Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

I'm not sure you can do "small part-of-the-image patches" when comparing against 175,000,000 images. And I don't mean that from a scale/processing perspective I mean it would seem you'd always get tons of small patch false positives from any realistic looking image.


In the limit of 1x1 patches, for sure. For 256 by 256 patches, who knows? I want to see how regurgitation varies as you vary N in NxN patches.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: