Image quality assessment for iris biometric

Kalka, Nathan D.; Zuo, Jinyu; Schmid, Natalia A.; Čukić, Bojan

doi:10.1117/12.666448

Cited by 112 publications

(45 citation statements)

References 15 publications

(11 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, it is expected that the captured images contain off-angle and partial irises and are blurred (due to bad focus or motion). Some of these noise factors were recently addressed by several authors (e.g., [12] and [13]). …”

Section: Noncooperative Iris Recognitionmentioning

confidence: 99%

Toward Noncooperative Iris Recognition: A Classification Approach Using Multiple Signatures

Proença

Alexandre

2007

IEEE Trans. Pattern Anal. Machine Intell.

177

View full text Add to dashboard Cite

Abstract-This paper focus on noncooperative iris recognition, i.e., the capture of iris images at large distances, under less controlled lighting conditions, and without active participation of the subjects. This increases the probability of capturing very heterogeneous images (regarding focus, contrast, or brightness) and with several noise factors (iris obstructions and reflections). Current iris recognition systems are unable to deal with noisy data and substantially increase their error rates, especially the false rejections, in these conditions. We propose an iris classification method that divides the segmented and normalized iris image into six regions, makes an independent feature extraction and comparison for each region, and combines each of the dissimilarity values through a classification rule. Experiments show a substantial decrease, higher than 40 percent, of the false rejection rates in the recognition of noisy iris images.

show abstract

Section: Noncooperative Iris Recognitionmentioning

confidence: 99%

Toward Noncooperative Iris Recognition: A Classification Approach Using Multiple Signatures

Proença

Alexandre

2007

IEEE Trans. Pattern Anal. Machine Intell.

177

View full text Add to dashboard Cite

show abstract

“…The authors compared the efficiency of their metric with existing ones according two types of alterations (occlusions and blurring) which may significantly decrease the performance of iris recognition systems. Other iris quality metrics are presented in [21,22].…”

Section: Alonso-fernandez Et Al (2007)mentioning

confidence: 99%

Evaluation of Biometric Systems

El-Abed¹,

Giot²,

Rosenberger³

2012

New Trends and Developments in Biometrics

View full text Add to dashboard Cite

International audienceBiometrics is considered as a promising solution among traditional methods based on "what we own" (such as a key) or "what we know" (such as a password). It is based on "what we are" and "how we behave". Few people know that biometrics have been used for ages for identification or signature purposes. In 1928 for example, fingerprints were used for women clerical employees of Los Angeles police department as depicted in Figure 1. Fingerprints were also already used as a signature for commercial exchanges in Babylon (-3000 before JC). Alphonse Bertillon proposed in 1879 to use anthropometric information for police investigation. Nowadays, all police forces in the world use this kind of information to resolve crimes. The first prototypes of terminals providing an automatic processing of the voice and digital fingerprints have been defined in the middle of the years 1970. Nowadays, biometric authentication systems have many applications [1]: border control, e-commerce, etc. The main benefits of this technology are to provide a better security, and to facilitate the authentication process for a user. Also, it is usually difficult to copy the biometric characteristics of an individual than most of other authentication methods such as passwords. Despite the obvious advantages of biometric systems, their proliferation was not as much as attended. The main drawback is the uncertainty of the verification result. By contrast to password checking, the verification of biometric raw data is subject to errors and represented by a similarity percentage (100% is never reached). Others drawbacks related to vulnerabilities and usability issues exist. In addition, in order to be used in an industrial context, the quality of a biometric system must be precisely quantified. We need a reliable evaluation methodology in order to put into obviousness the benefit of a new biometric system. Moreover, many questions remain: Shall we be confident in this technology? What kind of biometric modalities can be used? What are the trends in this domain? The objective of this chapter is to answer these questions, by presenting an evaluation methodology of biometric systems

show abstract

“…According to their study, the focus, the eye movement and the view angle degrade more the performances. They analyzed the high frequency components to measure the degree of blur due to camera distance and the directional properties of the Fourier spectrum for the blur due to the movement (Kalka et al, 2006). To evaluate the angle of view, they measured the circularity of iris by applying an integro-differential operator to different images obtained by projecting the original image at different angles.…”

Section: Quality Measures In the Frequential Domainmentioning

confidence: 99%