PERSON IDENTIFICATION BASED ON LOW QUALITY EYE IMAGES USING ARTIFICIAL INTELLIGENCE

Abstract

Contactless person identification in hospital during COVID-19 pandemic based on low quality images is very important. The low quality of eye images can be resulted by low-resolution camera in the mobile phone or moving eyes. In this paper, we proposed a method to identify person in the hospital based on low quality images. The eye images capture using low-resolution camera or moving camera. The proposed system employs an image segmentation algorithm and compares three different machine learning approaches for effectively classifying each segmented region as the appropriate recognition type using Cascade Trainer: neural networks, support vector machines, and random forest decision trees. The use of a wrapper technique combined with recursive feature reduction is proven to be successful in maintaining the classifiers' performance while considerably lowering the number of required predictors. The results obtained with Jupyter demonstrate that classifiers based on fitted neural networks, random forest models, and support vector machines achieve high overall accuracy on a testing with significant differences for the purpose of this project is to provide a consistent and robust methodological framework for the creation of trustworthy computational systems to assist eye recognition for patient identification by using standard classification methods. The preliminary findings of this study suggest that based on eyes images of the classes collected in the dataset can be autonomously recognize.