Indexing Iris Biometric Database Using Energy Histogram of DCT Subbands

Mehrotra, Hunny; Srinivas, Badrinath G.; Majhi, Banshidhar; Gupta, Phalguni

doi:10.1007/978-3-642-03547-0_19

Cited by 24 publications

(14 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An indexing approach based on the histogram of energy derived from the texture of iris was proposed [24]. The energy histogram was used for indexing iris database.…”

Section: Two Methods Have Been Proposed By Mukherjeementioning

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

“…An indexing approach based on the histogram of energy derived from the texture of iris was proposed [24]. The energy histogram was used for indexing iris database.…”

Section: Two Methods Have Been Proposed By Mukherjeementioning

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

show abstract

“…An efficient indexing scheme based on energy histogram obtained from the iris texture was proposed in [9]. Image is stored into the database along with a key during enrolment.…”

Section: Based On Iris Texturementioning

confidence: 99%

Iris Indexing Techniques: A Review

Poonguzhali¹,

Ezhilarasan²

2013

IJCA

View full text Add to dashboard Cite

The objective of this paper is to present the state of art in iris indexing. The potential raise of accurateness along with enhanced robustness beside forgeries makes in fact iris recognition a promising field for research. The performance of a biometric system is evaluated based on the retrieval time and error rate which are dependent on the size of the database and hence the need for indexing. Iris indexing can be categorized based on the texture analysis, color and SFIT key point. Further the paper discusses the description of some databases used for indexing techniques to prove the efficiency. The performance evaluation metrics are also discussed.

show abstract

“…In our case θ = π 4 and σ = 0.0916. Another set of features that was proposed for iris indexing was DCT coefficients in various subbands [13]. After normalizing for pose and illumination variations using an adaptive histogram equalization, image is divided into non-overlapping 8×8 pixel blocks and are transformed to generate DCT coefficients.…”

Section: B Effect Of Feature Representationmentioning

confidence: 99%

“…Unfortunately the method performs poorly with larger feature vectors such as Gabor responses of IRIS images. Mehrotra et al [13] proposed the use of ordered DCT coefficients for indexing a dataset of IRIS images. The authors were able to prune the database to around 2.6% with an FNIR of 35.6%.…”

Section: Introductionmentioning

confidence: 99%

Cascaded filtering for biometric identification using random projections

Iqbal

Namboodiri

2011

2011 National Conference on Communications (NCC)

View full text Add to dashboard Cite

Abstract-Biometric identification often involves explicit comparison of a probe template against each template stored in a database. This approach becomes extremely time-consuming as the size of the database increases. Filtering approaches use a light-weight comparison to reduce the database to smaller set of candidates for explicit comparison. However, most existing filtering schemes use specific features that are hand-crafted for the biometric trait at each stage of the filtering. In this work, we show that a cascade of simple linear projections on random lines can achieve significant levels of filtering. Each stage of filtering consists of projecting the probe onto a specific line and removal of database samples outside a window around the probe. The approach provides a way of automatic generation of filters and avoids the need of developing specific features for different biometric traits. The method also provides us with a variety of parameters such as the projection lines, the number and order of projections, and the window sizes to customize the filtering process to a specific application. Experimental results show that using an ensemble of projections reduce the search space by 60% without increasing the false negative identification rate.

show abstract

Indexing Iris Biometric Database Using Energy Histogram of DCT Subbands

Cited by 24 publications

References 9 publications

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

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

Iris Indexing Techniques: A Review

Cascaded filtering for biometric identification using random projections

Contact Info

Product

Resources

About