Merge pull request #773 from Arihant-Bhandari/cotton-disease

[Project Addition] Cotton Disease Classification using DL
abhisheks008 · Jun 11, 2024 · e4d0473 · e4d0473
2 parents 674c8d1 + 460e467
commit e4d0473
Show file tree

Hide file tree

Showing 25 changed files with 149 additions and 0 deletions.
diff --git a/Cotton Disease Classification using DL/Dataset/README.md b/Cotton Disease Classification using DL/Dataset/README.md
@@ -0,0 +1,3 @@
+The link for the dataset used in this project:  https://www.kaggle.com/datasets/dhamur/cotton-plant-disease
+
+The dataset consists of 6 subdirectories dealing with 5 diseases (Aphids, Army Worms, Bacterial Blight, Powdery Mildew, Target Spot) and Healthy set: each set has approximately 520 images totalling to 3118 images.
diff --git a/Cotton Disease Classification using DL/Images/Aphids.png b/Cotton Disease Classification using DL/Images/Aphids.png
diff --git a/Cotton Disease Classification using DL/Images/Army Worms.png b/Cotton Disease Classification using DL/Images/Army Worms.png
diff --git a/Cotton Disease Classification using DL/Images/Bacterial Blight.png b/Cotton Disease Classification using DL/Images/Bacterial Blight.png
diff --git a/Cotton Disease Classification using DL/Images/CNN Accuracy.png b/Cotton Disease Classification using DL/Images/CNN Accuracy.png
diff --git a/Cotton Disease Classification using DL/Images/CNN Loss.png b/Cotton Disease Classification using DL/Images/CNN Loss.png
diff --git a/Cotton Disease Classification using DL/Images/DenseNet-121 Accuracy.png b/Cotton Disease Classification using DL/Images/DenseNet-121 Accuracy.png
diff --git a/Cotton Disease Classification using DL/Images/DenseNet-121 Loss.png b/Cotton Disease Classification using DL/Images/DenseNet-121 Loss.png
diff --git a/Cotton Disease Classification using DL/Images/EDA.png b/Cotton Disease Classification using DL/Images/EDA.png
diff --git a/Cotton Disease Classification using DL/Images/Healthy.png b/Cotton Disease Classification using DL/Images/Healthy.png
diff --git a/Cotton Disease Classification using DL/Images/InceptionV3 Accuracy.png b/Cotton Disease Classification using DL/Images/InceptionV3 Accuracy.png
diff --git a/Cotton Disease Classification using DL/Images/InceptionV3 Loss.png b/Cotton Disease Classification using DL/Images/InceptionV3 Loss.png
diff --git a/Cotton Disease Classification using DL/Images/MobileNet Accuracy.png b/Cotton Disease Classification using DL/Images/MobileNet Accuracy.png
diff --git a/Cotton Disease Classification using DL/Images/MobileNet Loss.png b/Cotton Disease Classification using DL/Images/MobileNet Loss.png
diff --git a/Cotton Disease Classification using DL/Images/Powdery Mildew.png b/Cotton Disease Classification using DL/Images/Powdery Mildew.png
diff --git a/Cotton Disease Classification using DL/Images/RESNET50 Accuracy.png b/Cotton Disease Classification using DL/Images/RESNET50 Accuracy.png
diff --git a/Cotton Disease Classification using DL/Images/RESNET50 Loss.png b/Cotton Disease Classification using DL/Images/RESNET50 Loss.png
diff --git a/Cotton Disease Classification using DL/Images/Target Spot.png b/Cotton Disease Classification using DL/Images/Target Spot.png
diff --git a/Cotton Disease Classification using DL/Images/VGG16 Accuracy.png b/Cotton Disease Classification using DL/Images/VGG16 Accuracy.png
diff --git a/Cotton Disease Classification using DL/Images/VGG16 Loss.png b/Cotton Disease Classification using DL/Images/VGG16 Loss.png
diff --git a/Cotton Disease Classification using DL/Images/Xception Accuracy.png b/Cotton Disease Classification using DL/Images/Xception Accuracy.png
diff --git a/Cotton Disease Classification using DL/Images/Xception Loss.png b/Cotton Disease Classification using DL/Images/Xception Loss.png
diff --git a/Cotton Disease Classification using DL/Model/cotton-disease.ipynb b/Cotton Disease Classification using DL/Model/cotton-disease.ipynb
diff --git a/Cotton Disease Classification using DL/README.md b/Cotton Disease Classification using DL/README.md
@@ -0,0 +1,138 @@
+## **Cotton Disease Classification using DL**
+
+### 🎯 **Goal**
+
+The objective of this project is to classify images of Cotton Leaves into 6 categories: Aphids, Army Worms, Bacterial Blight, Powdery Mildew, Target Spot and Healthy.
