KLASIFIKASI TELUR FERTIL DAN INFERTIL PADA CITRA CANDLING TELUR ITIK MAGELANG MENGGUNAKAN ALGORITMA K-NEAREST NEIGHBOR (KNN)

Yulia Siti Ambarwati, NIM.: 16650078 (2020) KLASIFIKASI TELUR FERTIL DAN INFERTIL PADA CITRA CANDLING TELUR ITIK MAGELANG MENGGUNAKAN ALGORITMA K-NEAREST NEIGHBOR (KNN). Skripsi thesis, UIN SUNAN KALIJAGA YOGYAKARTA.

Preview	Text (KLASIFIKASI TELUR FERTIL DAN INFERTIL PADA CITRA CANDLING TELUR ITIK MAGELANG MENGGUNAKAN ALGORITMA K-NEAREST NEIGHBOR (KNN)) 16650078_BAB-I_IV-atau-V_DAFTAR-PUSTAKA.pdf - Published Version Download (949kB) | Preview
	Text (KLASIFIKASI TELUR FERTIL DAN INFERTIL PADA CITRA CANDLING TELUR ITIK MAGELANG MENGGUNAKAN ALGORITMA K-NEAREST NEIGHBOR (KNN)) 16650078_BAB-II_sampai_SEBELUM-BAB-TERAKHIR.pdf - Published Version Restricted to Registered users only Download (1MB) | Request a copy

Abstract

Magelang ducks as one of the leading cattle in Central Java that has the best egg quality is a promising commodity for poultry farmers. To increase the productivity of Magelang ducks, candling is an important process for sorting fertile and infertile eggs. However, the manual candling process is limited to the accuracy of human vision. Therefore, researchers want to utilize technology in the process of duck egg candling that subsequently classified using a computer. The research began with image acquisition. The next step is pre-processing the image by cropping, resizing, and segmenting with the triangle threshold followed by the extraction of the color, shape, and Gray Level Co-ocurrence Matrix (GLCM) texture features. After normalizing the results of feature extraction, then perform the feature selection using the variance threshold method. Then classify the relevant features using the KNN algorithm. This study aims to choose the best features of the best classification performance. The analysis is to find the highest solution and the fastest time in the classification process. The results of this study showed the highest accuracy of 92.31% and the classification time of 0.008 seconds on features: green, roundness, variance, and std at the value of k = 5.

Share this knowledge with your friends :

Actions (login required)

View Item