Indexing iris images using the Burrows-Wheeler Transform

Gadde, Ravindra B.; Adjeroh, Donald A.; Ross, Arun

doi:10.1109/wifs.2010.5711467

Cited by 24 publications

(6 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…log in case of a binary search tree. Such search structures might be designed for iris-codes [19,20] as well as iris images [21][22][23]. While the majority of works report hit/ penetration rates on distinct datasets, required computational efforts are frequently omitted.…”

Section: Related Workmentioning

confidence: 99%

Methods for accuracy‐preserving acceleration of large‐scale comparisons in CPU‐based iris recognition systems

et al. 2017

View full text Add to dashboard Cite

To confirm an individual's identity accurately and reliably iris recognition systems analyse the texture that is visible in the iris of the eye. The rich random pattern of the iris constitutes a powerful biometric characteristic suitable for biometric identification in large-scale deployments. Identification attempts or deduplication checks require an exhaustive one-to-many comparison. Hence, for large-scale biometric databases with millions of enrollees the time required for a biometric identification is expected to significantly increase. In this work we analyse techniques to accelerate Hamming distance-based comparisons of binary biometric reference data, i.e. iris-codes, in large-scale iris recognition systems, which preserve the biometric performance. Focus is put on software-based optimizations, an efficient twostep iris-code alignment process referred to as TripleA, and a combination thereof. Benchmarking the throughput and identifying potential bottlenecks of a portable commodity hardware-based iris recognition system, is of particular interest. Based on conducted experiments we point out practical boundaries of large-scale comparisons in CPU-based iris recognition systems, bridging the gap between the fields of iris recognition and software design.

show abstract

Section: Related Workmentioning

confidence: 99%

Methods for accuracy‐preserving acceleration of large‐scale comparisons in CPU‐based iris recognition systems

et al. 2017

View full text Add to dashboard Cite

show abstract

“…The selected methods are due to: 1) Gadde et al [6], which analyzed the distribution of intensities and selected patterns with low coefficients of variation (CVs) as indexing pivots. For each probe represented in the polar domain, a radial division of nbands was performed and indexed using the radial band of the highest density of CV patterns.…”

Section: Parametermentioning

confidence: 99%

Creating synthetic IrisCodes to feed biometrics experiments

Proença

Neves

2013

2013 IEEE Workshop on Biometric Measurements and Systems for Security and Medical Applications

View full text Add to dashboard Cite

The collection of iris data suitable to be used in experiments is difficult, mainly due to two factors: 1) the time spent by volunteers in the acquisition process; and 2) security / privacy concerns of volunteers. Even though there are methods to create images of artificial irises, there is no method exclusively focused in the synthesis of the iris biometric signatures (IrisCodes). In experiments related with some phases of the biometric recognition process (e.g., indexing / retrieval), a large number of signatures is required for proper evaluation, which, in case of real data, is extremely hard to obtain. Hence, this paper describes a stochastic method to synthesize IrisCodes, based on the notion of data correlation. These artificial signatures can be used to feed experiments on iris recognition, namely on the iris matching, indexing and retrieval phases. We experimentally confirmed that both the genuine and impostor distributions obtained on the artificial data closely resemble the values obtained in data sets of real irises. Finally, another interesting feature is that the method is easily parametrized to mimic IrisCodes extracted from data of varying levels of quality, i.e., ranging from data acquired in high controlled to unconstrained environments.

show abstract

“…Among the many biometric features, iris is deemed as important because it is used to verify a person by using distinct texture patterns, it is a rich in unique texture features to every individual [20] [11]. The extracted features during enrolment process are stored in a high dimensional data, it becomes challenging to identify a person in large-scale biometric systems e.g.…”

Section: Introductionmentioning

confidence: 99%

Efficient Classifying and Indexing for Large Iris Database Based on Enhanced Clustering Method

Khalaf¹,

Mohammed²,

Moorthy³

et al. 2019

STUD INFORM CONTROL

View full text Add to dashboard Cite

Explosive growth in the volume of stored biometric data has resulted in classification and indexing becoming important operations in image database systems. A new method is presented in this paper to extract the most relevant features of iris biometric images for indexing the iris database. Three transformation methods DCT, DWT and SVD were used to analyse the iris image and to extract its local features. The clustering method shouldering on the responsibility of determining the partitioning and classification efficiencies of the system has been improved. In the current work, the new Weighted K-means algorithm based on the Improved Firefly Algorithm (WKIFA) has been used to overcome the shortcomings in using the Fireflies Algorithm (FA). The proposed method can be used to perform global search and exhibits quick convergence rate while optimizing the initial clustering centers of the K-means algorithm. From the experimental results, the proposed method was indeed more effective for clustering and classification and outperformed the traditional k-mean algorithm. The Penetration Rates underwent reductions and reached the levels of 0.98, 0.13 and 0.12 for three different databases. Also, the Bin Miss Rates decreased to 0.3037, 0.4226 and 0.2019 for the investigated databases.

show abstract

Indexing iris images using the Burrows-Wheeler Transform

Cited by 24 publications

References 17 publications

Methods for accuracy‐preserving acceleration of large‐scale comparisons in CPU‐based iris recognition systems

Methods for accuracy‐preserving acceleration of large‐scale comparisons in CPU‐based iris recognition systems

Creating synthetic IrisCodes to feed biometrics experiments

Efficient Classifying and Indexing for Large Iris Database Based on Enhanced Clustering Method

Contact Info

Product

Resources

About