Klasifikasi Kualitas Biji Kopi Menggunakan MultilayerPerceptron Berbasis Fitur Warna LCH

Abstract

Coffee is one of Indonesia's foreign exchange earners and plays an important role in the development of the plantation industry. In previous studies, coffee bean quality research has been carried out using the ANN method using color features. RGB and GLCM. However, the results carried out in the study only had an accuracy value of up to 47%. Therefore, this study aims to improve the performance of coffee bean quality classification using four machine learning methods and 7 color features. From the results obtained, it shows that MultilayerPerceptron is better starting with RGB color with an accuracy of 38% split ratio 90:10. HSV has an accuracy of 57% split ratio 90:10. CMYK has an accuracy of 63% split ratio 90:10. LAB has a 58% curation split ratio of 90:10. The YUV type has an accuracy of 58% split ratio 90:10. Furthermore, the HSI color type has an accuracy of 42% split ratio 90:10. The HCL color type has an accuracy of 65% split ratio 90:10 and LCH has an accuracy of 78% split ratio 90:10. In testing, it can be concluded that the MultilayerPerceptron method is better than other methods for the coffee bean classification process.

Keywords

• coffee backpropagation, ann, glcm, color feature