Klasifikasi Untuk Menentukan Tingkat Kematangan Buah Pisang Sunpride

Gracelia Adelaida Bere, Elizabeth Nurmiyati Tamtjita, Anggraini Kusumaningrum

Abstract

         YIQ (Iuma, In-phase, Quadrature) is a color space used to transmit analog TV signal. This research is conducting a possibility test on using YIQ as color features for fruit ripeness classification, which tested on Sunpride bananas. Classification is done using k-NN algorithm against YIQ values of several ripeness stage. The classification process itself consists of two steps: training and testing. In the training step, values from RGB color space of the images as training samples are converted into YIQ and extracted as features to form the classes, while in testing step, the test image went through the same conversion and feature extraction process, then classified using k-NN against the classes’ features, using k=3 and k=1. There are 120 Sunpride banana images used as test objects, and the results obtained shown that the classification performance using k=3 for Sangat Matang class is 100%, Busuk class is 66,67%, Mengkal class is 60% and Matang class is 60%. Results using k=1 for Sangat Matang class is 100%, Busuk class is 66,67%, Mengkal class is 66,7% and Matang class is 56,67%.

Keywords  : Classification, YIQ Color Space, Banana Sunpride, Euclidean Distance, k-Nearest Neighbors

References

Rajkumar,Rani et all., 2015, Classification of banana fruit maturity using zNose, Journal of Departement of Food and Agriculture, Vol.17, No.4 : 389-396, India.

Tapre dan Jain, 2012, Study of Advanced Maturity stages of banana, International Journal of Advanced Engineering Research and studies, Vol.1 No.3 : 272-274, Gujarat, India.

Li, Ze-Nian dan Drew, Mark S., 2004, Fundamentals of Multimedia, Pearson Prentice Hall, New Jersey.

Duda, Richard O. et all., 2000, Pattern Classification, John Wiley & Sons, Inc., California.

Tamatjita, E.N. dan Harjoko, Agus, 2014, Klasifikasi Lagu Berdasarkan Genre pada Format WAV, Jurnal IJCCS, Vol.8, No.2 : 145-154, Yogyakarta.

Article Metrics

Abstract view : 287 times
PDF (Bahasa Indonesia) - 709 times

Refbacks

  • There are currently no refbacks.