Computer vision vs human vision, an example
Both images below read “Hello!”. Yes, both! If you don’t believe it, copy the “blank” image and sharpen it with any photo editing software (”Auto Contrast” in Photoshop). However, you need to do that only for the sake of humans - computers don’t need it! If you run Pixcavator, the result will be similar to the image on the right. The moral is: image “enhancement” tools have nothing to do with computer vision.
Here is another example.
December 30th, 2007 at 5:24 pm
[…] Last time we had an image that looked blank and yet Pixcavator was able to detect objects that spelled “Hello!”. The reason was that humans can only recognize about 30 levels of gray while standard image formats have 256. Since the text was in virtually white (254) on white (255) background, it was invisible. This was supposed to illustrate the ability of computer vision to succeed where humans fail. […]