John Resig - OCR and Neural Nets in JavaScript
http://ejohn.org/blog/ocr-and-neural-nets-in-javascript/

Canvas element used to do basic image-processing on an image. Can a JS port of NumPy be far behind? What about the effects on expectations for javascript from users and engine writers? *Mind buzzes*

Breaking Captchas with a GreaseMonkey script

WhatTheFont for iPhone connects directly to MyFonts’ acclaimed font identification service, which has been helping customers pinpoint mystery fonts for 10 years. It works via Wi-Fi or the mobile phone network, so you can get your font fix right there on the spot.

App identifies fonts from a picture taken on the iphone.

facial recognition Star Trek

Navigate video by facial recognition, demo'd on the original Star Trek

face mining - nice

Now that's a good use of facial recognition!

have been working hard on Photo Finder, a powerful tool for finding pictures of you and your friends on Facebook. This application is the fastest, most powerful and most accurate facial recognition outside of TV crime dramas.

face recognition photo finder for facebook

Face.com - Face recognition for the masses. - http://face.com/

I have used it and it works. Limit to ten pages per hour, each 2 MB or less.

Anyone who works with LaTeX knows how time-consuming it can be to find a symbol in symbols-a4.pdf that you just can't memorize. Detexify is an attempt to simplify this search.

LaTeX handwritten symbol recognition

super neato

Gives Latex syntax for characters by hand-drawing them.

Detecção de faces utilizando javascript

Script permettant de faire de la détection faciale à l'aide de javascript.

This tutorial will show you how to use multi layer perceptron neural network for image recognition.

Simple video monitoring software brings enterprise-grade functionality to anyone with a webcam or network camera.

Introducing Vitamin D Video. Our simple video monitoring software brings enterprise-grade functionality to anyone with a webcam or network camera.

AudioTag scans your files or YouTube video and returns a list of matches.

Serviço de face detection com API bem bacana. Vc faz um pedido via API com o endereço da imagem e ele te retorna um JSON com as faces detectadas.

face.comが顔認識のAPIを公開。

The accuracy of computer speech recognition flat-lined in 2001, before reaching human levels. The funding plug was pulled, but no funeral, no text-to-speech eulogy followed. Words never meant very much to computers—which made them ten times more error-prone than humans. Humans expected that computer understanding of language would lead to artificially intelligent machines, inevitably and quickly. But the mispredicted words of speech recognition have rewritten that narrative. We just haven’t recognized it yet. In 2001 recognition accuracy topped out at 80%, far short of HAL-like levels of comprehension. Adding data or computing power made no difference. Researchers at Carnegie Mellon University checked again in 2006 and found the situation unchanged. With human discrimination as high as 98%, the unclosed gap left little basis for conversation.

In passing, interesting-looking thing about why computers can't understand language.

link to scientific article which shows low accuracy of 2006 products

Speech recognition flatlined at 80% accuracy in 2001, and you'd be forgiven for concluding it will never get better: http://bit.ly/aoSCO0 – iconmaster (iconmaster) http://twitter.com/iconmaster/statuses/14370926269

The accuracy of computer speech recognition flat-lined in 2001, before reaching human levels. The funding plug was pulled, but no funeral, no text-to-speech eulogy followed. Words never meant very much to computers—which made them ten times more error-prone than humans. Humans expected that computer understanding of language would lead to artificially intelligent machines, inevitably and quickly. But the mispredicted words of speech recognition have rewritten that narrative. We just haven’t recognized it yet.