Iris Extraction

Input	Pupil Detection	Iris Detection

Iris Segmentation	Iris Bounding Box	Normalization

Requirements

Python Library	Version
numpy	1.18.1
opencv-python	4.4.0.46
matplotlib	3.0.3

Running

$ python3 iris_extraction.py <input image> [-p] [-s]

Args

• input image (required): path to the grayscale input image.
• plot (optional): if -p or --plot is used, the resulting images will be shown on the screen.
• save (optional): if -s or --save is used, the resulting images will be saved as JPG files.

Testing

I used samples from the MMU iris database to test the code. You can find the database on Kaggle.

References

John Daugman. How Iris Recognition Works. IEEE Transactions on Circuits and Systems for Video Technology, vol. 14, no. 1, 2004. Link.

Shireen Y. Elhabian. Iris Recognition. University of Lousiville, CVIP Lab, 2009. Link.

OpenCV. Hough Circle Transform. Link.

OpenCV. connectedComponentsWithStats. Link.

Wikipedia. Polar Coordinate System. Link.

Cheng Yifeng. IrisReco. GitHub repo. Link.

M. Vinicius Junqueira. IrisRecognition. GitHub repo. Link.

Qingbao Guo. Iris. GitHub repo. Link.