jump to navigation

A personal note April 11, 2008

Posted by Johan in Off Topic.
2 comments

I’m taking a break. It isn’t clear to me that a blog is the optimal format for a weekly or fortnightly 1000+ words on technical matters. It’s too much, too seldom for most readers. In any case, blogging has mainly been about entertaining myself, and it doesn’t do that for me anymore. I may be back at some point, or I may join another blog. Watch this space to find out.

As an aside: I will get my BSc in Psychology from York this summer. I have received an offer for a PhD at the MRC Cognition and Brain Sciences Unit at Cambridge. Curiously, this blog was mentioned by one of the panelists during my interview. I have no idea how much weight, if any, that my efforts here carried in the decision to admit me. It nevertheless makes for a natural and happy ending to this blog. I started writing these posts because I wanted some direction and purpose for my extracurricular readings. Starting this autumn, my own research may provide that outlet instead.

A big thank you to everyone who read, commented, or linked to my posts.

Holiday July 1, 2007

Posted by Johan in Off Topic.
add a comment

Gotland is an island off the coast of Sweden. Expect more blogging in two weeks or so.

Let’s play internet memes June 22, 2007

Posted by Johan in Links, Off Topic.
add a comment

Orli at Neurontic tagged me with one of those irritating, yet strangely appealing memes. I’m doing this one out of nostalgia – I spent much of my teenage years filling out inane questionnaires (e.g., do you eat the stems of broccoli?), and this is really more of the same. At least Orli doesn’t threaten 7 years of bad luck if I don’t pass it on…

Superfluous Information About the Author:

1) I do in fact eat the stems. Who doesn’t?

2) There is a defunct 16-channel mixing board in my closet. This is a remnant from a past life, in which I thought I’d be a rock star.

3) I honestly believe that orange marmalade and cheese is the perfect sandwich combination.

4) As a child, my dream job was to be a parking attendant. To this day, my family mocks me about this.

5) I once had a job that involved literally standing by the side of the road, counting the cars that went by. Incidentally, this was shortly before I decided that University would be a good idea after all.

6) My biggest concern at the moment is the health of my succulents. Arty picture below:

I have patiently cared for them since they were just a few centimetres each. I’m soon leaving York for the summer, and they will have to survive for a few months with no attention. I know they’re meant to be desert plants, but I’m not entirely sure that they’ll make it.

7) Like many psychologists keen on neuroscience (I imagine), I have brief moments of despair where I wish I had done a degree in biology instead. Then I glance over to my partner’s textbooks (right now: “The Physiology of Flowering Plants”), and I’m reminded I made the right choice after all.

8) I love cooking. Currently, I’m trying to master the risotto.
I tag:

Puzzlebrain
Retrospectacle
Bohemian Scientist
Cognitive Daily
Madam Fathom
Memoirs of a Postgrad
Mixing Memory
Peripersonal Space

The Rules:

1. Players start with 8 random facts about themselves.
2. Those who are tagged should post these rules and their 8 random facts.
3. Players should tag 8 other people and notify them they have been
tagged.

My exams will be over on Wednesday. There might just be some serious blogging after that.

Google images now detects faces (poorly) June 17, 2007

Posted by Johan in AI, Face Perception, Off Topic, Sensation and Perception.
2 comments

Google has somewhat secretly rolled out a special filter for its image searches, that enables you to restrict your searches to faces. Geeks in the know say that this technology comes from their purchase of Neven Vision, a company I’ve never heard of before.

To use this technology, simply add &imgtype=face to the search URL – adding it in the search box won’t work (although Quicksilver users will find that it does work if you use the Google search plugin – I have no idea why).

Face detection algorithms are all the rage in computer science, and there are lots of implementations out there. I thought I’d compare Google to the competition.

An initial test suggests that Google does rather well. Compare a search for “house” with the image filter and without it. There are only faces (including a certain british-comedian turned american-doctor) in the former, and only houses in the latter.

However, it turns out that it’s quite easy to trip Google up once you throw faces of non-human animals at it. According to Google, this is a face:

But it’s not. So how about the competition? There are many online demos of face detection algorithms, but I quite like PittPatt by the Face Group at Carnegie Mellon. You can just plug in a URL rather than having to upload anything, and it’s quite fast. Pittpatt puts rectangles over each part of the image where it thinks a face is. Nothing lights up for the poor dog above.

Let’s make things more difficult for Pittpatt. Gorillas look more like people, right? Google produces mostly faces, but also this:

Ah, Pittpatt seems confused:

Apparently there are a few facial features in there, but I think the blue colour of the frame indicates uncertainty – from the gallery of uploaded pictures on Pittpatt, it seems the most obvious faces are framed in green or at times yellow.

How about chimps, then? Google fails this one spectacularly – all the faces on the first page are non-human, except for a bearded guy and a few pictures of George W. Bush. Go figure. To be fair, this probably has less to do with Dubya’s chimp-like features and more to do with Google’s page rank system, where a picture that is linked a number of times with the word “chimp” nearby ends up on page one of the results for that term. So Bush doesn’t necessarily look like a chimp, it’s just that the Internet thinks he does.

Google thinks this is a face. And you might be inclined to agree, but for the sake of argument I’m assuming that Google wants their algorithm to pick out human faces, not general primate or mammal faces. Pittpatt produces only another weak blue cube, this time restricted to the mouth of the chimp.

So what can we conclude here? This test is of course terribly unfair – I’ve only picked faces that Google failed so at best, Google could only have done as badly as Pittpatt. But it seems like Google’s face detection algorithm isn’t all that great compared to the alternatives. Another possibility is that they’re just trying not to be specist, but I somewhat doubt that. Also, we have learned that a fake statue of King Kong apparently looks more human than a fat dog or a young chimp, according to Pittpatt. I’m not sure what to do with that information.

In any case, it is pretty fascinating that computers can get this good at face detection. While primate faces can look like a human face to us, there is no way you would confuse the two. I guess you might interpret the ambiguous output of Pittpatt as something similar – there is something face-like there, but it’s not quite it.

Update: Other geeks inform me that the face detection algorithm that Google uses is probably trained by either of their two online games Peekaboom or Image Labeler. I couldn’t figure out how Peekaboom works without registering, but the point of the image labeler game is basically for both players to give the same name to a picture. With a training procedure like that, you suddenly start to see how the chimp above might appear under a “face” search – while “chimp” might be the first word you try there, then possibly “ape,” “face” isn’t going to be far behind. This actually points to a problem of human-trained computers – they acquire all our idiosyncrasies and imperfections, for better and for worse.

Coursework is due shortly, no time to blog June 13, 2007

Posted by Johan in Links, Off Topic.
add a comment

Meanwhile, enjoy this informative news story, which reveals that Alzheimer’s may be misdiagnosed in many patients.

Or not.

Follow

Get every new post delivered to your Inbox.