This past weekend I had the pleasure of being a mentor for a team competing in the USC SS12 competition. SS12 is a weekend long coding event, organized around the theme of software aiding the disabled. There were 8 teams working on 8 projects (a few teams working on different instances of the same project) working against teams at UCLA.

This competition highlights the very interesting use of AI for aiding the disabled. All of the projects basically come down to using AI to stand in for a missing sense:

-Helping the color-blind see color. -Bridge between the deaf and the non (through a sign-language reading system) -Reading for the blind - My team's project

Reading currency, in particular. - here's an example of someone *else's* currency reader in action doing pretty much what ours (mostly) did. Here's the idea: someone who is visually impaired has difficulty telling what denomination US currency they're holding. The reason for this is that in the US, unlike other nations, all bill denominations are the same size. So, our task was to create something for your phone, which, when pointed at a bill, pronounces what denomination you're holding (see video for the idea in action).

We did this using the Scale-invariant feature transform (SIFT) algorithm. SIFT did the following for us: given an unidentified image, its key features are identified, and compared with the key features of images of US bills we have on file. The reference bill that returns the highest number of matched key features is returned as having highest likelihood of matching. Even if the image is rotated, crumpled, or otherwise messed with, SIFT is able to extract the essential elements that make that image unique.

Interestingly, we got the currency recognition working straight away, and spent the rest of the time struggling with the Android API.

Posted
Authorddini
CategoriesUncategorized
2 CommentsPost a comment

On security issues with cloud computing:

You give your credit card to a waiter at a restaurant and they go in the back room with it. They could be running copies! If you buy something at Amazon, it's pretty damn safe, way safer than giving your credit card to somebody who you don't know, and them going away with it. I mean, think about what that's all about. And we're comfortable with that because we're used to it, but it's not safer than buying something online.

Full interview here

Posted
Authorddini
CategoriesUncategorized

Here's an article on software developed by Ray Kurzweil for the mobile phone which snaps a picture of text, deciphers the text, and produces audible speech:

On how far his technology has come:

Kurzweil released his first reading machine, developed in partnership with the National Federation for the Blind, in 1976; on the day it was unveiled, TV anchor Walter Cronkite used its speech synthesizer as he signed off the air. The device could scan printed pages, decipher the letters, and speak the words aloud. It was about the size of a washing machine and cost $50,000. Stevie Wonder bought the first production model, Kurzweil recalls.

Posted
Authorddini
CategoriesUncategorized

A collaboration between Univ. of Washington, Cornell, and Microsoft has created a system that searches public photos of cities, and uses that data to extract a 3d model of that city.

Our experimental results demonstrate that it is now possible to reconstruct cities consisting of 150K images in less than a day on a cluster with 500 compute cores

Link to paper here.

Link to fancy videos here.

Posted
Authorddini
CategoriesUncategorized

...and report form Microsoft's last MIX conference

User experience (UX) is more than just visual design, information architecture, interaction design (what most experience design folks used to call it), UI development. There's a fifth role: User Research (it puts the U in UX!)

Check it here.

From Jason

Posted
Authorddini
CategoriesUncategorized

StartupSchool 2009 event starts in about an hour right here: Speaker list:

  • Chris Anderson
  • Paul Buchheit
  • Jason Fried
  • Paul Graham
  • Tony Hsieh
  • Mitchell Kapor
  • Greg McAdoo
  • Biz Stone
  • Mark Pincus
  • Evan Williams
  • Mark Zuckerberg
Posted
Authorddini
CategoriesUncategorized

I'm going to appear on a panel of speakers tonight at USC's ACM general meeting, to talk about careers in computer science. In my case success is directly proportional to amount of star trek TNG watched.

edit: Whoops: it's in MHP 105 @ 7PM

Posted
Authorddini
CategoriesMethod in Mind

This past weekend I was a judge at a weekend long programming competition at USC. It was very kind of the ACM to ask me to do it and I definitely had a lot of fun. Here was the situation: something on the order of 10 teams of students were assigned the theme of "Change in your Pocket" on Friday evening, and had until Sunday evening to make a mobile phone application. Nearly all of the teams had no prior experience whatsoever with iPhone or Android development, so the fact that they had anything working at all on Sunday evening that was more than the most trivial application is extremely impressive. Hopefully this fact alone inspires people reading this - if these kids can put together what they did in 48 hours, there's nothing stopping you from making an awesome mobile app.

I don't want to post exactly what they came up with quite yet because many of the teams plan on doing a legit App Store release, so I'll wait for that to happen. But suffice it to say it gives me faith in humanity after seeing abject shit like this for so long.

I ran into an exec from another LA startup over there who was a very nice fellow and he said some things that make me want to punch the web in the face. I mentioned how this amazing talk by David Heinemeier Hansson at startup school was full of all kinds of great old fashioned advice like "your company should make money" and "there was a time when $1,000,000 was a lot of money." He responded by saying that 37signals is a lifestyle company. I said I hesitate to call a >= $30,000,000 business a lifestyle company. He said they're not going to get VC funding with their attitude.

Somehow this perverse notion that getting funding is a signifier for success has got itself into web businesses. It is as if the lifecycle of the web company is supposed to be 1. idea 2. launch 3. get funding 4. DONE. As if getting people to actually buy what you make is secondary.

Here are some pics from the Hackathon event.

And here's one of me being a judgmental prick whilst drinking redbull.

Anyways. Hooray humanity!

Posted
Authorddini
CategoriesUncategorized