PENGGUNAAN K-NEAREST NEIGHBOR (KNN) UNTUK MENGIDENTIFIKASI CITRA BATIK PEWARNA ALAMI DAN PEWARNA SINTETIS BERDASARKAN WARNA
Total View This Week0
Total View This Week0
Institusion
Universitas Pembangunan Nasional Veteran Jakarta
Author
Ismail Habibi Herman, .
Subject
QA76 Computer software
Datestamp
2022-01-13 02:13:21
Abstract :
Batik is a type of original Indonesian fabric that is made specifically and has a variety of motifs and different colors, batik coloring is divided into two types, namely synthetic dyes and natural dyes. However, there are still many batik users who cannot distinguish directly between synthetic dyes and natural dyes because they have a similar color composition. The science and technology that has evolved makes it possible to help in distinguishing synthetic dye batik and natural dye batik by using image processing. This study aims to determine the accuracy of the K-Nearest Neighbor (KNN) algorithm as a classification method for the introduction of batik types through batik images. This study use 84 images of “BATIK BETAWI†as data and will be processed with various stages ranging from pre-process image resizing, data separation into validation data totaling 80 data which will be subdivided using K-Fold Cross Validation and 4 data as final evaluation data as data test at the final evaluation stage, then the image features are extracted into the form of images of Hue, Saturation, Value (HSV), and the validation test and final evaluation are carried out by classifying the image using the K-Nearest Neighbor (KNN) algorithm. The results of the final evaluation stage for each of the 4 final evaluation test data on neighbor values (K) produce 100% accuracy at a value of K = 1, a value of K = 3, and a value of K = 5.
Batik is a type of original Indonesian fabric that is made specifically and has a variety of motifs and different colors, batik coloring is divided into two types, namely synthetic dyes and natural dyes. However, there are still many batik users who cannot distinguish directly between synthetic dyes and natural dyes because they have a similar color composition. The science and technology that has evolved makes it possible to help in distinguishing synthetic dye batik and natural dye batik by using image processing. This study aims to determine the accuracy of the K-Nearest Neighbor (KNN) algorithm as a classification method for the introduction of batik types through batik images. This study use 84 images of “BATIK BETAWI†as data and will be processed with various stages ranging from pre-process image resizing, data separation into validation data totaling 80 data which will be subdivided using K-Fold Cross Validation and 4 data as final evaluation data as data test at the final evaluation stage, then the image features are extracted into the form of images of Hue, Saturation, Value (HSV), and the validation test and final evaluation are carried out by classifying the image using the K-Nearest Neighbor (KNN) algorithm. The results of the final evaluation stage for each of the 4 final evaluation test data on neighbor values (K) produce 100% accuracy at a value of K = 1, a value of K = 3, and a value of K = 5.
Download
book
BibTex
Latex, Jabref
cloud_download
Original Resource
url resource Institution
