Individual Recognition Using Histogram of Oriented Gradients
5 Pages Posted: 17 Oct 2018
Date Written: October 17, 2018
This paper discusses a face identification approach. The approach consists of preprocessing, feature extraction using histogram of oriented gradients and classification using K-Nearest Neighbor method. We have implemented the discussed algorithm using MATLAB. Furthermore, we have applied the method to a case study. The case study consists of 225 images taken from 45 individuals. Those images are divided into training data (180 images from 45 individuals) and testing data (45 images from 45 individuals). According to our simulation, the average accuracy is approximately 80%, where the highest accuracy is attained when K = 1 is used in the classification.
Suggested Citation: Suggested Citation