Michael's Interest in Computer Vision
Computer Vision concerns the area where we want to make computer see. A
example is that the computer in a car can drive the car without any human
intervention, and is able to reach the destination safely. If you take a look
around, you see many objects and recognize all of them by their names,
properties, uses, etc.
Making computer do the same thing is incredibly difficult.
All computer sees is a bunch of numbers that describe the color of
the scene (through a camera or some visual device) and making sense of them at the level of human understanding is next to
impossible. You take a photo and get a billion pixels, each of which represents a color. That's all you know.
A computer can follow concrete, precise instructions, not
instruction like 'Gimme a random number' or 'Tell me what you
think about this person.' Therefore computer would understand a list of instructions that say 'If you have a red pixel next to a black pixel
it means you have a red-black pattern'. Computer scientists create and improve algorithms to make computers recognize things
they want them to recognize.
A case in point is facial detection in a photo. This technology is rampant in today's
cyber world. Facebook is one of the biggest consumers of this technology where a Facebook user can easily tag people
by browsing the uploaded photo where Facebook already labels the faces in the photo for the FB user.
I took a graduate course that taught me a lot about computer vision. I also
single-handedly developed a Program in Matlab that finds the eyes of a person
in an image with high accuracy.
Take a look!