Claim Missing Document
Check
Articles

Found 2 Documents
Search
Journal : Infotekmesin

FUNGSI GLCM PADA BACKPROPAGATION UNTUK IDENTIFIKASI SIDIK JARI Kusanti, Jani; Tjendrowasono, Tri Irianto
Infotekmesin Vol 10, No 2 (2019): Infotekmesin: Juli 2019
Publisher : Politeknik Negeri Cilacap

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (863.581 KB) | DOI: 10.35970/infotekmesin.v10i2.40

Abstract

The use of fingerprints for identification has been done a lot, both in the police for investigations, in government for absences, in population and much more. To identify fingerprints, various methods are widely used which purpose is to produce a better level of accuracy. This is as reference to find out how important the function of the method will be used before the identification process is applied. The renewal of this research prioritizes how far the function of GLCM (GRAY LEVEL CO-OCCURRENCE MATRIX) is useful to improve the accuracy of fingerprint identification using the backpropagation method. The test results showed that GLCM can affect the increase in accuracy to 83%.
Optimasi Klasifikasi Parasit Malaria Dengan Metode LVQ, SVM dan Backpropagation Kusanti, Jani; Irianto Tjendrowarsono, Tri
Infotekmesin Vol 12 No 1 (2021): Infotekmesin: Januari 2021
Publisher : P3M Politeknik Negeri Cilacap

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35970/infotekmesin.v12i1.483

Abstract

The use of the classification method affects the accuracy of the test results. The accuracy of the classification method is affected by the number of classes in the image. The number of classes and the amount of data should be considered when making decisions in choosing a classification method. This study used 600 data, which were divided into 510 training data and 90 test data. The number of classes tested is 12 classes with the number of initial features used by 22 features. The characteristics used in the test consist of shape characteristics and texture characteristics. The classification methods used in this study are LVQ, Backpropagation, and SVM. The data has 22 features or attributes that are the result of texture and shape feature extraction. Texture features are energy 0o, energy 45o, energy 90o, energy 135o, entropy 0o, entropy 45o, entropy 90o, entropy 135o, contrast 0o, contrast 45o, contrast 90o, contrast 135o, homogeneity 00, homogeneity 45o, homogeneity 90o, homogeneity 135o, correlation 0o, Correlation 45o, correlation 90o, correlation 135o, features of área and perimeter shape. The test results using the Backpropagation method obtained 89.7% results, using the LVQ method obtained 77.78% results, and the SVM method obtained 99.1% results.