Summary of Leveraging Pre-trained Cnns For Efficient Feature Extraction in Rice Leaf Disease Classification, by Md. Shohanur Islam Sobuj et al.
Leveraging Pre-trained CNNs for Efficient Feature Extraction in Rice Leaf Disease Classification
by Md. Shohanur Islam Sobuj, Md. Imran Hossen, Md. Foysal Mahmud, Mahbub Ul Islam Khan
First submitted to arxiv on: 26 Feb 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Machine Learning (cs.LG)
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 The paper explores the impact of integrating feature extraction methodologies within pre-trained convolutional neural networks (CNNs) for rice disease classification. Initial experiments with baseline models showed commendable performance, but subsequent integration of Histogram of Oriented Gradients (HOG) led to significant improvements across architectures, particularly with EfficientNet-B7. Local Binary Patterns (LBP) demonstrated more conservative performance enhancements. The study also employed Gradient-weighted Class Activation Mapping (Grad-CAM) to visualize the attention paid by HOG-integrated models, which corroborated the observed accuracy gains. The findings highlight the pivotal role of feature extraction, particularly HOG, in refining representations and improving classification accuracy. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Rice disease classification is important for agriculture. Scientists tested different ways to improve pre-trained neural networks’ ability to identify rice diseases. They found that adding a technique called Histogram of Oriented Gradients (HOG) made the networks much better at recognizing diseases. This improved their accuracy from 92% to an impressive 97%. The study shows how important it is to use good feature extraction techniques with powerful neural networks to get accurate results. |
Keywords
» Artificial intelligence » Attention » Classification » Feature extraction
