Classification of Types of Dates Using Extraction of Shape and Texture Features with K-Nearest Neighbors Method

Muhammad Ichsan (Faculty of Computer Science, Dian Nuswantoro University, Semarang, Indonesia)
Abdul Syukur (Faculty of Computer Science, Dian Nuswantoro University, Semarang, Indonesia)
Affandy (Faculty of Computer Science, Dian Nuswantoro University, Semarang, Indonesia)
Moch. Arief Soeleman (Faculty of Computer Science, Dian Nuswantoro University, Semarang, Indonesia)

Influence: International Journal of Science Review
Vol. 4 No. 1 (2022): INFLUENCE: International Journal of Science Review

Dates are one type of plant that comes from palm trees, dates can also be called in Latin arecaceae. There are several types of dates available in the market making it difficult for buyers (consumers) to recognize the types. The purpose of this study was to determine the accuracy of the results of dates from ajwa, grape and mejol dates using the classification of texture and shape features using the K-NN (K-Nearest Neighbors) method. The stages of image processing, namely data processing, segmentation, and extraction using the K-Nearest neighbors method, from this research it is known that the accuracy value is 96.33%.