Synthetic Iris Model Based

Data Release Information

Dataset records are made available to researchers only after the receipt and acceptance of a completed and signed Database Release Agreement

Data Release Protocol (broken link)

Please submit requests for the dataset unless otherwise indicated:

WVUBiometricData@mail.wvu.edu


The gallery of synthetic iris images are generated in five steps using a model based, anatomy based approach, with 40 controllable random parameters such as fiber size, pupil size, iris thickness, top layer thickness, fiber cluster degree, iris root blur range, the location of the collaret, the amplitude of the collaret, top layer transparency parameter, eye angle, eye size etc. The software coded with Matlab, generates 10000 classes (5000 subjects, left and right eye). Each class has 16 images, 1 good quality image, 15 degenerated images, with combination effects among noise, rotation, blur, motion blur, low contrast and specular reflection. For each image segmentation results ( unwrapped template, enhanced template and occlusion mask) are provided.

Performance is evaluated using a traditional Gabor filter based system. A comprehensive comparison of synthetic and real data is performed at three levels of processing: (1) image level, (2) texture level , and (3) decision level. A sensitivity analysis is performed to conclude on importance of various parameters involved in generating iris images.

1.  Generate continuous fibers in 3D cylindrical coordinates.

iris_model_step1

 

2.  Project 3D fibers into a 2D flat image space.

iris_model_step2

 

3.  Transform the basis image to include the effect of collaret. Add a semitransparent top layer with an irregular edge.

iris_model_step3

 

4.  Blur the iris root and add a random bumpy pattern to the top layer.

iris_model_step4

 

5.  Add the eyelids at a certain degree of opening and randomly generated eyelashes.

iris_model_step5

 

Examples of synthetic iris images:

iris_model8 iris_model7 iris_model6 iris_model5

iris_model4 iris_model3 iris_model2 iris_model1

When using synthetic iris images please cite:
Zuo J., Natalia A. Schmid,_ On Generation and Analysis of Synthetic Iris Images,_ IEEE Transactions on Information Forensics and Security, volume 2, issue 1, March 2007, pages 77 to 90.