Implementasi Learning Vector Quantization untuk Klasifikasi Jenis Buah Kelapa menggunakan Image Processing

Abstract

Coconut fruit is a versatile plant because all parts from the stem to the coconut fruit have their benefits. Coconut fruit is the most valuable part of the economy. The problem so far that has occurred is that the process of classifying coconut species is still done manually and has not been computerized, namely the classification of coconut types is still based on experience, color, and shape of the coconut. This of course takes a long time and errors still occur frequently. So this research can help classify coconuts with Learning Vector Quantization (LVQ). The purpose of this research is to organize the types of coconuts with image processing and Learning Vector Quantization (LVQ) by using mean extraction from RGB (Red, Green, Blue) and standard deviation from RGB (Red, Green, Blue). The results of the study were taken from 2 different types of coconuts against the 80 training data, the accuracy of the training data was 83.75%. The evaluation results with the Confusion Matrix with a test accuracy value of 90% of the 20 test data.