Computer Vision
Machine Learning
Methods for acquiring, processing, analysing and reasoning about images or video sequences in order to extract meaningful/useful information that can be interpreted and acted upon as desired
Example applications
Robot vision & control
Species identification
Code reading (bar & QR codes)
Optical Character Recognition (OCR)
Photo enhancement
Facial recognition
Medical scan analysis/diagnosis
Topographical modelling
Navigation of autonomous vehicles / robots
Creation of training/test data for Machine Learning
Augmented reality
Video indexing (e.g. video splitting, sequence cataloguing)
Event detection
Techniques used in Computer Vision
Image manipulation
Style/feature transfer (e.g. transferring the style associated with an artist/topic to another image)
Image interpolation (e.g. morphing one image into another and producing intermediate images)
Enhancement (e.g. brightness/contrast levels)
Restoration, noise removal (e.g. inpainting)
Stitching
Filtering
Image analysis
Pattern recognition
Colour/intensity analysis
Pixel counting
Edge detection
Blob detection
Image/video generation
Scene reconstruction (e.g. generating faces/landscapes)
Motion analysis
Tracking movement
Motion estimation
Egomotion (estimating a camera's movement relative to a scene)
Optical flow (determining the apparent movement of each point in an image)
Object/feature recognition
Detection
Position extraction
Size measurement
Shape recognition
Classification
3D pose estimation (transforming an object in a 2D image into an estimated 3D model, describing the object's position and orientation)
Image search/retrieval (e.g. finding other images with similar features)