Iris Image Quality Assessment Research Articles

Possibilistic Reasoning based No-Reference Iris Image Quality Assessment

Low quality of data is one of the most critical issues for consumers of data distributed by autonomous sources. The outcomes of non-quality of data, or of poor quality, on decision-making are considerable and have disastrous effects. In this paper, we deal with this problem in the context of biometric applications, specifically those based on the iris modality. In fact, the iris image can be affected by different types of distortion which greatly affect its quality and generate different imperfection forms. Thus, the deterioration of the quality of these images increases the false rejection rate and therefore decreases significantly the performances of iris identification systems. In order to reduce the impact of bad quality of iris image, we add an Image Quality Assessment (IQA) phase to the identification system to reject poor quality images and thus improves system performances. In this paper, a new method based on the possibilistic modeling of imperfect information extracted from the iris images is proposed to assess the iris image quality. The aim of the proposed approach, noted Poss-IIQA, is to handles the different imperfection forms resulting from any type of distortions. As a result, the suggested method key advantage over the baseline system and other earlier approaches, which focuses more on distortions than on imperfections.

Iris image quality assessment based on ISO/IEC 29794-6:2015 standard

Iris image quality assessment based on ISO/IEC 29794-6:2015 standard

虹膜图像的质量评价研究

虹膜图像的质量评价研究

The research on adaptive fast iris capture and online iris image quality assessment algorithm

In this paper, we developed the adaptive fast iris capture device, and proposed a new online iris image quality assessment algorithm which combines pupil coarse location. On ARM embedded system of iris image capture, iris quality is real-time assessment, combined with feedback control to adjust light source, focal length, pupil contraction LED, etc. It does not require the user actively move to cooperate with the device during iris capture. The qualified iris image is transmitted through the USB interface to the host computer. Finally, we establish the iris library (has captured more than 1000 iris samples), and the capture device and iris quality assessment algorithm has been tested. The average capture can be completed within 1s. The test of iris recognition proved that the iris capture device and iris image quality assessment algorithm is valid.

Iris Recognition for Personal Identification System

In general, a typical iris recognition based Personal Identification System (PIS) includes iris imaging, iris image quality assessment, fake iris detection, and iris recognition. This paper presents a novel approach, which focusing on iris recognition. The novelty of this approach includes improving the speed and accuracy of the iris segmentation process, fetching the iris image so as to reduce the recognition error, producing a feature vector with discriminating texture features and a proper dimensionality so as to improve the recognition accuracy and computational efficiency. The Canny edge detection and circular Hough transforms are used for the segmentation process. The segmented iris is normalized using Daugman's rubber sheet model from –[32°,32°] and [148°,212°]. The phase data from 1D Log-Gabor filter is extracted and encoded efficiently to produce a proper feature vector. Experimental tests were performed using CASIAIrisV3 and UBIRIS iris databases. These tests prove that the proposed algorithm has an encouraging performance.

Hardware Architecture Optimized for Iris Recognition

One of the remaining problems in iris recognition is the implementation of its efficient hardware systems. The difficulty arises from the fact that the methods forming part of this type of authentication process are fairly complex. Furthermore, next generation algorithms for iris recognition will become even more complex to enhance the reliability and functionality of currently used solutions. An example of such an intensive processing task is iris image quality assessment and segmentation using video signal obtained at-a-distance and on-the-move. Thus, processing robustness and predictable analysis time in such dedicated architectures may be particularly important. This paper describes a hardware system designed to analyze iris biometric data developed as a part of the work conducted by the authors on the complete iris identification system (1:N). This specialized architecture is mainly composed of digital signal processors and field-programmable gate arrays. Several issues concerning efficient biometric sample processing are discussed. Algorithms for iris recognition previously developed by the authors on a PC platform were adapted to the described architecture. The obtained results are presented, and the developed system is compared with chosen commercially available iris authentication systems.

Automated personal identification system based on human iris analysis

In general, a typical iris recognition system includes iris imaging, iris liveness detection, iris image quality assessment, and iris recognition. This paper presents an algorithm focusing on the last two steps. The novelty of this algorithm includes improving the speed and accuracy of the iris segmentation process, assessing the iris image quality such that only the clear images are accepted so as to reduce the recognition error, and producing a feature vector with discriminating texture features and a proper dimensionality so as to improve the recognition accuracy and computational efficiency. The Hough transform, polynomial fitting technique, and some morphological operations are used for the segmentation process. The phase data from 1D Log-Gabor filter is extracted and encoded efficiently to produce a proper feature vector. Experimental tests were performed using CASIA iris database (756 samples). These tests prove that the proposed algorithm has an encouraging performance.