PERANCANGAN ALAT PENGKLASIFIKASI KERNEL JAGUNG PORTABLE BERBASIS PENGOLAHAN CITRA DIGITAL MENGGUNAKAN METODE PERCEPTRON
| Main Author: | Pratama, Yandy Fajar |
|---|---|
| Format: | Thesis NonPeerReviewed Book |
| Bahasa: | eng |
| Terbitan: |
, 2019
|
| Subjects: | |
| Online Access: |
http://eprints.umm.ac.id/44466/1/PENDAHULUAN.pdf http://eprints.umm.ac.id/44466/2/BAB%20I.pdf http://eprints.umm.ac.id/44466/3/BAB%20II.pdf http://eprints.umm.ac.id/44466/4/BAB%20III.pdf http://eprints.umm.ac.id/44466/5/Bab%20IV.pdf http://eprints.umm.ac.id/44466/6/Bab%20V.pdf http://eprints.umm.ac.id/44466/7/LAMPIRAN.pdf http://eprints.umm.ac.id/44466/ |
Daftar Isi:
- In this research discusses about determination of corn harvest period based on milk line stage of corn for easily for farmer to determine the time for harvest. Classification stage in corn kernels using digital image processing with the artificial neural network (ANN) Perceptron method. In this research corn kernels image capture with webcam already connected to raspberry pi for processing. Processed image of corn using for data training with using digital image processing for determine the thresholding value of corn kernels. After the thresholding value obtained, then it is classified according to the corn kernels stage class. In thresholding processed there are 3 readings of data for input namely yellow as a whole corn kernels, white as milk line, and percentage of milk line. The data used for classification is yellow and white to make data training. Perceptron classification using for classified for data training and data testing. Samples tested asa many as 40 image of corn kernels at, each image has 10 images. From 40 sample there is 5 false sample reading in stage 2 false is 1 sample, stage 3 and 4 each false is 2 sample. So that from the results obtained the level of accuracy of the perceptron classification is 87,5.