Hello,
I am currently working on Multilingual and effective Captcha project for GSOC 2014 just to encounter the same problem of difficult image I did proposed the solution as an indexing System for image which will improve overtime by removing non user friendly images from those user friendly, more detail about this image indexing system is discussed here: https://www.mediawiki.org/wiki/User:AalekhN/GSoC_proposal_2014#Image_Indexing_System Thank You Aalekh Nigam "aalekhN" On Wed, 02 Apr 2014 00:00:24 +0530 wrote >Has anyone ever collected statistics on which of our captcha images are most commonly entered incorrectly? I've noticed that some of our images are quite difficult to read and should probably be removed from rotation. I could imagine applying a heuristic like: 0-10% wrong: Delete - too easy 10-30% wrong: Keep - just right 30-100% wrong: Delete - too hard Ryan Kaldari _______________________________________________ Wikitech-l mailing list [email protected] https://lists.wikimedia.org/mailman/listinfo/wikitech-l Send by rediffmail _______________________________________________ Wikitech-l mailing list [email protected] https://lists.wikimedia.org/mailman/listinfo/wikitech-l
