Klasifikasi Citra Oral Lesions sebagai Pencegahan Dini Kanker Mulut Menggunakan Metode Capsule Neural Network

Abstract

In this study, Classification of Oral Lesions Image as Early Prevention of Oral Cancer Using the Capsule Neural Network Method was carried out. The initial step that must be done is to analyze the data that will be used for classification, then analyze several stages of image processing used, such as image processing, featured extraction with the gray level co-occurance matrix feature extraction method and the implementation of the method to be used, namely the Capsule Neural Network for classification. The amount of data processed is 1130 images of oral lesions which is obtained from mendeley data. After classifying the oral lesions image dataset, the lesion image training was carried out to obtain feature extraction values. The experimental results obtained the best accuracy value of 85%.