PENERAPAN ARTIFICIAL NEURAL NETWORK UNTUK KLASIFIKASI FERTILITAS TELUR ITIK MENGGUNAKAN RASPBERRY PI

Jamaludin Indra

Abstract


ABSTRAK

Artificial Neural Network (ANN) telah banyak diterapkan pada berbagai bidang, salah satunya penerapan pada bidang peternakan. Penetasan menggunakan mesin penetas telur, proses pengklasifikasian embrio telur menjadi sangat penting dalam proses penetasan untuk membedakan antara yang layak, berdasarkan adanya perkembangan embrio yang dapat dilanjutkan dalam proses inkubasi atau tidak layak (fertile atau infertile), dalam penelitian ini menyajikan klasifikasi menggunakan teknik pengolahan citra digital menggunakan metode artificial neural network yang diaplikasikan pada Raspberry Pi sebagai pemroses gambar dan menampilkan hasil klasifikasi. Dengan metode artificial neural network dan penggunaan Raspberry Pi mampu mencapai akurasi pendeteksian 95%.
Kata kunci: Artificial Neural Network, Pengolahan Citra Digital, Embrio , Klasifikasi, Telur .


ABSTRACT
Artificial Neural Network (ANN) has been widely applied in various fields, one of which is the application in the field of animal husbandry. Hatching using an egg incubator machine, the classification process of egg embryos is very important in the hatching process to distinguish between the appropriate, based on the embryonic development that can be continued in the process of incubation or inadequate (fertile or infertile), in this study presents classification using image processing techniques digital uses the artificial neural network method that is applied to the Raspberry Pi as an image processor and displays the classification results. With the artificial neural network method and the use of Raspberry Pi it is expected to be able to achieve 90% detection accuracy.
Key word : Artificial Neural Network, Digital Image Processing, Embriyo, Calssification, Egg.

Full Text:

PDF

References


DAFTAR PUSTAKA

Bhunaveshwari, M.. & Palanivelu, L.., 2015. Improvement In Detection Of Chicken Egg Fertility Using Image Processing. International Journal On Engineering Technology and Sciences - IJETS, 2(4), pp.64–67.

Chandel, R. & Gupta, G., 2013. Image Filtering Algorithms and Techniques : A Review. , 3(10), pp.198–202.

Dehrouyeh, M.H. et al., 2010. Grading and Quality Inspection of Defected Eggs Using Machine Vision. , 17(2005), pp.23–30.

Harsadi, P., 2015. Deteksi Embrio Ayam Berdasarkan Citra Grayscale Menggunakan KMeans Automatic Thresholding. Jurnal Ilmiah SINUS, pp.49–56.

Sadikoglu, F. & Uzelaltinbulat, S., 2016. Biometric retina identification based on neural network. Procedia - Procedia Computer Science, 102(August), pp.26– 33. Available at: http://dx.doi.org/10.1016/j.procs.2016.09.365.

Senthilkumar, G., Gopalakrishnan, K. & Kumar, V.S., 2014. Embedded Image

Capturing System Using Raspberry Pi System Abstract : , 3(2), pp.213–215.

Shilpashree, K.., Lokesha, H. & Shivkumar, H., 2015. Implementation of Image Processing on Raspberry Pi. , 4(5), pp.199–202.

Vala, H.J. & Baxi, P.A., 2013. A Review on Otsu Image Segmentation Algorithm. , 2(2), pp.387–389.

Zhu, Z. & Ma, M., 2011. The identification of white fertile eggs prior to incubation based on machine vision and least square support vector machine. , 6(12), pp.2699–2704.


Refbacks

  • There are currently no refbacks.