diff --git a/.gitignore b/.gitignore
index 00983fe..3e661a5 100644
--- a/.gitignore
+++ b/.gitignore
@@ -1 +1,14 @@
-/__pycache__/
\ No newline at end of file
+# Byte-compiled / optimized / DLL files
+/__pycache__/
+*.py[cod]
+*.pyo
+
+# Virtual environment
+/venv/
+
+# Images and outputs
+/images/
+/outputs/
+
+# Configuration file
+conf.py
\ No newline at end of file
diff --git a/README.md b/README.md
index ea803c8..78dceee 100644
--- a/README.md
+++ b/README.md
@@ -1,25 +1,65 @@
-See the `conf.py`:
-```
-scheme = 'A'
+# Image Processing with YOLO and Inpainting
+
+This project provides a framework for removing people from images using YOLO for object detection and OpenCV or LaMa for inpainting. You can configure the behavior of the program by editing the `conf.py` file.
+
+## Configuration
+
+Edit the `conf.py` file to select the processing scheme and customize its parameters:
+
+```python
+scheme = 'A'  # Choose 'A' or 'B'
 
 schemeA = {
-    'image_name': 'd1.jpg',
-    'is_lama': False,
-    'inpaint_radius': 3,
-    'is_gaussianblur': True,
-    'gaussian_radius': 9 # Odd number
+    'image_name': 'd1.jpg',  # Input image name
+    'is_lama': False,        # Use LaMa for inpainting (True/False)
+    'inpaint_radius': 3,     # Radius for OpenCV inpainting
+    'is_gaussianblur': True, # Apply Gaussian blur to the mask
+    'gaussian_radius': 9     # Gaussian blur radius (odd number)
 }
 
 schemeB = {
-    'image_name': 'd1.jpg',
-    'gaussian_radius': 51, # Odd number
-    'is_use_fill_color': False,
-    'fill_color': [227, 234, 244]
+    'image_name': 'd1.jpg',      # Input image name
+    'gaussian_radius': 51,       # Gaussian blur radius (odd number)
+    'is_use_fill_color': False,  # Use a fill color for blending
+    'fill_color': [227, 234, 244] # RGB fill color
 }
 ```
-You can choose scheme whcih you want.<br>
-The A is useof openCV inpaint or model(LaMa); And B is useof openCV but no inpaint.<br>
-When you finished the conf, run `python main.py`.<br>
-<br>
-If you have a better scheme, please connect me.<br>
-Email:  xiadongliang88@163.com<br>
\ No newline at end of file
+
+- **Scheme A**: Uses OpenCV or LaMa for inpainting.
+- **Scheme B**: Uses OpenCV for blending without inpainting.
+
+## How to Run
+
+1. Install the required dependencies:
+   ```bash
+   pip install -r requirements.txt
+   ```
+
+2. Configure the `conf.py` file to select the desired scheme and parameters.
+
+3. Run the main script:
+   ```bash
+   python main.py
+   ```
+
+## Outputs
+
+Processed images will be saved in the `outputs/` directory with filenames indicating the scheme and input image.
+
+## Directory Structure
+
+```
+├── images/          # Input images
+├── outputs/         # Processed images
+├── conf.py          # Configuration file
+├── main.py          # Main script
+├── schemeA.py       # Scheme A implementation
+├── schemeB.py       # Scheme B implementation
+├── requirements.txt # Python dependencies
+```
+
+## Contact
+
+If you have suggestions for improving this project or new schemes to add, feel free to contact me:
+
+**Email**: xiadongliang88@163.com
\ No newline at end of file