Ear detection using geomorphic metric and convolutional neural networks
Thiyagarajan Sampath, P. T. Vasanth Raj, Balashenbagam, Manoj Kumar · AIP conference proceedings · 2022
In this paper, we have designed an Ear will identify that person. Nowadays, Biometric identification has a few applications, particularly in the security framework. One of the mainstream biometric recognizable pieces of proof is individual distinguishes through ear because every individual has an extraordinary ear example. It doesn’t change rapidly; it may take less time to change than other identification. In this, we have to capture the person’s ear image, and then we have analyzed the ear image use of image processing and conventional neural network. To enhance the ear images for analysis, we use grayscale histogram features to make the photos fit for the study of ear patterns. We have also used the Feature Extraction technique for calculating the entropy of the image, with the help of entropy value, contrast, and energy. We can find whether the person is authenticated/ accessible or not. Our Approach (with ≥ 75% overlap) and time taken to identify in seconds are 1.77, and the detection rate is 96.35% (331 2D images).