<![CDATA[Iris recognition is a secure and reliable biometric identification system for user detection. Used to take a portrait of a person. This system was created by combining the artificial neural learning method with genetic algorithms. Implementation of this recognition system through several processes, namely the collection of iris data, iris data obtained through the acquisition process with image output. The recognition system was built using Matlab software, and the obtained images were separated into two parts: training images and test images. The training image is pre-processed. The iris recognition system's performance is evaluated using segmentation. Segmentation is used to locate the right iris region in a certain section of the eye and must be done exactly and accurately to eliminate the iris area's eyelashes, eyelids, reflections, and pupillary noise. We use the Daughman Algorithm segmentation of Iris Recognition in this study. In this research, we apply Daughman Algorithm segmentation for Iris Recognition. To reduce dimensional differences across the iris area, the segmented iris regions were normalized. The convolution theorem is used to code the characteristics of the iris. As a match metric, Hamming distance is included, which offers a count of how many mismatched bits there are between the iris templates. Pre-processing aids the identification, which includes training and testing. The pre-processing findings are used as input data in the training phase, whereas test image data is used in the testing phase. The use of artificial neural learning as well as a genetic algorithm to detect the iris pattern is effective and achieves the objectives. This is corroborated by the 95% recognition accuracy rate. According to the test findings, the clarity of the produced iris picture, the number of hidden mark sheet, the quantity of epoch parameters, as well as the appearance of the training sample are the criteria that determine the system's recognition rate.]]>
Copyrights © 2022
