Computer Vision
Course Description
The Computer Vision course introduces learners to the fascinating field where artificial intelligence meets visual perception. It focuses on teaching how machines can analyze, interpret, and understand digital images and videos to make intelligent decisions. Participants will explore essential topics such as image processing, object detection, facial recognition, image segmentation, and video analysis.
Through practical, hands-on projects using Python, OpenCV, TensorFlow, and PyTorch, learners will gain the skills to develop real-world computer vision applications — from self-driving car systems to medical imaging and security surveillance.
Course Curriculum
- Image Representation and Manipulation
- Geometric Transformations (Scaling, Rotation, Cropping)
- Filtering Techniques (Blurring, Sharpening, Edge Detection)
- Thresholding and Segmentation Basics
- Morphological Operations
- Histogram Equalization and Contrast Adjustment
- Hands-on: Building a Simple Image Editor in Python
- Introduction to Convolutional Neural Networks (CNNs)
- Architecture of CNNs (Convolution, Pooling, Activation, Fully Connected Layers)
- Popular CNN Architectures: LeNet, AlexNet, VGG, ResNet
- Data Augmentation and Transfer Learning
- Frameworks: TensorFlow & PyTorch
- Hands-on: Building an Image Classifier with CNN
- Project 1: Image Classification using CNN
- Project 2: Real-Time Object Detection with YOLO
- Project 3: Face Recognition System
- Project 4: Image Segmentation for Medical Imaging
- Project 5: Building a Vision-Based Attendance System
- Building a Professional CV Portfolio
- Preparing for Computer Vision Job Roles