Skip to content

Latest commit

 

History

History
88 lines (53 loc) · 2.57 KB

README.md

File metadata and controls

88 lines (53 loc) · 2.57 KB

Denoising-Image

🧠 Image Denoising using OpenCV

📸 Overview

This project demonstrates different image denoising techniques using OpenCV in Python. Image noise is a common problem caused by factors like low light, camera quality, or transmission errors. Here, we compare three popular filters — Gaussian Blur, Median Blur, and Bilateral Filter — to see how each one improves image quality while preserving important details.

⚙️ Features

✅ Removes noise from images using multiple filters

✅ Compares results visually in a single window

✅ Preserves edges and colors effectively (especially with Bilateral Filter)

✅ Easy-to-understand and beginner-friendly code

🧩 Techniques Used

  1. Gaussian Blur – Smooths the image by averaging neighboring pixels (good for general noise).
  2. Median Blur – Works best for “salt and pepper” noise by replacing each pixel with the median of its neighbors.
  3. Bilateral Filter – Reduces noise while keeping edges sharp; ideal for natural photos.

🧠 Libraries Used

pip install opencv-python numpy matplotlib
  • OpenCV – for image processing
  • NumPy – for numerical operations
  • Matplotlib – for visualization

🧾 Code Example

python
import cv2
import numpy as np
import matplotlib.pyplot as plt

def denoise_image(image_path):
    noisy_image = cv2.imread(image_path)
    noisy_image_rgb = cv2.cvtColor(noisy_image, cv2.COLOR_BGR2RGB)

    gaussian = cv2.GaussianBlur(noisy_image, (5,5), 0)
    median = cv2.medianBlur(noisy_image, 5)
    bilateral = cv2.bilateralFilter(noisy_image, 9, 75, 75)

    plt.figure(figsize=(15,10))
    plt.subplot(2,2,1); plt.title('Noisy Image'); plt.imshow(noisy_image_rgb); plt.axis('off')
    plt.subplot(2,2,2); plt.title('Gaussian Blur'); plt.imshow(cv2.cvtColor(gaussian, cv2.COLOR_BGR2RGB)); plt.axis('off')
    plt.subplot(2,2,3); plt.title('Median Blur'); plt.imshow(cv2.cvtColor(median, cv2.COLOR_BGR2RGB)); plt.axis('off')
    plt.subplot(2,2,4); plt.title('Bilateral Filter'); plt.imshow(cv2.cvtColor(bilateral, cv2.COLOR_BGR2RGB)); plt.axis('off')
    plt.show()

denoise_image('sample_image.jpg')

📊 Output

The program displays a 2×2 grid: | Noisy Image | Gaussian Blur | Median Blur | Bilateral Filter |

  • Gaussian Blur: Smooths noise but slightly blurs edges.
  • Median Blur: Excellent for salt-and-pepper noise.
  • Bilateral Filter: Keeps edges sharp and natural.