Gate6 Iris Recognition Package

G6_iris_recognition is a module for iris recognition. Using the image processing libraries and high-level mathematical functions, we’ll be providing fast and secure iris recognition solution.

Installation

Installations required before installing the package module

   python 
   numpy
   opencv-python
   matplotlib
   opencv-contrib-python
   requests
   scikit-image
   scipy
   imutils==0.5.2

- Install Python

Windows, Mac, Linux

- Install package module using pip:

  $ pip install G6-iris-recognition

Project Structure

• On your project folder, create an encodingModel directory & in that directory create a file named irisEncodings.pickle(encodingModel/irisEncodings.pickle).
• Create a directory named Input_database & under that directory put an individual's eye iris images, in the directories made on their individual names.

    Project/
    ├── encodingModel/
    │   ├── irisEncodings.pickle/                               # train model
    | 
    ├── Input_database/ 
    │   ├── person1 name/                                       # person1 directory
    |   │   ├── eye iris images of person1 /                    # images of person eye iris
    │   ├── person2 name/                                       # person2 directory
    |   │   ├── eye iris images of person2 /                    # images of person eye iris
    │   ├── person3 name/                                       # person3 directory
    |   │   ├── eye iris images of person3 /                    # images of person eye iris                   

How to use

Once all the settings of project are configured, you are ready to run the project. Import G6_iris_recognition module in your project to start.

   import G6_iris_recognition

Once the import is completed, user need to train existing images which are saved in the Input_database Folder.

   Input_database/

After that, create and train encoding module using Input_database Folder images, as per the instructions given below:

   G6_iris_recognition.iris_model_train(train_database_path,train_encoding_model_path)
   train_database_path        ===>  Input_database/
   train_encoding_model_path  ===>  encodingModel/irisEncodings.pickle

Once the model is trained, it’s ready to test with real-time images. Follow the process that is mentioned to test real time iris image:

   iris_name = G6_iris_recognition.iris_model_test(test_encoding_model_path,real_time_image_path) 
   test_encoding_model_path   ===>  encodingModel/irisEncodings.pickle
   real_time_image_path       ===>  real-time_image_path
   iris_name                  ===>  In response you’ll get the registered person’s name if image matches with the person’s image in the trained image model & if the image doesn’t match then the name returns as unmatched.

Requirements :

• Need clearer images from the scanner.
• Images shouldn't be captured in direct sunlight.
• Person shouldn't wear glasses or lenses while scanning.
• All the scanned images should be of same size/resolution (eg - 320x240).
• The parameters of filters need to be changed as per the size and quality/noise of the images.
• 90% of the eye iris needs to be captured.
• Minimum 5 clear images are required to train the model.
• Once everything is done accordingly, set threshold of Hamming Distance for easier recognition.

Support

If you face any difficulty in configuration or usage of Gate6 Iris Recognition Package as per the instructions documented above, please feel free to contact our development team.

License

MIT