Prediksi pada pengenalan tulisan tangan (handwriting recognition)

Isna Ganggalia, Nurul (2018) Prediksi pada pengenalan tulisan tangan (handwriting recognition). Project Report. studentstaff5, Perpustakaan Institut Teknologi Telkom Purwokerto. (Unpublished)

	Text COVER.pdf Download (257kB)
Preview	Text ABSTRAK.pdf Download (26kB) | Preview
Preview	Text ABSTRACT.pdf Download (26kB) | Preview
Preview	Text BAB I.pdf Download (162kB) | Preview
	Text BAB II.pdf Restricted to Registered users only Download (92kB) | Request a copy
	Text BAB III.pdf Restricted to Registered users only Download (431kB) | Request a copy
	Text BAB IV.pdf Restricted to Registered users only Download (40kB) | Request a copy
Preview	Text DAFTAR PUSTAKA.pdf Download (28kB) | Preview
Preview	Text LAMPIRAN.pdf Download (38kB) | Preview

Abstract

Humans have different handwriting patterns and unique. Reading handwriting is easy for humans, but a difficult task for computers. Handwriting Recognition is the ability of the system to receive handwritten input that can be understood from sources such as paper documents, photographs and more. The purpose of creating handwriting recognition as a form of automation of readings obtained from handwriting input. This study discusses how a system can recognize a digital image pattern in the form of handwriting letter recognition that uses a more in-depth branch of machine learning, namely deep learning. The method used is Convoutional Neural Network (CNN). The implementation of CNN in this study uses a Keras library and uses the Python programming language. Making prediction is the final step in this project, making prediction process after obtaining data in the form of models. This system is able to recognize and provide outputs from both digit and alphabet handwriting predictions. Keyword : CNN, deep learning, keras, prediction, handwriting

Actions (login required)

View Item