Corn leaf disease recognition based on improved EfficientNet

IET Image Processing, Journal Year: 2025, Volume and Issue: 19(1)

Published: Jan. 1, 2025

Abstract Maize leaf disease seriously affects maize yield, a identification model with an improved lightweight network EfficientNet was proposed in this study. First, the replaces SENet module MBConv CBAM module, so that not only focuses on correlation between channels but also adaptively learns attentional weight of each spatial location. Furthermore, multi‐scale feature fusion layer based residual connection is introduced to extract more comprehensive and richer features at different scales. Finally, by introducing double pooling method, overall distribution smoothed while highlighting important features. After three improvements, model's recognition accuracy test set increased 2.34%, 2.16%, 0.97%, respectively, achieved average 98.32%, precision 98.29%, recall 98.25%. The experimental results compared other models show 5.23%, 3.68%, 1.99%, 1.79%, 3.2% higher than ResNet34, DenseNet121, MobileNet V2, SqueezeNet, B0, respectively. Activation heat maps can effectively suppress background interference.

Language: Английский

---

Deep Learning Generalized Hybrid Models for Multi-Species Crop Disease Classification with Explainable Insights

Published: Jan. 1, 2025

Language: Английский

---

Comparative Study of Lightweight CNN Architectures for Maize Leaf Disease Detection

Deleted Journal, Journal Year: 2025, Volume and Issue: 3(2), P. 4 - 13

Published: March 1, 2025

The study evaluates different compact Convolutional Neural Networks (CNNs) used to detect maize leaf diseases because they serve vital functions in precision agriculture. Testing involved evaluating the performance of five various models including VGG19, ResNet50, MobileNetV3, Custom MobileNetV3 and InceptionV3 for detection four disease types namely Blight, Common Rust, Gray Leaf Spot Healthy. analysis demonstrates that surpasses all competing through its 97.63% accuracy 96.68% rating as well 97.96% recall value. model showed complete ability which indicated exceptional efficiency spotting this condition. ResNet50 displayed good by effectively detecting Rust together with Healthy leaves. level was lower based on results observed model. demonstrate surpassed both VGG19 MobileNetV3. poorest resulted from Wheat Blight being confused one another. stands out best since it delivers reliable while maximizing thus making appropriate limited resource scenarios. contributes useful information helps optimize machine learning applicable agricultural field usage.

Language: Английский

---

Classification of maize leaf diseases with deep learning: Performance evaluation of the proposed model and use of explicable artificial intelligence

Chemometrics and Intelligent Laboratory Systems, Journal Year: 2025, Volume and Issue: 262, P. 105412 - 105412

Published: April 23, 2025

Language: Английский

---