02/16/2020 Stanford- CS231-note introduction to Convolutional Neural Networks for visual recognition

real-time face detection by Paul Viola and Michael Jones
2001
computer chips were very slow but still able to do face detection in near real-time
2006- after 5 years
Fujifilme rolled out the first digital camera that has a real-time face detector
very rapid transfer from basic science research to real world application

feature object recognition
SIFT feature by David Lowe
match features than the entire object

Spatial Pyramid Matching
take features from different parts of image and in different resolutions and put them together in a feature descriptor and then support vector machine algorithm on top of that

machine learning algorithms:
graphical model, support vector machine, adaboost

bounding box/ image captioning

convolutional neuron network was a breakthrough(not invented) in 2012
1998 first invented for recognizing digits

why develop so fast recently?
Increasing computation/ available labeled datasets

cs2 TO visual