Back to Learning Center
Advanced
Computer Vision
Learn image processing, object detection, segmentation, and visual recognition with deep learning. Build real-world computer vision applications.
25-35 hours total20 modulesCertificate included
Course Modules
1
Introduction to Computer Vision
What machines can see
25 min
2
Image Fundamentals
Pixels, channels, and color spaces
35 min
3
Image Preprocessing
Augmentation and normalization
40 min
4
Convolutions Explained
Filters, kernels, and feature maps
50 min
5
CNN Architectures for Vision
LeNet to EfficientNet
60 min
6
Image Classification
Building classifiers from scratch
70 min
7
Transfer Learning for Vision
Using pretrained models
45 min
8
Object Detection Fundamentals
Localization and classification
60 min
9
YOLO Architecture
Real-time object detection
75 min
10
Faster R-CNN
Region-based detection
70 min
11
Semantic Segmentation
Pixel-wise classification
65 min
12
Instance Segmentation
Mask R-CNN explained
55 min
13
Face Detection & Recognition
Building face systems
80 min
14
Pose Estimation
Detecting body keypoints
60 min
15
Video Analysis
Temporal understanding
70 min
16
3D Vision
Depth estimation and point clouds
55 min
17
Vision Transformers
ViT and beyond
75 min
18
Multimodal Vision-Language
CLIP and visual QA
65 min
19
Edge Deployment
Mobile and embedded CV
50 min
20
Capstone: Build a Vision App
End-to-end CV project
120 min