Recognition of motion blurred iris images

It is inevitable to capture a portion of iris images with motion blur during iris recognition. The texture details on iris patterns are lost in motion blurred images so it may cause recognition performance degradation. This paper presents a first systematic study on the issue of motion blurred iris image recognition. Firstly, the reason of generating motion blurred iris images is analyzed. Secondly, the influence of the strength and the direction of motion blur on the accuracy of iris recognition is quantitatively investigated. Thirdly, we propose two solutions which can be used separately or jointly to improve recognition accuracy on motion blurred iris images. The first solution is a deblur-ring method in preprocessing stage and the other is a motion blur weight map with two generation methods in matching stage. Experimental results on both synthetic and real-world motion blurred iris image databases demonstrate the effectiveness and efficiency of our methods.

[1]  Tieniu Tan,et al.  Iris Matching Based on Personalized Weight Map , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Dinesh Rajan,et al.  Unified Blind Method for Multi-Image Super-Resolution and Single/Multi-Image Blur Deconvolution , 2013, IEEE Transactions on Image Processing.

[3]  K.W. Bowyer,et al.  The Best Bits in an Iris Code , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  John Daugman,et al.  How iris recognition works , 2002, IEEE Transactions on Circuits and Systems for Video Technology.

[5]  Ruigang Yang,et al.  Image deblurring for less intrusive iris capture , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[6]  Frédo Durand,et al.  Understanding and evaluating blind deconvolution algorithms , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[7]  H.M. Wechsler,et al.  Digital image processing, 2nd ed. , 1981, Proceedings of the IEEE.

[8]  Tieniu Tan,et al.  Toward Accurate and Fast Iris Segmentation for Iris Biometrics , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  Seungyong Lee,et al.  Fast motion deblurring , 2009, ACM Trans. Graph..

[10]  Moshe Eizenman,et al.  General theory of remote gaze estimation using the pupil center and corneal reflections , 2006, IEEE Transactions on Biomedical Engineering.

[11]  Kang Ryoung Park,et al.  Real-Time Image Restoration for Iris Recognition Systems , 2007, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[12]  Kang Ryoung Park,et al.  Restoration of motion-blurred iris images on mobile iris recognition devices , 2008 .

[13]  Tieniu Tan,et al.  Comprehensive assessment of iris image quality , 2011, 2011 18th IEEE International Conference on Image Processing.

[14]  Jiaya Jia,et al.  High-quality motion deblurring from a single image , 2008, ACM Trans. Graph..

[15]  Tieniu Tan,et al.  Ordinal Measures for Iris Recognition , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[16]  Paul Wintz,et al.  Digital image processing (2nd ed.) , 1987 .

[17]  Seungyong Lee,et al.  Handling outliers in non-blind image deconvolution , 2011, 2011 International Conference on Computer Vision.

[18]  Tieniu Tan,et al.  Iris Image Deblurring Based on Refinement of Point Spread Function , 2012, CCBR.

[19]  John Daugman,et al.  High Confidence Visual Recognition of Persons by a Test of Statistical Independence , 1993, IEEE Trans. Pattern Anal. Mach. Intell..