Edge detection is a fundamental tool in image processing and computer vision, particularly in the areas of feature detection and extraction. This project implements a pipeline to process raw images and extract clear boundaries using the Canny Edge Detection algorithm.
The tool follows a structured workflow to ensure high-quality edge extraction:
- Grayscale Conversion: Converting the input image to grayscale to simplify the data by removing color information.
- Noise Reduction (Gaussian Blur): Applying a 5x5 Gaussian filter to smooth the image and remove noise that could interfere with edge detection.
- Canny Edge Detection: Applying the Canny algorithm with dual thresholds (100 and 200) to identify strong edges while suppressing weak ones.
- Visualization: Comparing the original image vs. the edge-detected result using Matplotlib.
Below is a sample of the edge detection result achieved by the tool:
- Noise Filtering: Integrated Gaussian blur for better result accuracy.
- Dynamic Processing: Capable of processing various image formats through the OpenCV pipeline.
- Side-by-Side Comparison: Automated visualization of results for analytical review.
- Language: Python 3
- Libraries: OpenCV (
cv2), Matplotlib (plt), NumPy. - Environment: Jupyter Notebook.
Code/: Contains theFile Project.ipynbwith the full implementation.Images/: Contains the original images.
Developed by Computer Science students at King Faisal University:
- Atekah Hussain Aljafar
- Zainab Abdulkarim Alhadhari
- Anfal Ahmad Alsuhayib
- Maryam Ahmed Alshabib
Connect with me on LinkedIn for more projects! https://www.linkedin.com/in/ateka-hussain/