Computer Vision is the art of distilling actionable information from images. In this hands-on course, we’ll learn about Image Analysis techniques using OpenCV and the Microsoft Cognitive Toolkit to segment images into meaningful parts. We’ll explore the evolution of Image Analysis, from classical to Deep-Learning techniques.
Module 1Introduction to image processing and computer |
|---|
|
✅ Short introduction to computer vision ✅ Digital images ✅ Structure of human eye and vision ✅ Color models15m ✅ Image processing goals and tasks ✅ Contrast and brightness correction ✅ Image convolution ✅ Edge detection
|
Module 2Introduction, Installation and Configuration |
|---|
|
✅ Describe Apache Cassandra ✅ Common use cases - large deployments ✅ Cassandra architecture ✅ Select and install a Cassandra version ✅ Configure for a single node, multinode ✅ Start and stop a Cassandra instance ✅ Installing on Windows, Mac, Ubuntu ✅ Basic CLI Commands
|
Module 3Convolutional features for visual recognition |
|---|
|
✅ Recap: Image classification ✅ AlexNet, VGG and Inception architectures ✅ ResNet and beyond1 ✅ Fine-grained image recognition ✅ Detection and classification of facial attributes ✅ Content-based image retrieva ✅ Computing semantic image embeddings using convolutional neural networks ✅ Employing indexing structures for efficient retrieval of semantic neighbors ✅ Face verification ✅ The re-identification problem in computer vision ✅ Facial keypoints regression ✅ CNN for keypoints regression |
Module 4Object Detection |
|---|
|
✅ Object detection problem ✅ Sliding windows ✅ HOG-based detector ✅ Detector training ✅ Viola-Jones face detector ✅ Attentional cascades and neural networks ✅ Region-based convolutional neural network ✅ From R-CNN to Fast R-CNN ✅ Faster R-CNN ✅ Region-based fully-convolutional network ✅ Single shot detectors ✅ Speed vs. accuracy tradeoff ✅ Fun with pedestrian detectors |
Module 5Object tracking and action recognition |
|---|
|
✅ Object tracking and action recognition ✅ Introduction to video analysis ✅ Optical flow ✅ Deep learning in optical flow estimation ✅ Visual object tracking ✅ Examples of visual object tracking methods1 ✅ Multiple object tracking ✅ Examples of multiple object tracking methods ✅ Introduction to action recognition ✅ Action classification ✅ Action classification with convolutional neural networks ✅Action localization |
Module 6Image segmentation and synthesis |
|---|
|
✅ Image segmentation3m ✅ Oversegmentation4m ✅ Deep learning models for image segmentation ✅ Human pose estimation as image segmentation ✅ Style transfer5m ✅ Generative adversarial networks7m ✅ Image transformation with neural networks
|