Texture Feature Extraction in Grape Image Classification Using K-Nearest Neighbor

Indonesian Grapes are a vine. This fruit is often found in markets, shops, and the roadside. Along with development of computer technology today, computers can solve problems by classifying objects objects. How to apply GLCM K-NN methods for classification grapes. The purpose this study dataset used from kaggle.com sources, data tested 3 types grapes, number images 2624. that will be collection process limited three namely grape blue, pink, white. feature extraction contrast, energy, correlation, homogeneity. From testing test data, highest accuracy value 99.5441% k = 2 at level 8, while lowest 24.924% each 2. very influential on results, namely, higher value, value. getting better.