Retinal biometric identification using convolutional neural network

Abstract

Authentication is needed to enhance and protect the system from vulnerabilities or weaknesses of the system. There are still many weaknesses in the use of traditional authentication methods such as PINs or passwords, such as being hacked. New methods such as system biometrics are used to deal with this problem. Biometric characteristics using retinal identification are unique and difficult to manipulate compared to other biometric characteristics such as iris or fingerprints because they are located behind the human eye thus they are difficult to reach by normal human vision. This study uses the characteristics of the retinal fundus image blood vessels that have been segmented for its features. The dataset used is sourced from the DRIVE dataset. The preprocessing stage is used to extract its features to produce an image of retinal blood vessel segmentation. The image resulting from the segmentation is carried out with a two-dimensional image transformation such as the process of rotation, enlargement, shifting, cutting, and reversing to increase the quantity of the sample of the retinal blood vessel segmentation image. The results of the image transformation resulted in 189 images divided with the details of the ratio of 80 % or 151 images as training data and 20 % or 38 images as validation data. The process of forming this research model uses the Convolutional Neural Network method. The model built during the training consists of 10 iterations and produces a model accuracy value of 98 %. The results of the model's accuracy value are used for the process of identifying individual retinas in the retinal biometric system.

Automated model for identification on mastoid of temporal bone image

“…In carrying out the object extraction process, an image that has been generated from the segmentation and morphology process is needed with the aim of obtaining characteristics that can distinguish an object from other objects in the image [40]. To distinguish the features of the object to be analyzed, the separation is carried out by calculating the pixel statistics on the image object and determining the input value or parameter [41]. The parameters used in object extraction are shown in the (5).…”

Modeling mental peculiarities of a decision maker by a Fourier-holography technique

“…Из анализа выражений Из (19), (20) следует, что V St (граница нарушения классической формулы полной вероятности) зависит от параметров как спектров записанных на голограммах эталонных образов, так и НЧФ, возникающей на голограммах вследствие нелинейности ЭХ ГРС. Для наглядности на рис.…”

“…Задача объяснения аргументации и логики принятия решения особо остро стоит в тех областях, где цена ошибки неприемлемо высока: военном деле [11 -13], медицине [14 -18], энергетике [19], распознавании лиц и объектов [6,20,21] etc. Термин «принятие решения» в статье используется в смысле выбора из альтернатив (decision making), что точно соответствует сути ситуаций с высокой ценой ошибки [10 -18].…”

Biometric System for Person Authentication Using Retinal Vascular Branching Pattern

“…Research [7] was using hit or miss transformation to obtain bifurcation and crossover points on retinal blood vessel images. Retinal biometric system feature extraction research was carried out [8] using preprocessing, where the output of this feature extraction process is a binary image of retinal blood vessel segmentation that has undergone various processes of eliminating nonvascular objects and improving image quality. The purpose of performing this image transformation is to increase the quantity of the existing image but still not eliminate the biometric features of the image.…”

“…There was an error in the extraction carried out in this study where the central branch artery and vein were detected as non-blood vessels so that this object was removed and considered as noise. The feature extraction results are entered into the CNN model in forming the retinal biometric system [8]. Research to detect bifurcation and crossover was done by using the morphological operations of opening, closing, and watershed transformation.…”