Summary of Transfer Learning with Densenet201 Architecture Model For Potato Leaf Disease Classification, by Rifqi Alfinnur Charisma and Faisal Dharma Adhinata
Transfer Learning With Densenet201 Architecture Model For Potato Leaf Disease Classification
by Rifqi Alfinnur Charisma, Faisal Dharma Adhinata
First submitted to arxiv on: 25 Jan 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary Potato leaf disease classification is crucial to ensure food production. While humans can identify some symptoms, there are limitations and inconsistencies. A deep learning approach using the DenseNet201 architecture can improve accuracy and shorten processing time. This study evaluates the effectiveness of transfer learning with DenseNet201 in classifying potato leaf diseases compared to traditional methods. The study compares scenarios involving dropouts and optimizers, finding that a model with 0.1 dropout rate and Adam optimizer achieves an impressive 99.5% training accuracy, 95.2% validation accuracy, and 96% confusion matrix. These findings support the development of a reliable potato leaf disease classification system. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Potato plants are important for food production, but diseases can significantly decrease yields. To control these diseases effectively, we need to quickly and accurately identify them. However, humans often struggle with this task due to similarities between symptoms. A new approach using deep learning and the DenseNet201 architecture aims to improve accuracy and speed up processing time. This study compares different methods to see which one works best for classifying potato leaf diseases. The results show that a specific combination of dropout rate and optimizer can achieve high accuracy, making it possible to develop a reliable system for diagnosing potato leaf diseases. |
Keywords
» Artificial intelligence » Classification » Confusion matrix » Deep learning » Dropout » Transfer learning