+
+### 🧵 **Dataset**
+
+The dataset consists of 6 subdirectories dealing with 5 diseases (Aphids, Army Worms, Bacterial Blight, Powdery Mildew, Target Spot) and Healthy set: each set has approximately 520 images totalling to 3118 images.
+
+### 🧾 **Description**
+
+The project deals with multiclass classification, classifying images into 6 categories: Aphids, Army Worms, Bacterial Blight, Powdery Mildew, Target Spot and Healthy.
+
+### 🧮 **What I had done!**
+
+To achieve our goals, the following steps were implemented:
+
+- Images were loaded using keras.utils and normalized to the range 0 to 1.
+
+- Turned Labels into probability distributions.
+
+- Images were resized to a fixed size of 224x224 pixels.
+
+- Custom and pre-trained models were used for this task.
+
+### 🚀 **Models Implemented**
+
+models used:
+
+- ResNet-50
+- Xception
+- VGG16
+- CNN
+- InceptionV3
+- DenseNet-121
+- MobileNet
+
+### 📚 **Libraries Needed**
+
+- Keras
+
+- Tensorflow
+
+- Numpy
+
+- Matplotlib
+
+### 📊 **Exploratory Data Analysis Results**
+
+
+- #### **EDA**
+
+<p align="center">
+  <img src="https://github.com/Arihant-Bhandari/DL-Simplified/blob/cotton-disease/Cotton%20Disease%20Classification%20using%20DL/Images/Aphids.png" height="400px" width="400px" />
+  <img src="https://github.com/Arihant-Bhandari/DL-Simplified/blob/cotton-disease/Cotton%20Disease%20Classification%20using%20DL/Images/Army%20Worms.png" height="400px" width="400px" />
+  <img src="https://github.com/Arihant-Bhandari/DL-Simplified/blob/cotton-disease/Cotton%20Disease%20Classification%20using%20DL/Images/Bacterial%20Blight.png" height="400px" width="400px" />
+  <img src="https://github.com/Arihant-Bhandari/DL-Simplified/blob/cotton-disease/Cotton%20Disease%20Classification%20using%20DL/Images/Powdery%20Mildew.png" height="400px" width="400px" />
+  <img src="https://github.com/Arihant-Bhandari/DL-Simplified/blob/cotton-disease/Cotton%20Disease%20Classification%20using%20DL/Images/Target%20Spot.png" height="400px" width="400px" />
+  <img src="https://github.com/Arihant-Bhandari/DL-Simplified/blob/cotton-disease/Cotton%20Disease%20Classification%20using%20DL/Images/Healthy.png" height="400px" width="400px" />
+</p>
+
+<img src="https://github.com/Arihant-Bhandari/DL-Simplified/blob/cotton-disease/Cotton%20Disease%20Classification%20using%20DL/Images/EDA.png"/>
+
+- #### **DenseNet-121**
+
+<p align="center">
+  <img src="https://github.com/Arihant-Bhandari/DL-Simplified/blob/cotton-disease/Cotton%20Disease%20Classification%20using%20DL/Images/DenseNet-121%20Accuracy.png" height="400px" width="400px" />
+  <img src="https://github.com/Arihant-Bhandari/DL-Simplified/blob/cotton-disease/Cotton%20Disease%20Classification%20using%20DL/Images/DenseNet-121%20Loss.png" height="400px" width="400px" />
+</p>
+
+- #### **CNN**
+
+<p align="center">
+  <img src="https://github.com/Arihant-Bhandari/DL-Simplified/blob/cotton-disease/Cotton%20Disease%20Classification%20using%20DL/Images/CNN%20Accuracy.png" height="400px" width="400px" />
+  <img src="https://github.com/Arihant-Bhandari/DL-Simplified/blob/cotton-disease/Cotton%20Disease%20Classification%20using%20DL/Images/CNN%20Loss.png" height="400px" width="400px" />
+</p>
+
+- #### **InceptionV3**
+
+<p align="center">
+  <img src="https://github.com/Arihant-Bhandari/DL-Simplified/blob/cotton-disease/Cotton%20Disease%20Classification%20using%20DL/Images/InceptionV3%20Accuracy.png" height="400px" width="400px" />
