| Autor: |
Pradorn Sureephong, Suwit Wongsila, Parinya Chantrasri |
| Rok vydání: |
2021 |
| Předmět: |
|
| Zdroj: |
2021 Joint International Conference on Digital Arts, Media and Technology with ECTI Northern Section Conference on Electrical, Electronics, Computer and Telecommunication Engineering. |
| DOI: |
10.1109/ectidamtncon51128.2021.9425737 |
| Popis: |
The purpose of this work is to develop and design an algorithm for detection of mangoes infected with anthracnose. The study found that the higher performance ability of computers was developed and used into a deep learning system for the classification of fungal disease in plants. In the experiments, the main core of the systems is Convolutional Neural Network (CNN) was developed. In the training procedure of the systems the datasets of mango sample were divided into two parts: training and test datasets, using of 125+131 mango images with disease + without disease samples of mango photograph by the top and bottom position, in the efficiency test, 364 images from 85 + 97 images with disease + no disease samples were used for testing. Based on the testing results, the developed system was more than 70% accurate to isolate the disease mango. |
| Databáze: |
OpenAIRE |
| Externí odkaz: |
|
