IMPLEMENTATION OF THRESHOLD VALUE IN OTSU METHOD FOR BINARY IMAGE

Abstract

The uniqueness of facial geometry is one type of biometric that is often used in authentication systems. The segmentation process by producing a binary image or black and white image, known as facial image binarization, is one of the initial processes to determine the geometric characteristics of a face image. The main problem in this process is determining the threshold value because this value greatly affects the results of the segmentation process. In determining the geometric characteristics of the face, such as the shape of the nose, forehead, lips, and chin, it is necessary to perfect the results of the facial image segmentation process. In this study, the Otsu method was used to determine the threshold value for the segmentation process. The image used is a side view of the face. The side view face image is converted to grayscale with a white background. Based on the test, the Otsu method with a threshold value of T = 250 can provide a side view face image with a binary image that is better than other limits.