UTILIZATION OF HISTOGRAM OF ORIENTED GRADIENTS AND MACHINE LEARNING IN FACE RECOGNITION SYSTEM

• Main Author: Ervandy Rachmat, Muhammad
• Format: Final Project
• Language: Indonesia
• Online Access: https://digilib.itb.ac.id/gdl/view/76160
• Institution: Institut Teknologi Bandung

The development of computer science and technology in recent years has experienced great developments, this time there are types of technology that digitize almost everything related to human life, including human facial recognition. In recent years various methods for recognizing human faces have developed, one of them is using the Histogram of Oriented Gradients (HOG). On this occasion, an image processing system will be designed to recognize human faces using Histograms of Oriented Gradients (HOG) and machine learning such as Convolutional Neural Networks (CNN), and Support Vector Machines (SVM). detects the winking of the face, using computer-recognizable points in the eye area from 68 facial landmarks, so from these results the distance between the upper and lower eyelids can be measured, which if the distance (in pixels) is small enough, it can be interpreted as a wink. In addition, it is also limited by the distance of faces that can be detected to blink. In the end, if the blinking of a recognized face is detected, the time and date will be recorded which will then also open a solenoid lock using serial communication via Arduino Uno so that it can become a security system. From 100 facial photos and 207 blink tests, 89.86% found that the computer could detect a "True Positive" wink, besides that the recommended tolerance parameter value for this facial recognition system is between 0.42 to 0.48.