE Trans. Pattern Anal. Mach. Intell.

293

155

View full text Add to dashboard Cite

Abstract-Non-contact biometrics such as face and iris have additional benefits over contact based biometrics such as fingerprint and hand geometry. However, three important challenges need to be addressed in a non-contact biometrics-based authentication system: ability to handle unconstrained acquisition, robust and accurate matching and privacy enhancement without compromising security. In this paper, we propose a unified framework based on random projections and sparse representations, that can simultaneously address all the three issues mentioned above in relation to iris biometrics. Our proposed quality measure can handle segmentation errors and a wide variety of possible artifacts during iris acquisition. We demonstrate how the proposed approach can be easily extended to handle alignment variations and recognition from iris videos, resulting in a robust and accurate system. The proposed approach includes enhancements to privacy and security by providing ways to create cancelable iris templates. Results on public datasets show significant benefits of the proposed approach.

show abstract

“…It consists of averaging of N frames to create a single average image. In the same manner as the work performed in [6,8], fragile bit masking is implemented to screen complex coefficients which lie too close to the axes and might end up as a zero or a one in different iris codes of the same iris image. In our experiments, this is referred to as the 1-1 Signal Fusion-Fragile comparison.…”

Section: -To-1 and N-to-1 Comparisonsmentioning

confidence: 99%

“…A high quality iris image is subsequently obtained by adopting a support vector machine based learning approach. Multiple frames from an iris video are averaged into a single frame using signal fusion to improve performance in [7] [8]. In their experiments, Hollingsworth et al use varying number of frames and masking.…”

Section: Introductionmentioning

confidence: 99%