Early Recognition of Betel Leaf Disease using Deep Learning with Depth-wise Separable Convolutions

Hridoy, Rashidul Hasan; Habib, Tarek; Jabiullah, Ismail; Rahman, Riazur; Ahmed, Faez

doi:10.1109/tensymp52854.2021.9551009

Cited by 10 publications

(3 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the architecture, depth-wise separable convolutions were used to decrease the number of parameters, speed up training, address the overfitting problem, and achieve an accuracy of 96.02%. In contrast, a different CNN architecture created with conventional convolutions and taught using the same training methodology obtained a test accuracy of 89.53% [30]. However, there hasn't been significant research on betel leaf bringing good performance in accuracy and other criteria.…”

Section: Related Workmentioning

confidence: 99%

PlantDet: A Robust Multi-Model Ensemble Method Based on Deep Learning For Plant Disease Detection

et al. 2023

View full text Add to dashboard Cite

Plant disease is a significant health concern among all living creatures. Early diagnosis can help farmers takenecessary steps to cure the disease and accelerate the production rate efficiently. Our research has beenconducted with five most common rice leaf diseases, such as bacterial leaf blight, brown spot, leaf blast,leaf scald, and narrow brown spot, including healthy class, and two categories of betel leaf, such as healthyand unhealthy class. A robust new deep ensemble model, based on InceptionResNetV2, EfficientNetV2L,and Xception, has been proposed, known as, PlantDet, in this research. PlantDet solves not only underfitting problems but also leverage nourished performances simultaneously for scarce dataset of the sparse number of different background image dataset. PlantDet integrates efficient data augmentation, preprocessing, Global Average Pooling layer, Dropout mechanism, L2 regularizers, PRelu activation function, Batch Normalization layers, and more Dense layers that make the model more robust compared to all existing models and help to handle underfitting and overfitting problems while maintaining high performance. PlantDet exceeds the previous state-of-art model for the Rice Leaf dataset with an Accuracy of 98.53%, a Precision of 98.50%, a Recall of 98.35%, a F1 of 98.42% and a Specificity of 99.71%. In addition, for the Betel Leaf dataset, PlantDet also surpassed all existing base models, including several robust ensemble models. Finally, Grad-CAM and Score-CAM have been accomplished with the Xception method to explain the model performances particularly to elaborate how the Deep Learning (DL) models works for this complex dataset. Score-CAM slightly outperformed Grad-CAM++ in terms of localizing the predicted area.

show abstract

Section: Related Workmentioning

confidence: 99%

PlantDet: A Robust Multi-Model Ensemble Method Based on Deep Learning For Plant Disease Detection

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Finally, 3,763,200 / 91,500 = 41x less multiplications are required. Since the depth separable convolution has a lower trainable parameter number than a typical CNN, the risk of overfitting on small datasets is minimized [29]. Moreover, the time complexity of standard convolutional layers applied in block 1 and block 2 is ∼ 𝑶(𝑴 𝟐 * 𝑲 𝟐 * 𝑪 𝒊𝒏 * 𝑪 𝒐𝒖𝒕 ) while the time complexity of the depth-wise separable convolution layer applied in block 3 is ∼ 𝑶(𝑴 𝟐 * 𝑲 𝟐 * 𝑪 𝒊𝒏 + 𝑴 𝟐 * 𝑪 𝒊𝒏 * 𝑪 𝒐𝒖𝒕 ) where 𝑀 is the size of feature map, 𝐾 is the size of kernel, 𝐶 𝑖𝑛 is the number of input channels, 𝐶 𝑜𝑢𝑡 is the number of output channels.…”

Section: B Depth-wise Separable Convolutional Layers With Batch Norma...mentioning

confidence: 99%

FL-ToLeD: An Improved Lightweight Attention Convolutional Neural Network Model for Tomato Leaf Diseases Classification for Low-End Devices

Alnamoly,

Hady,

Abd El-Kader

et al. 2024

IEEE Access

View full text Add to dashboard Cite

The agricultural sector is still a major provider of many countries' economies, but diseases that continuously infect plants represent continuous threats to agriculture and cause massive losses to the country's economy. In this study, a lightweight convolutional neural network model called FL-ToLeD was proposed for tomato disease classification based on a soft attention mechanism with a depth-wise separable convolution layer. With a model size of 2.5 MB and 221,594 trainable parameters, FL-ToLeD achieved 99.5%, 99.10%, 99.04% for training, validation and testing accuracy respectively, and 99 % for each of precision, recall, and f1-score, it also achieved 99.90% for ROC-AUC with average inference time of 2.06924 µs. FL-ToLeD outperformed H. Ulutaş (2023) by 2.2% in terms of accuracy, precision, recall and f1-score. Additionally, it performed better than M. Agarwal (2023), Abbas (2021), and S. Verma (2020) in terms of accuracy, precision, recall, and f1-score by 8%, 2%, and 6%, respectively. It also outperformed Arshad (2023) by 4.77%, 8.92%, 35.18% and 5.11% in terms of accuracy, precision, recall and f1-score, respectively. Furthermore, FL-ToLeD is 90 times smaller than S. Verma (2020) and 2.5 times smaller than H. Ulutaş (2023) in terms of model size. All this makes FL-ToLeD more suitable for low-end devices in precision agriculture.

show abstract

“…The accuracy of a conventional convolutional neural network was 6.49 percent lower than that of our system. Hridoy et al [18] created an effective EfficientNet model for eight types of papaya diseases based on picture augmentation and transfer learning. Using Efficient Net B5, B6, and B7, the average accuracy of 6931 test images was 97.31 percent.…”

Section: Literature Surveymentioning

confidence: 99%

The Novel ML Approaches on Wheat Disease by CLF and FOHF of Image Equalization Techniques

Kanna.R¹,

V.²

2023

INDJCSE

View full text Add to dashboard Cite

Crop diseases and insect pests are the most significant obstacles to agricultural production. Consequences include a decrease in crop yields and the obstruction of the long-term development of high-quality, high-efficiency agriculture. Rapid and accurate detection of wheat leaf disease categories promotes early deployment of field control and improvement of wheat yield and quality. It's no exaggeration to say that wheat is one of the world's most vital crops. Wheat leaf diseases, though, severely hamper development. The quality of wheat and the agricultural economy rely on prompt and correct identification of wheat leaf diseases. This work propose an integrated machine learning technique, According to the results of this study, when compared to other models, the Fuzzy Opponent Histogram Filter that makes use of Bayes Net performs the best. The Fuzzy Opponent Histogram Filter with Bayes Net gives best outcome which is 97% of accuracy.

show abstract

Early Recognition of Betel Leaf Disease using Deep Learning with Depth-wise Separable Convolutions

Cited by 10 publications

References 13 publications

PlantDet: A Robust Multi-Model Ensemble Method Based on Deep Learning For Plant Disease Detection

PlantDet: A Robust Multi-Model Ensemble Method Based on Deep Learning For Plant Disease Detection

FL-ToLeD: An Improved Lightweight Attention Convolutional Neural Network Model for Tomato Leaf Diseases Classification for Low-End Devices

The Novel ML Approaches on Wheat Disease by CLF and FOHF of Image Equalization Techniques

Contact Info

Product

Resources

About