Toward Accurate and Fast Iris Segmentation for Iris Biometrics

  title={Toward Accurate and Fast Iris Segmentation for Iris Biometrics},
  author={Zhaofeng He and Tieniu Tan and Zhenan Sun and Xianchao Qiu},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
  • Zhaofeng He, T. Tan, Xianchao Qiu
  • Published 1 September 2009
  • Computer Science
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
Iris segmentation is an essential module in iris recognition because it defines the effective image region used for subsequent processing such as feature extraction. Traditional iris segmentation methods often involve an exhaustive search of a large parameter space, which is time consuming and sensitive to noise. To address these problems, this paper presents a novel algorithm for accurate and fast iris segmentation. After efficient reflection removal, an Adaboost-cascade iris detector is first… 
An accurate and easy method towards iris localization
  • Pengwei Yu, M. Xie
  • Computer Science
    2010 The 2nd International Conference on Computer and Automation Engineering (ICCAE)
  • 2010
This paper proposes a new method in iris segmentation that is excellent in both accuracy and speed and modified neighbor function criterion algorithm originated from the pattern recognition is adopted.
A Fast and Accurate Iris Segmentation Approach
A novel algorithm for accurate and fast iris segmentation is presented, using a gray histogram-based adaptive threshold to generate a binary image, followed by connected component analysis, and rough pupil is separated.
Robust iris segmentation based on learned boundary detectors
Extensive experiments on the challenging CASIA-Iris-Thousand iris image database demonstrate the effectiveness of the proposed iris segmentation method based on specific edge detectors.
Robust Iris Segmentation Based on Local Image Gradient Properties
A robust and accurate iris segmentation algorithm for closed-up NIR eye images is developed and reduced false negative rate of the iris recognition system by half, compared to results obtained using Masek's method.
Efficient and robust segmentation of noisy iris images for non-cooperative iris recognition
Fast and reliable iris segmentation algorithm
Experimental results demonstrate that the proposed iris segmentation algorithm significantly minimises the required time to segment the iris without affecting the segmentation accuracy, and the comparison results show the superiority of the proposed algorithm in terms of segmentsation accuracy and recognition performance.
Fast and Efficient Iris Image Segmentation
It is demonstrated that the proposed iris segmentation algorithm outperforms some well-known methods in both accuracy and processing speed, and is capable of offering recognition performances comparable with those reported by other state-of-the-art methods.
A robust preprocessing algorithm for iris segmentation from low contrast eye images
An image pre-processing algorithm for robust iris segmentation of low contrast images, aimed at reducing mis-localization errors of basic curve-fitting algorithms.
A Novel Iris Location Method for Fast Iris Recognition
A novel iris location method, based on rotation average analysis of intensity-inversed image, is presented here for iris segmentation, which shows faster and robust properties in locating the pupillary and limbus boundaries with higher tolerance of faintness and scaling.


Active shape models for effective iris segmentation
Effective use of active shape models (ASMs) for doing iris segmentation is demonstrated and a method for building flexible model by learning patterns of iris invariability from a well organized training set is described.
Iris Localization via Pulling and Pushing
This paper proposes a novel iris localization method based on a spring force-driven iteration scheme that is faster and more accurate than state-of-the-art iri localization methods.
Efficient iris recognition by characterizing key local variations
The basic idea is that local sharp variation points, denoting the appearing or vanishing of an important image structure, are utilized to represent the characteristics of the iris.
A new iris segmentation method for recognition
Experimental results on a set of 2,096 images show that the proposed method based on the fusion of edge and region information has encouraging performance for improving the recognition accuracy.
IRIS Segmentation: Detecting Pupil, Limbus and Eyelids
An active contour model to accurately detect pupil boundary is presented to improve the performance of iris recognition systems and an iterative algorithm has been developed in order to capture limbus and eyelids.
The relative distance of key point based iris recognition
Iris recognition: an emerging biometric technology
Iris recognition as one of the important method of biometrics-based identification systems and iris recognition algorithm is described and experimental results show that the proposed method has an encouraging performance.
Experiments with an improved iris segmentation algorithm
An improved iris segmentation and eyelid detection stage of the algorithm is developed and implemented, which leads to an increase of over 6% in the rank-one recognition rate.
Boosting ordinal features for accurate and fast iris recognition
A novel iris recognition method based on learned ordinal features, which outperforms Adaboost in terms of both accuracy and generalization capability across different iris databases and the well-known cascade architecture is adopted to reorganize the learned SOBoost classifier into a dasiacascadepsila.
Performance evaluation of non-ideal iris based recognition system implementing global ICA encoding
A series of receiver operating characteristics (ROCs) demonstrates various effects on the performance of the non-ideal iris based recognition system implementing the global ICA encoding.