PERBANDINGAN METODE RAPSV DAN GLCM UNTUK EKSTRAKSI FITUR PADA KLASIFIKASI JENIS KAYU
Total View This Week0
Total View This Week0
Institusion
Universitas Muhammadiyah Gresik
Author
Pratama, Angga Mahditya Indra
Subject
Informatics Engineering
Datestamp
2024-01-26 07:57:05
Abstract :
Wood is an important natural resource and is used as a raw material in the production of various household products such as sideboards, cupboards, chairs, tables, and so on. Identification of wood species after being logged is difficult because it requires recognition of small features such as pore arrangement, pore shape, pore frequency, and wood radius, which can only be seen clearly using a tool such as a microscope with a minimum magnification of 10x. The classification of wood image types serves to determine which includes agathis wood images, keruing wood images and meranti wood images. The extraction methods to be compared are the RAPSV (Radial Average Power Spectrum) Algorithm and the GLCM Algorithm, using the KNN, Naïve Bayes, and Random Forest classification methods. which is higher than the GLCM feature extraction method, namely 93.14% using KNN with K=1, 70% using Naïve Bayes and 92.57% using Random Forest.
Wood is an important natural resource and is used as a raw material in the production of various household products such as sideboards, cupboards, chairs, tables, and so on. Identification of wood species after being logged is difficult because it requires recognition of small features such as pore arrangement, pore shape, pore frequency, and wood radius, which can only be seen clearly using a tool such as a microscope with a minimum magnification of 10x. The classification of wood image types serves to determine which includes agathis wood images, keruing wood images and meranti wood images. The extraction methods to be compared are the RAPSV (Radial Average Power Spectrum) Algorithm and the GLCM Algorithm, using the KNN, Naïve Bayes, and Random Forest classification methods. which is higher than the GLCM feature extraction method, namely 93.14% using KNN with K=1, 70% using Naïve Bayes and 92.57% using Random Forest.
Download
book
BibTex
Latex, Jabref
cloud_download
Original Resource
url resource Institution
