Wyniki wyszukiwania - BazTech

Ograniczanie wyników

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Sortuj według:

Ogranicz wyniki do:

Iris Recognition Based on Local Grey Extremum Values with CNN-based approaches

Malinowski Kamil, Saeed Khalid

Machine Graphics and Vision

2023

Vol. 32, No. 3/4

205--232

One of the most important steps in the operation of biometric systems based on iris recognition of the human eye is pattern comparison. However, the comparison of the recorded pattern with the pattern stored in the database of the biometric system cannot function properly without effective extraction of key features from the iris image. In the presented work, we propose an iris recognition system based on image feature extraction and extreme grey shade analysis. Harris-Laplace, RANSAC and SIFT descriptor algorithms were used to find and describe key points. In the experimental part, two methods were used to compare descriptors: the Brute Force method and the Siamese Network method. IIT Delhi Iris Database (version 1.0), MMU v2 database, UBIRIS v1, UBIRIS v2 image databases were used for the study. The proposed method utilizes a different approach when using the generalized corner extraction algorithm (Harris-Laplace algorithms) for comparing iris patterns. In addition, we prove that the use of the descriptor and the Siamese neural networks significantly improves the results obtained in the original method based on paths alone in the case of well contrasted infrared images with very low resolutions.

An iris segmentation using harmony search algorithm and fast circle fitting with blob detection

Malinowski Kamil, Saeed Khalid

Biocybernetics and Biomedical Engineering

2022

Vol. 42, no. 1

391--403

Pupil and iris segmentation based on ellipsis or circle recognition are sensitive to light reflections and reflected images. The method presented here is independent of size and shape and at the same time insensitive to light reflections and reflected mirror images. The pupil detected using the algorithm can be a reference point to further segmentation of the sclera of the eye as well as of the iris. The method is also effective when the pupil and iris are not positioned perpendicularly to the camera eye. The algorithm’s average segmentation accuracy for all tested databases was 96% when considering only noisy and distorted images whilst a result of 100% was achieved with unblurred and clear images. The proposed method can be quickly and simply reproduced with a combination of known image processing methods. The developed algorithm for detecting the eyelid boundaries is effective with noisy and poor quality images due to the use of edge approximation using the Harmony Search Algorithm. An optimized shape detection method was used to detect the pupil and its edges. A method based on the variation and the average was used to eliminate shadows and eyelashes. The proposed scheme was tested on the UBIRIS.v1 database, MMU.v1 database and MILES databases, providing high results and short segmentation time. Segmentation accuracy for UBIRIS.v1 was 98.14%, for MMU.v1 – 90% and for MILES – 99.8%.