COMPUTER VISION 101
How can computers understand the visual world of humans? Well, this is the fundamental question of our topic. However there is an issue that should be elucidated at first; “How can newborn babies understand the visual world of humans?”. Answer of this question is an illuminator to the way of teaching machines to learn.
Vision is an amazing feat of natural intelligence. Visual cortex occupies about 50% of Macaque brain, that means more human brain, the most powerful visual intelligence machinery yet developed, devoted to vision than anything else.
— Why computers should understand the visual world of humans? Why computer vision matters?
Computer vision has noticable benefits on six fundamental area: safety, security, comfort, health, access and fun. There are some basics of computer vision to provide benefits on these areas and more :
- Image creation
- Cameras, Eyes, Calibration
- Features, correspondence
- 3D vision
- Optical Flow
- Compression, vision for content delivery
Actually, computer vision is not a recent issue, it has a ridiculously brief history which has began in 1966(Minsky assigns computer vision as an undergrad summer project):
- 1960’s: interpretation of synthetic worlds
- 1970’s: some progress on interpreting selected images
- 1980’s: ANNs come and go; shift toward geometry and increased mathematical rigor
- 1990’s: face recognition; statistical analysis in vogue
- 2000’s: broader recognition; large annotated datasets available; video processing starts
- 2010’s: self-driving cars are on the road, robotic and VR technologies are greatly improved. Computer vision facilities have started gaining a seat in daily life.
The goal, says Fei-Fei Li, are computers that not only discern, but understand visual content. To provide this, a guideline database should be created by humans because there is not a wikipedia of images, faces, objects’ relations and movements.
I believe in that one day, all dreams of computer scientists will become true. The question is “Will we be one of the architectures of the upcoming new-world?”.
- Computer Vision: Algorithms and Applications, by Richard Szeliski