Thanks to visit codestin.com
Credit goes to www.scribd.com

Scribd
Upload
6 views2 pages

Computer Vision Notes

The document outlines key concepts in computer vision, distinguishing between image enhancement and restoration, and detailing pre-processing tasks like noise removal and image resizing. It covers feature extraction, thresholding, the RGB color model, edge detection, and the role of CNNs in deep learning for image analysis. Additionally, it explains the differences between supervised and unsupervised learning, as well as the function of OCR in converting images of text into editable formats.

Uploaded by

pirsadam786
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
6 views2 pages

Computer Vision Notes

The document outlines key concepts in computer vision, distinguishing between image enhancement and restoration, and detailing pre-processing tasks like noise removal and image resizing. It covers feature extraction, thresholding, the RGB color model, edge detection, and the role of CNNs in deep learning for image analysis. Additionally, it explains the differences between supervised and unsupervised learning, as well as the function of OCR in converting images of text into editable formats.

Uploaded by

pirsadam786
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 2

Computer Vision - Key Concepts

1. Image Enhancement vs. Image Restoration

- Image Enhancement: Improves visual appearance (e.g., brightness, contrast).

- Image Restoration: Recovers original image from a degraded version (e.g., blur, noise).

2. Pre-processing Tasks

- Noise Removal: Removes random variation (e.g., Gaussian filter).

- Image Resizing & Normalization: Standardizes size and scales pixel values.

3. Feature Extraction

- Identifies important patterns (edges, corners) to help machines understand images.

4. Thresholding

- Converts grayscale image into binary by setting a pixel value limit.

- Used for segmentation (black & white image).

5. RGB Color Model

- Uses Red, Green, Blue channels to create color images.

- Each pixel is a mix of these values.

6. Edge Detection

- Finds object boundaries by detecting brightness changes.

- Algorithms: Sobel, Canny.

7. CNN (Convolutional Neural Network)

- Deep learning model for images.


- Uses convolutional and pooling layers to learn image features.

- Used in object detection, recognition, etc.

8. Supervised vs. Unsupervised Learning

- Supervised: Trained on labeled data.

- Unsupervised: Finds patterns in unlabeled data.

9. OCR (Optical Character Recognition)

- Converts text in images to editable machine-encoded text.

- Used in digitizing documents and recognizing handwriting.

You might also like