Introduction to Computer Vision

Overview:

Introduces the fundamentals of digital image processing, including how images are loaded, represented, and quantized.

Topics to Cover:

• Fundamentals of image representation, loading, sampling, and quantization

Overview:

Introduces the fundamentals of digital image processing, including how images are loaded, represented, and quantized.

Topics to Cover:

• Techniques for scaling, rotation, translation, and affine transforms.

Overview:

Explains how to modify image intensity for enhancement and preprocessing.

Topics to Cover:

• Histogram operations, thresholding, and contrast adjustments.

Overview:

Focuses on filtering techniques using local neighbourhoods to enhance or detect features in images.

Topics to Cover:

• Filtering, blurring, sharpening, denoising, and edge detection.

Overview:

Introduces frequency-based filtering methods for image analysis and enhancement.

Topics to Cover:

• Fourier transforms, blurring, edge detection, and selective filtering.

Overview:

This module delves into advanced topics such as Generative Adversarial Networks (GANs), diffusion models, and synthetic data generation.

Tools to Cover:

• Erosion, dilation, and applications in binary image processing.

Overview:
Explains colour models and transformations for colour-based image processing.

Topics to Cover:

• Color spaces, conversions, and color-based processing.

Overview:
Focuses on different ways to represent images for computer vision tasks.

Topics to Cover:

• Encoding, features, and efficient representation of images.

Overview:
Introduces CNNs and their role in computer vision, including kernels, convolution, and implementation.

Topics to Cover:

• Introduction to convolutional neural networks, kernels, and Conv2D operations.

Overview:
Covers deep learning architectures for image classification and recognition.

Topics to Cover:

• Deep learning architectures: LeNet, AlexNet, VGG, ResNet, Inception, EfficientNet.

Overview:
Explains methods and architectures for detecting and localizing objects in images.

Topics to Cover:

• Methods and models: R-CNN, SSD, YOLO, RetinaNet.

Overview:
Covers segmentation techniques for pixel-level classification of images.

Topics to Cover:

• Pixel-level classification using FCN, U-Net, DeepLab, PSPNet, and Mask R-CNN.