Multi Scale ICA Based IRIS Recognition Using BSIF and HOG

Sagar, G. Vidhya; Nc, Abidali Munna; K, Suresh Babu; Raja, Kiran B.; Venugopal, K R

doi:10.5121/sipij.2017.8602

Cited by 3 publications

(2 citation statements)

References 18 publications

(20 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ujwalla et al, [19] applied local binary pattern on segmented iris image to extract the significant details of iris image. Sagar et al, [23] adopted multi ICA and HOG techniques to produce the iris features. Further the iris images are matched using Euclidean distance classifier.…”

Section: Comparison Of Proposed Methods With Existing Methodsmentioning

confidence: 99%

Performance Analysis of MSB Based Iris Recognition Using Hybrid Features Extraction Technique

Harakannanavar¹,

Prashanth²,

Raja³

2019

IJEAT

Self Cite

View full text Add to dashboard Cite

In the modern days, biometric identification is more promising and reliable to verify the human identity. Biometric refers to a science for analyzing the human characteristics such as physiological or behavioral patterns. Iris is a physiological trait, which is unique among all the biometric traits to recognize an individual effectively. In this paper, MSB based iris recognition based on Discrete Wavelet Transform, Independent Component Analysis and Binariezed Statistical Image Features is proposed. The left and right region is extracted from eye images using morphological operations. Binary split is performed to divide the eight-bit binary of every pixel into four bit Least Significant Bits and four bit Most Significant Bits. DWT is applied on four bit MSB to extract the iris features. Then ICA is applied on approximate sub band to extract the significant details of iris. The obtained features are then applied on BSIF to obtain the enhanced response with final features. Finally features produced are matched with the test features using Euclidean distance classifier on CASIA database. The experiments are performed on proposed iris model using MATLAB 7.0 software considering various combinations of Person inside Database (PID’s) and Person outside Database (POD’s) to evaluate the recognition accuracy of the proposed iris model.

show abstract

Section: Comparison Of Proposed Methods With Existing Methodsmentioning

confidence: 99%

Performance Analysis of MSB Based Iris Recognition Using Hybrid Features Extraction Technique

Harakannanavar¹,

Prashanth²,

Raja³

2019

IJEAT

Self Cite

View full text Add to dashboard Cite

show abstract

“…The two dimensional Gabor filters was adopted to extract phase information of an iris image. Sagar et al, [25] explains multi ICA and HOG techniques to produce the iris features. Further the iris images are matched using Euclidean distance classifier.…”

Section: Performance Analysismentioning

confidence: 99%

Performance Analysis of Iris Recognition Using Multi Stage Wavelet Transform Decomposition and Bicubic Interpolation Technique

Harakannanavar¹,

Prashanth²,

Raja³

2019

IJEAT

Self Cite

View full text Add to dashboard Cite

Biometric identification is highly reliable for human identification. Biometric is a field of science used for analyzing the physiological or behavioural characteristics of human. Iris features are unique, stable and can be visible from longer distances. It uses mathematical pattern-recognition techniques on video images of one or both iris of an individual's. Compared to other biometric traits, iris is more challenging and highly secured tool to identify the individual. In this paper iris recognition based on the combination of Discrete Wavelet Transform (DWT), Inverse Discrete Wavelet Transform (IDWT), Independent Component Analysis (ICA) and Binariezed Statistical Image Features (BSIF) are adopted to generate the hybrid iris features. The first level and second level DWT are employed in order to extract the more unique features of the iris images. The concept of bicubic interpolation is applied on high frequency coefficients generated by first level decomposition of DWT to produce new set of sub-bands. The approximation band generated by second level decomposition of DWT and new set of sub-bands produced by second level decomposition of DWT are applied on IDWT to reconstruct the coefficients. The ICA 5x5 filters and BSIF are adopted for selecting the appropriate images to extract the final features. Finally based on the matching score between the database image and test image the genuine and imposters are identified. Using CASIA database, training and testing of the features is performed and performance is evaluated considering different combinations of Person inside Database (PID) and Person outside Database (POD).

show abstract