K-Nearest Neighbor Algorithm to Identify Cucumber Maturity with Extraction of One-Order Statistical Features and Gray-Level Co-Occurrence

Determination of the maturity cucumber fruit after harvest is subjective. The level thoroughness each individual's selection different. cucumbers seen from age fruit, resemblance ripe or old, raw young difficult to distinguish in terms texture skin. use red, green, blue, and grayscale color modes imagery, then processed using extraction statistical features Order-One Order-Two GLCM methods. Imagery a 13 megapixels smartphone camera. Texture parameter values are used first order: mean, variance, skewness, kurtosis, entropy. Second energy, contrast, correlation, inverse different moments, angular second variance 2, entropy 2. classification parameters both order uses an algorithm K-Nearest Neighbors as comparison test data training data. So that system made can identify old young. highest accuracy found imagery with combination two skewness kurtosis euclidean distance calculation Neighbor 96.05%.