PERANCANGAN ALAT PENGKLASIFIKASI KERNEL JAGUNG PORTABLE BERBASIS PENGOLAHAN CITRA DIGITAL MENGGUNAKAN METODE NAIVE BAYES
| Main Author: | Senjaya, Cahya Bagus Tri |
|---|---|
| Format: | Thesis NonPeerReviewed Book |
| Bahasa: | eng |
| Terbitan: |
, 2019
|
| Subjects: | |
| Online Access: |
http://eprints.umm.ac.id/44745/1/PENDAHULUAN.pdf http://eprints.umm.ac.id/44745/2/BAB%20I.pdf http://eprints.umm.ac.id/44745/3/BAB%20II.pdf http://eprints.umm.ac.id/44745/4/BAB%20III.pdf http://eprints.umm.ac.id/44745/5/BAB%20IV.pdf http://eprints.umm.ac.id/44745/6/BAB%20V.pdf http://eprints.umm.ac.id/44745/7/LAMPIRAN.pdf http://eprints.umm.ac.id/44745/ |
Daftar Isi:
- Maize commodity supplies not only domestically but also foreign industry, therefore the increase in productivity must be maintained especially seed maize which has very high productivity compared to local maize. This increase in production has not been followed by the quality improvement that makes maize production from farmer is often rejected by feed mills because it is not match the criteria for maize harvest period. We need an estimation system for harvest determination that can classify maize kernels using digital image processing and learning method. Digital image of maize kernel is taken with a webcam and processed using Python programming. Digital image processing is used to extract milk line and yellow colour features of the maize kernel. While the learning method is used for stage classification of maize kernel based on milk line. This study used 128 maize kernels for training data and 160 maize kernels for testing data. The assessment of maize harvest estimation is divided into 4 levels, namely stage 1, stage 2, stage 3 and stage 4. Parameters used to input the learning method are mean value, standard deviasi value and probability value. The learning method used is Naïve Bayes classifier. The level of maize kernel stage classification using the Naïve Bayes method was successful with a classification success rate of 87.5%. From the results of the classification that has been done produces four classification outputs, those are stage 1 by 90%, stage 2 by 100%, stage 3 by 90% and stage 4 by 70%.