Merge pull request #779 from Arihant-Bhandari/plant-pathogen

[Project Addition] Plant Pathogen Detection using DL
abhisheks008 · Jun 11, 2024 · 5da8d60 · 5da8d60
2 parents e4d0473 + a3e6d69
commit 5da8d60
Show file tree

Hide file tree

Showing 24 changed files with 152 additions and 0 deletions.
diff --git a/Plant Pathogen Detection using DL/Dataset/README.md b/Plant Pathogen Detection using DL/Dataset/README.md
@@ -0,0 +1,5 @@
+The link for the dataset used in this project:  https://www.kaggle.com/datasets/kanishk3813/pathogen-dataset
+
+The dataset consists of 5 subdirectories dealing with Healthy, Virus, Bacteria, Fungi and Pests: each carrying approximately 8000 images totalling to approximately 40000 images.
+
+We downsampled to approximately 1000 images per class totalling to 5000 images.
diff --git a/Plant Pathogen Detection using DL/Images/Bacteria.png b/Plant Pathogen Detection using DL/Images/Bacteria.png
diff --git a/Plant Pathogen Detection using DL/Images/CNN Accuracy.png b/Plant Pathogen Detection using DL/Images/CNN Accuracy.png
diff --git a/Plant Pathogen Detection using DL/Images/CNN Loss.png b/Plant Pathogen Detection using DL/Images/CNN Loss.png
diff --git a/Plant Pathogen Detection using DL/Images/DENSENET121 Accuracy.png b/Plant Pathogen Detection using DL/Images/DENSENET121 Accuracy.png
diff --git a/Plant Pathogen Detection using DL/Images/DENSENET121 Loss.png b/Plant Pathogen Detection using DL/Images/DENSENET121 Loss.png
diff --git a/Plant Pathogen Detection using DL/Images/EDA.png b/Plant Pathogen Detection using DL/Images/EDA.png
diff --git a/Plant Pathogen Detection using DL/Images/Fungi.png b/Plant Pathogen Detection using DL/Images/Fungi.png
diff --git a/Plant Pathogen Detection using DL/Images/Healthy.png b/Plant Pathogen Detection using DL/Images/Healthy.png
diff --git a/Plant Pathogen Detection using DL/Images/InceptionV3 Accuracy.png b/Plant Pathogen Detection using DL/Images/InceptionV3 Accuracy.png
diff --git a/Plant Pathogen Detection using DL/Images/InceptionV3 Loss.png b/Plant Pathogen Detection using DL/Images/InceptionV3 Loss.png
diff --git a/Plant Pathogen Detection using DL/Images/MobileNet Accuracy.png b/Plant Pathogen Detection using DL/Images/MobileNet Accuracy.png
diff --git a/Plant Pathogen Detection using DL/Images/MobileNet Loss.png b/Plant Pathogen Detection using DL/Images/MobileNet Loss.png
diff --git a/Plant Pathogen Detection using DL/Images/NASNetMobile Accuracy.png b/Plant Pathogen Detection using DL/Images/NASNetMobile Accuracy.png
diff --git a/Plant Pathogen Detection using DL/Images/NASNetMobile Loss.png b/Plant Pathogen Detection using DL/Images/NASNetMobile Loss.png
diff --git a/Plant Pathogen Detection using DL/Images/Pests.png b/Plant Pathogen Detection using DL/Images/Pests.png
diff --git a/Plant Pathogen Detection using DL/Images/VGG16 Accuracy.png b/Plant Pathogen Detection using DL/Images/VGG16 Accuracy.png
diff --git a/Plant Pathogen Detection using DL/Images/VGG16 Loss.png b/Plant Pathogen Detection using DL/Images/VGG16 Loss.png
diff --git a/Plant Pathogen Detection using DL/Images/Virus.png b/Plant Pathogen Detection using DL/Images/Virus.png
diff --git a/Plant Pathogen Detection using DL/Images/Xception Accuracy.png b/Plant Pathogen Detection using DL/Images/Xception Accuracy.png
diff --git a/Plant Pathogen Detection using DL/Images/Xception Loss.png b/Plant Pathogen Detection using DL/Images/Xception Loss.png
diff --git a/Plant Pathogen Detection using DL/Model/plant-pathogen.ipynb b/Plant Pathogen Detection using DL/Model/plant-pathogen.ipynb
diff --git a/Plant Pathogen Detection using DL/README.md b/Plant Pathogen Detection using DL/README.md
@@ -0,0 +1,139 @@
+## **Plant Pathogen Detection using DL**
+
+### 🎯 **Goal**
+
+The objective of this project is to classify images of Plants into 5 categories: Healthy, Virus, Bacteria, Fungi and Pests.
+
+### 🧵 **Dataset**
+
+The dataset consists of 5 subdirectories dealing with Healthy, Virus, Bacteria, Fungi and Pests: each carrying approximately 8000 images totalling to approximately 40000 images.
+
+We downsampled to approximately 1000 images per class totalling to 5000 images.
+
+### 🧾 **Description**
+
+The project deals with multiclass classification, classifying images of Plants into 5 categories: Healthy, Virus, Bacteria, Fungi and Pests.
+
+### 🧮 **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:
