CROP PESTS DETECTION USING FASTER-RCNN
Agriculture is an important sector in Malaysia as it produces food for the people and increases the country's income. Pests have always been a threat to agriculture. Pests can damage crops by eating leaves, stems and roots, resulting in a decrease in the market value of the crop and thus reduci...
Saved in:
| Main Author: | |
|---|---|
| Format: | Final Year Project Report |
| Language: | English |
| Published: |
Universiti Malaysia Sarawak, (UNIMAS)
2023
|
| Subjects: | |
| Online Access: | http://ir.unimas.my/id/eprint/44196/1/Esther%20Wong%20Ching%20Ya%20ft.pdf http://ir.unimas.my/id/eprint/44196/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Agriculture is an important sector in Malaysia as it produces food for the people and increases the country's income. Pests have always been a threat to agriculture. Pests can damage crops by eating leaves, stems and roots, resulting in a decrease in the market value of the crop and thus reducing farmers' income. In addition, pests can spread viruses that kill crops, resulting in reduced crop yields. Most crop pests are small and difficult to detect with the human eye. Therefore, this project uses a set of evidence images (such as chewed leaves) instead of pest images to train the model. Several pest detection models that have been developed by other researchers have been reviewed. This project proposes a detection model using the Faster-RCNN pre-trained model. The model is fine-tuned to the project dataset. The performance of the model was evaluated. The model can make predictions on images, although only 28.1% accurate. |
|---|