Welcome to the Computer Vision section of this repository. 🚀
This section covers the fundamentals and modern techniques used to help computers understand, analyze, and interpret visual information.
The topics are organized as a progressive learning path, starting from basic image processing and gradually moving toward Object Detection, Segmentation, Tracking, and Vision Transformers. 🧠
- 01-Image-Recognition — Introduction to image recognition and basic visual understanding
- 02-Contrast-Brightness — Understanding and adjusting image contrast and brightness
- 03-Filters — Image filtering and common spatial filters
- 04-Noise-Denoise — Noise types and image denoising techniques
- 05-Sharp — Image sharpening and enhancement
- 06-Edges — Edge detection and extracting image boundaries
- 07-Hough-Transform — Line and circle detection using Hough Transform
- 08-Transfer_Learning — Transfer Learning and pretrained models
- 09-PyTorch — Building and training Computer Vision models with PyTorch
- 10-R-CNN — Region-based Convolutional Neural Networks and two-stage detection
- 11-SSD-YOLO — Single-stage object detection with SSD and YOLO
- 12-Segmentation — Semantic and instance segmentation
- 13-Tracking — Object tracking across video frames
- 14-Vision-Transformer — Transformer-based architectures for Computer Vision
The topics are designed to progress from traditional image processing to modern deep learning architectures.
🖼️ Image Recognition
↓
🎨 Contrast & Brightness
↓
🔧 Filters
↓
🌫️ Noise & Denoising
↓
✨ Sharpening
↓
📐 Edge Detection
↓
⭕ Hough Transform
↓
🔄 Transfer Learning
↓
🔥 PyTorch
↓
🎯 R-CNN
↓
🚀 SSD & YOLO
↓
🎭 Segmentation
↓
🎥 Tracking
↓
🧠 Vision Transformer
The goal of this section is to build a solid understanding of Computer Vision, starting with classical image processing techniques and progressing toward modern deep learning and Transformer-based approaches.
🚀 From pixels to intelligent visual understanding.