Article Per Year (5 Year)
p-Index From 2019 - 2024
0.983
P-Index
This Author published in this journals
All Journal Energy : Jurnal Ilmiah Ilmu-Ilmu Teknik Technologia: Jurnal Ilmiah Jurnal Aplikasi Teknologi Informasi dan Manajemen (JATIM)
Hoiriyah Hoiriyah
Unknown Affiliation
Aerospace Engineering Automotive Engineering Chemical Engineering, Chemistry & Bioengineering Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Electrical & Electronics Engineering Energy Engineering Industrial & Manufacturing Engineering Mechanical Engineering

Published : 7 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search
Journal : Energy : Jurnal Ilmiah Ilmu-Ilmu Teknik

 1 
Sistem Pengenalan Citra Dokumen Tanda Tangan Menggunakan Metode CNN (Convolutional Neural Network) Raudlatul Jannah; Miftahul Walid; Hoiriyah Hoiriyah
Energy - Jurnal Ilmiah Ilmu-Ilmu Teknik Vol 12 No 2 (2022): Jurnal Energy Vol. 12 No. 2 November 2022
Publisher : Fakultas Teknik

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51747/energy.v12i2.1116

Abstract

A signature is a marker or identity that is on a document. Signatures have an important role in verifying and legalizing documents. The signature is not just any sign but is a legal and original image of the owner. With the development of today's technology, identification of signature patterns can not only be done manually, but can also be done with the help of a computer. However, the computer does not automatically carry out the identification process, but requires a pattern recognition process first which can be done by extracting the signature feature. Identification of the signature pattern is needed to recognize and distinguish the signature of each individual based on the characteristics of the signature. Therefore, this study is expected to be an alternative to minimize signature recognition errors by using the CNN (convolutional neural network) method. The research stages include taking signatures from 10 respondents as many as 200 signature images for training data, and 50 signatures for testing data. then taken with a scanner. The results of this study are the Convolutional Neural Network method can recognize each signature image with an accuracy of 100% in the validation testing process and 85% in the testing process. Keywords: Signature, convolutional neural network, Digital Image Processing
Co-Authors Chandra, Herry Adi Fakhriani Ekawati Lilis Anggraini Miftahul Walid Mokhamad Ramdhani Raharjo Muhammad Saidi Rahman Raudlatul Jannah