The Utilization of Padding Scheme on Convolutional Neural Network for Cervical Cell Images Classification
Toto Haryanto, Imas Sukaesih Sitanggang, Muhammad Asyhar Agmalaro, Riries Rulaningtyas
Abstract
Cervical cancer identification through pap-smear images analysis is a challenge for medicians, especially in distinguishing cells, between the normal and abnormal one. This study aims to create the classification model of Cervical Cell Images using the Convolutional Neural Network (CNN) algorithm. The dataset used is the image dataset SIPaKMeD. The CNN algorithm was implemented using the AlexNet architecture with and non-padding scheme. Padding is included in the experiments by adding the pixel 0 on the original images to improve the accuracy of the model. The experimental results show that using the utilization padding scheme on the AlexNet architecture can increase the accuracy of the model slightly significantly from 84.88% to 87.32%.