https://github.com/jmcheon/leaffliction

An innovative computer vision project utilizing leaf image analysis for disease recognition.
https://github.com/jmcheon/leaffliction

image-analysis image-classification opencv-python plantcv python3 pytorch

Last synced: about 2 months ago
JSON representation

An innovative computer vision project utilizing leaf image analysis for disease recognition.

Host: GitHub
URL: https://github.com/jmcheon/leaffliction
Owner: jmcheon
Created: 2024-08-20T18:18:51.000Z (almost 2 years ago)
Default Branch: main
Last Pushed: 2024-09-18T13:49:15.000Z (almost 2 years ago)
Last Synced: 2025-07-01T05:04:21.225Z (12 months ago)
Topics: image-analysis, image-classification, opencv-python, plantcv, python3, pytorch
Language: Python
Homepage:
Size: 89.3 MB
Stars: 0
Watchers: 1
Forks: 0
Open Issues: 0
Metadata Files:
- Readme: README.md

Awesome Lists containing this project

README

# Leaffliction - Computer vision
>*_Summary: Image classification by disease recognition on leaves._*

| Requirements | Skills |
|--------------|--------|
| - `python3.10`
- `torch`
- `torchvision`
- `opencv`
- `plantcv`
- `numpy`
- `matplotlib`
| - `Rigor`
- `Group & interpersonal`
- `Algorithms & AI` |

## Usage
There are 4 distinct parts in this project, `01. Distribution`, `02. Augmentation`, `03. Transformation`, and `04. Classification`.

### 01. Distribution
Download image dataset and generate distribution chart image
```bash
usage: 01.Distribution.py [-h] directories [directories ...]

A program to analyze plant images and generate charts.

positional arguments:
directories The directories to store extracted images and save the charts (ex: 01.Distribution apple)

options:
-h, --help show this help message and exit
```

#### Example
```bash
python3 01.Distribution.py apple grape
```

### 02. Augmentation
Augment unbalanced image dataset
```bash
usage: 02.Augmentation.py [-h] [file_path]

A program to augment images samples by applying 6 types of transformation.

positional arguments:
file_path Image file path to transform to 6 different types.

options:
-h, --help show this help message and exit
```

#### Example
```bash
python3 02.Augmentation.py
```

### 03. Transformation
Save transformed image plots

```bash
usage: 03.Transformation.py [-h] -src [SRC_PATH] [-dst [DST_PATH]] [-gaussian] [-mask] [-roi] [-analyze] [-pseudo] [-hist]

A program to display image transformation.

options:
-h, --help show this help message and exit
-src [SRC_PATH], --src_path [SRC_PATH]
Image file path.
-dst [DST_PATH], --dst_path [DST_PATH]
Destination directory path.
-gaussian, --gaussian_blur
Gaussian Transform
-mask Mask Transform
-roi, --roi_objects Roi Transform
-analyze, --analyze_object
Analyze Transform
-pseudo, --pseudolandmarks
Psudolandmark Transform
-hist, --color_histogram
Color histogram Transform
```

#### Example
```bash
python3 03.Transformation.py -src [SRC_PATH] -dst [DST_PATH]
```

### 04. Classification
Print the accuracy on validation dataset

```bash
usage: 04.Classification.py [-h] [folder_path]

A program to classify a type of leaf from validation set.

positional arguments:
folder_path Image folder path.

options:
-h, --help show this help message and exit
```

#### Example
```bash
python3 04.Classification
```

## Implementation

### Leaf Classifier CNN Model
The model is designed to classify leaf diseases based on images of leaves. The model is implemented using Pytorch and consists of 4 convolutional layers followed by max pooling, along with 2 fully connected layers. The final output is produced using a softmax function for multi-class classification.

#### Model Architecture
1. Input layer
- Input: Leaf images with a shape of (256, 256, 3) corresponding to 256 x 256 RGB images.

2. Convolutional layers
- Conv Layer 1
- Input channels: 3 (RGB)
- Output channels: 32
- Kernel size: 3 x 3
- Activation function: ReLU
- Max Pooling: 2 x 2
- Conv Layer 2
- Input channels: 32
- Output channels: 64
- Kernel size: 3 x 3
- Activation function: ReLU
- Max Pooling: 2 x 2
- Conv Layer 3
- Input channels: 64
- Output channels: 128
- Kernel size: 3 x 3
- Activation function: ReLU
- Max Pooling: 2 x 2
- Conv Layer 4
- Input channels: 128
- Output channels: 256
- Kernel size: 3 x 3
- Activation function: ReLU
- Max Pooling: 2 x 2

3. Fully connected layers
- FC Layer 1
- Input: Flattened tensor from the previous convolutional layers (256 * 14 * 14 = 50176 units)
- Output: 512 units
- Activation function: ReLU
- Dropout: 0.5
- FC Layer 2
- Input: 512 units
- Output: `NUM_CLASSES` units (representing the number of disease classes)
- Activation function: Softmax

## Visualization

### 01. Distribution
There are 2 distinct leaf types; `apple` and `grape`, each of which consists of 4 labels.

Apple Image Distribution

Grape Image Distribution

### 02. Augmentation
The following 6 image augmentation techniques are applied to one single-leaf image labeled `apple black rot`.

Brightness

Contrast

Flip

Perspective

Rotate

Saturation

augmentation brightness image

augmentation contrast image

augmentation flip image

augmentation perspective image

augmentation rotate image

augmentation saturation image

### 03. Transformation
The following 6 image transformation techniques are applied to one single-leaf image labeled `apple black rot`.

Mask

Gaussian Blur

Roi objects

Analyze object

Pseudolandmarks

transformation mask image

transformation gaussian blur image

transformation roi objects image

transformation analyze object image

transformation pseudolandmarks image