KLASIFIKASI CITRA DIGITAL TULISAN TANGAN ANGKA MENGGUNAKAN METODE CONVOLUTIONAL NEURAL NETWORK

Antonius Angga Kurniawan
Rama Dian Syah
Rizki Ariyani

Jurnal Ilmiah Teknik (JUIT)
Vol. 1 No. 1 (2022): Januari : Jurnal Ilmiah Teknik

Rapid technological advances have led to the development of computer vision science in various fields. This research aims to detect handwriting using deep learning technology with the Convolutional Neural Network (CNN) method. The research stages are data sample selection, data preprocessing, data training, data testing, and evaluation of results. This research succeeded in detecting handwriting with an accuracy value of 0.9800 and a loss value of 0.0665. There are several classification errors because images with numbers are less clear and almost look like numbers that they should not be. The more training data, the more the network will learn so that the accuracy will be better.