Article Per Year (5 Year)
p-Index From 2021 - 2026
0
P-Index
This Author published in this journals
All Journal Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer
Willy Karunia Sandy
Fakultas Ilmu Komputer, Universitas Brawijaya
Computer Science & IT Control & Systems Engineering Education Electrical & Electronics Engineering Engineering

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Penentuan Keaslian Tanda Tangan Menggunakan Shape Feature Extraction Techniques Dengan Metode Klasifikasi K Nearest Neighbor Dan Mean Average Precision Willy Karunia Sandy; Agus Wahyu Widodo; Yuita Arum Sari
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 2 No 3 (2018): Maret 2018
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1383.128 KB)

Abstract

The pace of technological development introduces the automatic identification of signature authenticity which is an important task in many activities requiring legitimate evidence. The process of authenticating signatures begins with preprocessing, which consists of gray transformation, median filter, binary transformation, cropping, and edge detection. After the process of preprocessing followed by the process of determining the extraction of form characteristics with the method of Shape Feature Extraction Techniques consisting of area, perimeter, centroid, rectangularity, eccentricity, roundness. Then classified based on training data obtained from calculations Shape Feature Extraction Techniques. After classification with K Nearest Neighbor then done calculation process Mean Average Precision to determine the authenticity of signature and percentage calculation of Mean Average Precision. In the system accuracy test results obtained 61% accuracy with the retrieval of random data for 25 data. Then obtained an accuracy of 61% accuracy with the retrieval of random data for 15 data and 58% on the retrieval of 5 data. Highest accuracy was obtained on the largest data collection with an accuracy of 61%.
Co-Authors Agus Wahyu Widodo Yuita Arum Sari