Since zoomify (and other such interfaces) uses image pyramids, the zoomable interface uses a bunch of small image files, I could not host it on this wordpress site (or didn’t have the time/inclination to figure it out).

I’ve hosted it here via Coral CDN.

I would like to use openzoom for this, maybe at a later point.

For now, this project is close. Thanks Aishwarya, for lending your eyes.

See previous post.

Using those and metapixel, I created a composite which you can see below:

Next step is to use something like zoomify to let you see the actual component eyes in detail.

(see previous).

Following a bunch of sources, (including an easier python binding framework), I finally settled upon compiling opencv and using the new python bindings on ubuntu 64. Too bad I couldn’t use the pyopencv bindings.. looked cool but no x64 support yet.

After mucking around, I got it to capture frames from a webcam and detect my face and my eyes and track it. I’m using the default haarcascade_frontalface_alt.xml and haarcascade_eye.xml cascade files that come with opencv.

Here’s the sample image

In a nutshell, face detection, eye detection (any object detection) using opencv works pretty well as long as you have a properly defined haarcascades file for it.

Next up, rewriting the script to a runnable script for extracting and saving eyes from images.

Getting there…

One good idea would be to extract eyes from existing photographs of people that I already have. That would mean detecting, cutting, pasting and saving eye images from thousands of pics.

Sounds like a programming job. You’d think!

Turns out there aren’t any free libraries out there.. and coming up with a pattern matching algorithm on your own is not trivial..

Enter OpenCV, an open source computer vision package started by Intel. Besides giving you lots of image manipulation stuff, it gives you object detection using HaarCascades, based on a paper by Viola and Jones, “Rapid object detection using boosted cascade of simple features”, Computer Vision and Pattern Recognition.

The detect object feature basically uses trained classifiers based on known object images to detect similar objects in a given image. The classifiers are stored in xml files that the library can load up. The opencv framework even gives you tools to create and train your own classifiers AND a set of sample cascade files. There are other cascade files available on the net.

Awesome.

Here’s an excerpt about the talk posted on TED.com

Jill Bolte Taylor got a research opportunity few brain scientists would wish for: She had a massive stroke, and watched as her brain functions — motion, speech, self-awareness –- shut down one by one. An astonishing story.

What I got out of the talk is that once we have the ability to think selectively from the right side of the brain, we enter a sort of zen mode of existence. Which makes me think about the mode that we (or people who can) get into when they’re meditating. Even more fascinating is the possibility of switching from the right to the left at will, and being able to co-relate the individuality aspects (left brain) with the connectedness and universality aspects (right brain) in day to day life.

Fascinating stuff. This probably adds more to brain research and our place in existence than all the mind/brain research done in the last hundred years.

The content on TED is amazing. Chris Anderson (of Wired and long tail fame) has done a tremendous job of ensuring that the content is available for everyone to view. Contrary to what I’ve heard from some folks, I don’t believe TED is elitist at all.

The “religious people praying for the bull to rise” bit ..

boing boing reporting on people praying to the bull

A search on google returns 18 million hits.

Get your ranting/15 minutes of fame/self publishing fix somewhere else. Every social site has some form of expression/microblogging features.

But I keep trying…

Dear Diary, tonight I saw a shirtless man run down the middle of the street. Being chased by another shirtless man. Whose pants were falling down. Because he had just taken off his belt. Which he then began using to beat the first man.

Good times.

http://jwz.livejournal.com/924938.html

It’s based on a statistical analysis of what humans perceive to be beautiful.

When human raters are presented with a collection of shapes and asked to rank them according to their aesthetic appeal, the results often indicate that there is a statistical consensus among the raters. Yet it might be difficult to define a succinct set of rules that capture the aesthetic preferences of the raters. In this work, we explore a data-driven approach to aesthetic enhancement of such shapes. Specifically, we focus on the challenging problem of enhancing the aesthetic appeal (or the attractiveness) of human faces in frontal photographs (portraits), while maintaining close similarity with the original.