RIDB: A Dataset of fundus images for retina based person identification

Abstract

The paper describes a dataset, entitled Retina Identification Database (RIDB). The stated dataset contains Retinal fundus images acquired using Fundus imaging camera TOPCON-TRC 50 EX. The abovementioned dataset holds a significant position in retinal recognition and identification. Retinal recognition is considered as one of the reliable biometric recognition features. Biometric recognition has become an integral part of any organization's security department. Before biometrics, the information was secured through passwords, pin keys, etc. However, the fear of decryption and hacking retained. Biometric verification includes behavioural (voice, signature, gait), morphological (Fingerprint, face, palm print, retina) and biological (Odour, saliva, DNA) features [1] . Amongst all of them, retina based identification is considered as the spoof proof and most accurate identification system. Since the retina is embedded inside the eye thus is least affected by the outer environment and retain in its original state. Moreover, the vascular pattern in the retina is unique and remains unchanged during the entire life span. The data presented in the paper is composed of 100 retinal images of 20 individuals (5 images were captured from each patient). The dataset is supported by research work [2] and [7] . These research papers proposed retinal recognition algorithms for biometric verification and identification. The proposed method utilized both vascular and non-vascular features for identification and yields recognition rates of 100 % and 92.5% respectively.

Human retinal biometric recognition system based on multiple feature extraction

“…This paper has utilized the following four standardized databases: RIDB, VARIA, DRIVE, and STARE. Among the four, the following two were publicly available retinal image datasets for authentication purposes: RIDB 41 (Fatima et al 42 43 …”

“…This paper has utilized the following four standardized databases: RIDB, VARIA, DRIVE, and STARE. Among the four, the following two were publicly available retinal image datasets for authentication purposes: RIDB 41 (Fatima et al 42 ) and VARIA (Ortega et al 43 ). These cation databases contained a large number of images captured at various times for each individual.…”

Deep Learning Model for Static Ocular Torsion Detection Using Synthetically Generated Fundus Images

“…We adopted Adam optimization, 37 an extended version of the stochastic gradient descent algorithm with better computational efficiency, for model weights decay with the default learning rate of 0.001.…”

“… 36 Access to fundus images for research has become difficult, both because pathologic fundus torsion datasets are sparse and heightened concern for patient privacy, as fundus photographs can be used for biometric identification. 37 Three possible solutions to address model training when data are scarce include (1) data augmentation (introduce more variations), 36 (2) transfer learning (enhance training by using previously learned features for a new task), 38 , 39 and (3) synthetic image generation (increase dataset size). 40 – 42 Using these strategies, two deep learning-based static torsional classifiers to differentiate the direction (intorsion versus extorsion) and amount (physiologic versus pathologic) of static ocular torsion from a small digital fundus image dataset were developed.…”

A Survey on Automatic Diabetic Retinopathy Screening

“…This dataset comprises of 33 healthy retina and 7 disease images and all annotations for vessel segmentation is given for all images by medical experts [19]. [23].…”