Klasifikasi Kualitas Kesegaran Buah Semangka berdasarkan Fitur Warna YCbCr menggunakan Algoritma Weigthed K-Means

  • Lalu Zulfikar Muslim universitas mataram
  • I Gede Pasek Suta Wijaya
  • Fitri Bimantoro
Keywords: Weighted K-Means Algorithm, Fruit Classification, YCbCr, Pattern Recognition, Training and Testing data


The classification of fruit quality on a computer using image data is very necessary for a faster and easier sorting process. Additionally, this can also be used in making decisions and policies related to business strategies in the industry. The paper presents the quality classification of watermelon that is carried out using the Weighted K - Means Algorithm. The watermelon is classified into three grou ps, namely fresh, medium, and rotten. There are two stages for the classification process, namely training, and examinations. The classification works using the YCbCr color space. In the training phase, the pair of input and the target of data that is proc essed to obtain the weight of k - Means. While for the testing/classification phase, the input data processed is an arbitrary image that has not been classified. The classification shows that the greater the amount of training data is, the more computing tim e is needed for the training and testing process and the higher accuracy, precision, and recall of the classification are obtained. While the greater the number of k values, the longer computational time needed for the training and testing.