Hybrid Feature Extractions and CNN for Enhanced Periocular Identification During Covid-19

Abstract

The global pandemic of novel coronavirus that started in 2019 has seriously affected daily lives and placed everyone in a panic condition. Widespread coronavirus led to the adoption of social distancing and people avoiding unnecessary physical contact with each other. The present situation advocates the requirement of a contactless biometric system that could be used in future authentication systems which makes fingerprint-based person identification ineffective. Periocular biometric is the solution because it does not require physical contact and is able to identify people wearing face masks. However, the periocular biometric region is a small area, and extraction of the required feature is the point of concern. This paper has proposed adopted multiple features and emphasis on the periocular region. In the proposed approach, combination of local binary pattern (LBP), color histogram and features in frequency domain have been used with deep learning algorithms for classification. Hence, we extract three types of features for the classification of periocular regions for biometric. The LBP represents the textual features of the iris while the color histogram represents the frequencies of pixel values in the RGB channel. In order to extract the frequency domain features, the wavelet transformation is obtained. By learning from these features, a convolutional neural network (CNN) becomes able to discriminate the features and can provide better recognition results. The proposed approach achieved the highest accuracy rates with the lowest false person identification.

Investigation of Android Malware with Machine Learning Classifiers using Enhanced PCA Algorithm

“…In this paper, we have created a dataset ensuring system calls, API calls, and permissions with recent exploits and zero-day vulnerabilities. The next step is the creation of a model using supervised learning [25].…”

Pixel-Level Feature Extraction Model for Breast Cancer Detection

“…Object-oriented algorithms, firefly models, and hybrid models have been developed for the segmentation and classification of nuclei. A recent study [3] extracted the color histogram as well as features of texture and the frequency domain from RGB images to identify periocular cancer. Another study [4] used four hybrid algorithms for segmentation: K-means, fuzzy C-means, the comparative learning-based neural network, and Gaussian mixture.…”

Machine Learning for Wireless Sensor Networks Security: An Overview of Challenges and Issues

“…Figure 10 shows the arc mechanism of the CNN algorithm [98]. In the first stage, the process of identifying and extracting feature selections is performed, then the classification process is performed [96]. It is characterized by having one or more hidden layers which extract the attributes in images or videos, and a fully linked layer to produce the desired output [97].…”

“…Convolutional Neural Networks Convolutional Neural Networks (CNNs) are deep learning systems that are comparable to a multi-layer Perceptron at their foundation but differ in what they learn, how they are built, and what their purpose is. Moreover, CNNs are often used in various applications through data analysis.In the first stage, the process of identifying and extracting feature selections is performed, then the classification process is performed[96]. It is characterized by having one or more hidden layers which extract the attributes in images or videos, and a fully linked layer to produce the desired output[97].…”