Hi everyone!
I'm excited to share an exercise I recently completed to enhance my knowledge of computer vision. It was a lot of fun! I was looking for hands-on ways to study, so I asked GPT for ideas, and it suggested some really cool exercises. This is the first one I tackled.
In this project, I focused on practising the basics of image processing, including:
- Loading and displaying an image.
- Converting between colour spaces (RGB, HSV, grayscale).
- Performing basic transformations: resizing, cropping, and rotating images.
- Filters such as blurring, sharpening, and edge detection are applied using the Canny method.
- Enhancing image contrast through histogram equalization.
I just wanted to share my experience and encourage others to dive into similar exercises!
Happy learning!