COURSE OVERVIEW
Introduction to Computer Vision
• What is Computer Vision?
• Applications of Computer Vision
• CV vs Image Processing
• Challenges in Computer Vision
• Image Classification vs Object Detection vs Segmentation
Image Fundamentals
• Pixels, Color Channels (RGB, BGR, Grayscale)
• Image Representation in Arrays
• Image Dimensions and Shapes
• Image File Formats (JPG, PNG, BMP)
• Image Resolution and Aspect Ratio
Working with Images in Python
• Using OpenCV for Image I/O
• Reading, Writing, and Displaying Images
• Image Resizing, Cropping, Flipping
• Drawing Shapes and Text on Images
• Image Color Conversions
• Histogram and Pixel Value Analysis
Image Processing Techniques
• Image Thresholding (Binary, Adaptive)
• Blurring and Smoothing (Gaussian, Median)
• Edge Detection (Sobel, Canny)
• Morphological Operations (Erosion, Dilation)
• Image Gradients and Contours
• ROI (Region of Interest)
Deep Learning for CV (CNN-based)
• Role of CNNs in Computer Vision
• Convolution and Pooling Recap
• Building Image Classification Models
• Transfer Learning with Pretrained Models
• VGG, ResNet, Inception, MobileNet
• Fine-tuning and Feature Extraction
• Data Augmentation Techniques
• Handling Class Imbalance
Object Detection
• Object Detection Overview
• Sliding Window & Region Proposals
• Bounding Boxes and IOU
• Object Detection Algorithms
• R-CNN
• Fast R-CNN
• Faster R-CNN
• YOLO (You Only Look Once)
• SSD (Single Shot Detector)
• Real-Time Object Detection with YOLO
Image Segmentation
• What is Image Segmentation?
• Semantic vs Instance Segmentation
• U-Net Architecture
• Mask R-CNN
• Applications: Medical Imaging, Scene Understanding
Face and Gesture Recognition
• Face Detection with OpenCV
• Facial Landmarks and Alignment
• Face Recognition with Deep Learning
• Hand Gesture Recognition
• Emotion Detection
Optical Character Recognition (OCR)
• Introduction to OCR
• Using Tesseract OCR
• Text Detection in Images
• Preprocessing Techniques for OCR
• Scene Text Recognition
Video Processing and Analysis
• Reading and Writing Video with OpenCV
• Frame Extraction and Manipulation
• Motion Detection
• Object Tracking
• Meanshift, Camshift
• KCF, CSRT, MOSSE
• Background Subtraction
Project Ideas
• Face Mask Detection
• Vehicle Detection and Counting
• OCR Scanner
• Sign Language Interpreter
• Virtual Paint App
• Emotion-based Music Player
• Fire and Smoke Detection
Deployment of CV Models
• Exporting CV Models
• Using Streamlit, Flask for Demo Apps
• Integration with Webcams or CCTV Feeds
• Cloud Deployment (GCP, AWS, Azure)
• Mobile Deployment
Course Outcomes
-
Understand the fundamentals of image formation, processing, and analysis.
-
Apply techniques for image filtering, enhancement, and feature extraction.
-
Implement object detection, recognition, and tracking methods.
-
Use machine learning and deep learning models for vision tasks.
-
Develop real-world computer vision applications using libraries like OpenCV and TensorFlow/PyTorch.
-
Evaluate and optimize vision models for accuracy, efficiency, and robustness.
