Course Content
Module 1 Computer Vision Foundations
The core concepts every real CV engineer must know before touching deep learning.
0/7
1.1 How Machines Interpret Images
30:00
1.2 Image Processing Fundamentals
30:00
1.3 Feature Extraction (Classical Computer Vision)
30:00
1.4 OpenCV Foundations
01:45:00
1.5 Applied Computer Vision Mini-Project
06:30:00
Core Foundations of Computer Vision
00:10:00
Rebuilding ResNet-18 Using Custom Code (No Copy-Paste Allowed)
Module 2 Deep Learning for Vision
This module takes learners from basic image operations to full-scale deep learning pipelines for vision tasks. The focus is on understanding how CNNs extract hierarchical features, how models learn spatial patterns, and how to train, optimize, and deploy real-world vision models. Students build modern architectures from scratch, implement training loops, and gain the skills required to handle classification, detection, and segmentation workflows.
0/7
2.1 Why Deep Learning Works for Vision
45:00
2.2 Convolutional Neural Networks (CNNs)
45:00
2.3 Building a CNN From Scratch
01:30:00
2.4 Training CNNs Properly
45:00
2.5 Modern CNN Architectures
01:30:00
Deep Learning for Vision
00:10:00
Constructing a Full CNN Pipeline for Image Classification
Module 3 Image Classification & Transfer Learning
Transfer Learning: Why it works Fine-tuning vs Feature Extraction Using Pretrained Models (ResNet, EfficientNet) Improving real-world accuracy Project: Build a high-accuracy classifier using transfer learning
Module 4 Object Detection
Traditional Detectors (Haar, HOG + SVM) Deep Learning Detectors YOLO family SSD Faster R-CNN Bounding box loss functions NMS & anchor boxes Project: Train a YOLO object detector on a custom dataset
Module 5 Image Segmentation
Sematic vs Instance vs Panoptic segmentation U-Net Architecture Breakdown Mask R-CNN Practical tips for dataset annotation Project: Build a semantic segmentation model for medical or industrial images
COMPUTER VISION AI

Topics

  • Local descriptors: SIFT, SURF, ORB

  • Keypoint detection: corners, blobs

  • Feature matching with BFMatcher + FLANN

  • Homography & perspective transforms

  • Why classical CV still matters in robotics, AR, and SLAM

Practical Work

  • Extract keypoints

  • Match features across images

  • Estimate homography & warp images

Previous
Next