+  <img src="https://github.com/Arihant-Bhandari/DL-Simplified/blob/cotton-disease/Cotton%20Disease%20Classification%20using%20DL/Images/InceptionV3%20Loss.png" height="400px" width="400px" />
+</p>
+
+- #### **VGG16**
+
+<p align="center">
+  <img src="https://github.com/Arihant-Bhandari/DL-Simplified/blob/cotton-disease/Cotton%20Disease%20Classification%20using%20DL/Images/VGG16%20Accuracy.png" height="400px" width="400px" />
+  <img src="https://github.com/Arihant-Bhandari/DL-Simplified/blob/cotton-disease/Cotton%20Disease%20Classification%20using%20DL/Images/VGG16%20Loss.png" height="400px" width="400px" />
+</p>
+
+- #### **MobileNet**
+
+<p align="center">
+  <img src="https://github.com/Arihant-Bhandari/DL-Simplified/blob/cotton-disease/Cotton%20Disease%20Classification%20using%20DL/Images/MobileNet%20Accuracy.png" height="400px" width="400px" />
+  <img src="https://github.com/Arihant-Bhandari/DL-Simplified/blob/cotton-disease/Cotton%20Disease%20Classification%20using%20DL/Images/MobileNet%20Loss.png" height="400px" width="400px" />
+</p>
+
+- #### **RESNET50**
+
+<p align="center">
+  <img src="https://github.com/Arihant-Bhandari/DL-Simplified/blob/cotton-disease/Cotton%20Disease%20Classification%20using%20DL/Images/RESNET50%20Accuracy.png" height="400px" width="400px" />
+  <img src="https://github.com/Arihant-Bhandari/DL-Simplified/blob/cotton-disease/Cotton%20Disease%20Classification%20using%20DL/Images/RESNET50%20Loss.png" height="400px" width="400px" />
+</p>
+
+- #### **Xception**
+
+<p align="center">
+  <img src="https://github.com/Arihant-Bhandari/DL-Simplified/blob/cotton-disease/Cotton%20Disease%20Classification%20using%20DL/Images/Xception%20Accuracy.png" height="400px" width="400px" />
+  <img src="https://github.com/Arihant-Bhandari/DL-Simplified/blob/cotton-disease/Cotton%20Disease%20Classification%20using%20DL/Images/Xception%20Loss.png" height="400px" width="400px" />
+</p>
+
+### 📈 **Performance of the Models based on the Accuracy Scores**
+
+#### Metrics: 
+
+We used Validation **Loss** and **Accuracy** as metrics.
+
+| Models | Accuracy | Loss |
+|--------|---------------------|--------------------------|
+| ResNet-50 | 17.95% | 13.2251 |
+| InceptionV3 | 97.22%  | 0.1047 | 
+| CNN | 92.52% | 0.3026 |
+| VGG16 | 98.50% | 0.0673 |
+| MobileNet | 99.36% | 0.0264 |
+| DenseNet-121 | 99.57% | 0.0295 |
+| Xception | 97.22% | 0.0989 |
+
+### 📢 **Conclusion**
+
+We conclude the following:
+
+All models except Resnet-50 work excpetionally well on this task, and the ideal choices are **DenseNet-121**, **MobileNet**, **Xception** and **VGG16**. We can also observe that a custom CNN can be a good match for the task as well, being highly accurate with a simpler and smaller architecture.
+
+### ✒️ **Your Signature**
+
+Original Contributor: Arihant Bhandari [https://github.com/Arihant-Bhandari]
diff --git a/Cotton Disease Classification using DL/requirements.txt b/Cotton Disease Classification using DL/requirements.txt
@@ -0,0 +1,7 @@
+tensorflow
+keras
+numpy
+skLearn
+pandas
+matplotlib
+seaborn
Original file line number	Diff line number	Diff line change
		@@ -0,0 +1,3 @@
		The link for the dataset used in this project: https://www.kaggle.com/datasets/dhamur/cotton-plant-disease

		The dataset consists of 6 subdirectories dealing with 5 diseases (Aphids, Army Worms, Bacterial Blight, Powdery Mildew, Target Spot) and Healthy set: each set has approximately 520 images totalling to 3118 images.