Skripsi
KLASIFIKASI GAMBAR JENIS JAMUR DENGAN METODE CONVOLUTIONAL NEURAL NETWORK
Indonesia is a country rich in mushrooms diversity. According to data from the 2015 Indonesia Biodiversity and Action Plan, there are around 86,000 types of macro and micro mushrooms in Indonesia out of 1.5 million fungal species worldwide. This number is only about 6% of the total types of mushrooms worldwide that are found in Indonesia. This classification of mushroom types can be useful for the general public's knowledge. In this research, classification will be carried out using the CNN method to classify nine types of mushrooms, including Agaricus, Amanita, Boletus, Cortinarius, Entoloma, Hygrocybe, Lactarius, Russula, and Suillus. The Convolutional Neural Network (CNN) method has relatively optimal accuracy in classifying various digital images. This research aims to develop software to classify pictures of mushroom types using the CNN method with the LeNet-5 and VGG-19 architectures and to compare the accuracy results of classification with the two architectures and varying parameters. The data used in this research classified the types of mushrooms, which consist of 9 types. Based on the test results on 679 test data, the accuracy value was 0.66, Precision 0.63, Recall 0.59, and F1-Score 0.60 with the VGG-19 architecture model epoch 30 batch size 32
Inventory Code | Barcode | Call Number | Location | Status |
---|---|---|---|---|
2407000835 | T139214 | T1392142024 | Central Library (Referens) | Available but not for loan - Not for Loan |
No other version available