+
+- NASNetMobile
+- 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/plant-pathogen/Plant%20Pathogen%20Detection%20using%20DL/Images/Bacteria.png" height="400px" width="400px" />
+  <img src="https://github.com/Arihant-Bhandari/DL-Simplified/blob/plant-pathogen/Plant%20Pathogen%20Detection%20using%20DL/Images/Fungi.png" height="400px" width="400px" />
+  <img src="https://github.com/Arihant-Bhandari/DL-Simplified/blob/plant-pathogen/Plant%20Pathogen%20Detection%20using%20DL/Images/Pests.png" height="400px" width="400px" />
+  <img src="https://github.com/Arihant-Bhandari/DL-Simplified/blob/plant-pathogen/Plant%20Pathogen%20Detection%20using%20DL/Images/Virus.png" height="400px" width="400px" />
+  <img src="https://github.com/Arihant-Bhandari/DL-Simplified/blob/plant-pathogen/Plant%20Pathogen%20Detection%20using%20DL/Images/Healthy.png" height="400px" width="400px" />
+</p>
+
+<img src="https://github.com/Arihant-Bhandari/DL-Simplified/blob/plant-pathogen/Plant%20Pathogen%20Detection%20using%20DL/Images/EDA.png"/>
+
+- #### **DenseNet-121**
+
+<p align="center">
+  <img src="https://github.com/Arihant-Bhandari/DL-Simplified/blob/plant-pathogen/Plant%20Pathogen%20Detection%20using%20DL/Images/DENSENET121%20Accuracy.png" height="400px" width="400px" />
+  <img src="https://github.com/Arihant-Bhandari/DL-Simplified/blob/plant-pathogen/Plant%20Pathogen%20Detection%20using%20DL/Images/DENSENET121%20Loss.png" height="400px" width="400px" />
+</p>
+
+- #### **CNN**
+
+<p align="center">
+  <img src="https://github.com/Arihant-Bhandari/DL-Simplified/blob/plant-pathogen/Plant%20Pathogen%20Detection%20using%20DL/Images/CNN%20Accuracy.png" height="400px" width="400px" />
+  <img src="https://github.com/Arihant-Bhandari/DL-Simplified/blob/plant-pathogen/Plant%20Pathogen%20Detection%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/plant-pathogen/Plant%20Pathogen%20Detection%20using%20DL/Images/InceptionV3%20Accuracy.png" height="400px" width="400px" />
+  <img src="https://github.com/Arihant-Bhandari/DL-Simplified/blob/plant-pathogen/Plant%20Pathogen%20Detection%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/plant-pathogen/Plant%20Pathogen%20Detection%20using%20DL/Images/VGG16%20Accuracy.png" height="400px" width="400px" />
+  <img src="https://github.com/Arihant-Bhandari/DL-Simplified/blob/plant-pathogen/Plant%20Pathogen%20Detection%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/plant-pathogen/Plant%20Pathogen%20Detection%20using%20DL/Images/MobileNet%20Accuracy.png" height="400px" width="400px" />
+  <img src="https://github.com/Arihant-Bhandari/DL-Simplified/blob/plant-pathogen/Plant%20Pathogen%20Detection%20using%20DL/Images/MobileNet%20Loss.png" height="400px" width="400px" />
+</p>
+
+- #### **NASNetMobile**
+
+<p align="center">
+  <img src="https://github.com/Arihant-Bhandari/DL-Simplified/blob/plant-pathogen/Plant%20Pathogen%20Detection%20using%20DL/Images/NASNetMobile%20Accuracy.png" height="400px" width="400px" />
+  <img src="https://github.com/Arihant-Bhandari/DL-Simplified/blob/plant-pathogen/Plant%20Pathogen%20Detection%20using%20DL/Images/NASNetMobile%20Loss.png" height="400px" width="400px" />
+</p>
+
+- #### **Xception**
+
+<p align="center">
+  <img src="https://github.com/Arihant-Bhandari/DL-Simplified/blob/plant-pathogen/Plant%20Pathogen%20Detection%20using%20DL/Images/Xception%20Accuracy.png" height="400px" width="400px" />
+  <img src="https://github.com/Arihant-Bhandari/DL-Simplified/blob/plant-pathogen/Plant%20Pathogen%20Detection%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 |
+|--------|---------------------|--------------------------|
+| NASNetMobile | 94.67% | 0.1586 |
+| InceptionV3 | 93.47%  | 0.2511 | 
+| CNN | 91.20% | 0.2696 |
+| VGG16 | 97.20% | 0.1099 |
+| MobileNet | 97.33% | 0.0917 |
+| DenseNet-121 | 97.73% | 0.0754 |
+| Xception | 95.20% | 0.1823 |
+
+### 📢 **Conclusion**
+
+We conclude the following:
+
+All models worked exceptionally well on the task, and the ideal models for this are: **Xception**, **VGG16**, **MobileNet** and **DenseNet-121**.
+
+### ✒️ **Your Signature**
+
+Original Contributor: Arihant Bhandari [https://github.com/Arihant-Bhandari]
diff --git a/Plant Pathogen Detection using DL/requirements.txt b/Plant Pathogen Detection using DL/requirements.txt
@@ -0,0 +1,7 @@
+tensorflow
+keras
+numpy
+skLearn
+pandas
+matplotlib
+seaborn