KLASIFIKASI BAKTERI PADA DAGING SAPI DENGAN METODE NAIVE BAYES MENGGUNAKAN PENGOLAHAN CITRA DIGITAL
| Main Author: | Hidayat, Alif Firman |
|---|---|
| Format: | Thesis NonPeerReviewed Book |
| Bahasa: | eng |
| Terbitan: |
, 2018
|
| Subjects: | |
| Online Access: |
http://eprints.umm.ac.id/41318/1/PENDAHULUAN.pdf http://eprints.umm.ac.id/41318/2/BAB%20I.pdf http://eprints.umm.ac.id/41318/3/BAB%20II.pdf http://eprints.umm.ac.id/41318/4/BAB%20III.pdf http://eprints.umm.ac.id/41318/5/BAB%20IV.pdf http://eprints.umm.ac.id/41318/6/BAB%20V.pdf http://eprints.umm.ac.id/41318/7/LAMPIRAN.pdf http://eprints.umm.ac.id/41318/ |
Daftar Isi:
- In this research discusses how to detect the types of bacteria produced by laboratory tests on processed beef to make it easier to determine the type of bacteria, especially to microbiologists. The process of determining the type of bacteria uses the Naive Bayes classification method by utilizing digital image processing techniques. The bacteria studied in this study were bacteria escherichia coli, staphylococcus, and campylobacter. The bacterial image is taken by means of a capture process (photo) using a microscope camera which is then stored in a computer for its characteristics. Bacterial training images are then processed using digital image processing in the form of conversion to binary imagery and search features or distinguishing features for each type of bacteria with the Canny Edge Detection (CED) method. The CED method can automatically detect the edges of bacteria so that each bacterium has its own pattern. Characteristics of the results of the image processing process are then stored in a database using MySQL. Naive Bayes classification is used to classify testing data with training data in the database. Of the 31 sample results simulated with the application, 15 samples of Escherichia coli bacteria images were read correctly, 12 images of staphylococcus bacteria were read correctly and 2 campylobacter bacteria were read correctly. For the other 2 samples it reads incorrectly. So that from the results of the application simulation obtained an accuracy value of 96%, a precision value of 100% and a recall value of 93% using the formula for calculating the confusion matrix.