Komparasi Metode Backpropagation Neural Network dan Convolutional Neural Network Pada Pengenalan Pola Tulisan Tangan

Comparison of Backpropagation Neural Network and Convolutional Neural Network on Handwriting Pattern Recognition

Abstract

Historical manuscripts are one of documents that important to be preserved because they contain a lot of information, one example of them is script as the historical documents . Historical document mostly still use handwriting in so many reserch. Currently, there are many research regarding the preservation of characters. One way of preservation that can be used is the digitization process. Digitizing’s process tanable by recognizing existing information using technology. The technology that can be used is machine learning. Handwriting is a complex case because of the many variations of these characters and the output of the author where variations of the author will produce different writings. The relevant fields for text and documents are Optical Chacarter Recognition (OCR) and handwriting recognition. There are several methods that can be used in the machine learning process, including Artificial Neural Network (ANN) and Convolutional Neural Network (CNN). Both of these methods are methods that can accept complex image input to be processed and recognized, therefore this method is highly recommended for processing handwriting.