Comment on How did websites like TinEye recognize cropped photos of the same image (and other likened pictures), without the low-entry easyness of LLM/AI Models these days?

over_clox@lemmy.world ⁨1⁩ ⁨day⁩ ago

JPEG works in 8x8 pixel blocks, and back in the day, most JPEG images weren’t all that big. Each 8x8 pixel block (64 pixels per block) could easily and quickly be processed as if it were a single pixel.

So if you had a 1024x768 JPEG, then the fast scanning technique would only scan the 128x96 blocks, not necessary to process every single pixel.

Of course the results could never be perfectly accurate, but most images are unique enough that this would be more than sufficient for fast scanning.

source
Sort:hotnewtop