OMORROW I shall do the eighth stage of the Mr. Fitness competition. So far I have gotten first place in almost every stage, but tomorrow’s stage is hard and I have done almost no practice towards it. It’s so much easier to just do stuff on the computer (photos below are from today and yes, I’ve stayed home all day).

fter persistence and a new type of mask put in place (with a little trick to penalise for miscorrespondence around the top) I have been getting good validation results again, with over 98% for the first 50 pairs I have tested (just one mistake some far). Some of the harder surface pairs have not been reached yet.

In an attempt to master GMDS as cross-identity discriminator I have further cut down the process, which now operates through a pipeline of reverse dilation, as shown in the first image beneath. The second shows a broader mask working upon false pairs and mostly failing, which is probably what we want. In terms of performance, as long as the true pairs are similar enough (some are far harder than others, e.g. expression variation), we are able to get decent results. Running this on the whole database again would not help beat results that we got around December, though. Several experimental modifications are hard to identify as means of reverting back to old versions. A lot of those were made to facilitate diffusion as a supported (surrogate) option.

I have reduced the number of points in GMDS to just 10 because it seemed as though it would significantly speed up the process without compromising too much in terms of performance. The experiments were then run on “hard” pairs, giving verification performance of almost 90%, depending on the method used.

In an attempt to understand how well one can do with just 10 samples in GMDS (because it is faster and insensitive to small changes) I took some of the hardest classification cases and ran repeated coarse GMDS on them, reaching a success rate of only 75% or thereabouts. This falls short because we are assuming that only for false pairs will we have improper correspondence, whereas for true pairs everything will be perfect. As shown in the images produced from the same false pair, sometimes a good correspondence is found, but usually not (symbolised by white colours in the dots, e.g. in the third example from the top, on the right hand side).

The example at the very bottom shows that even for different identities a decent correspondence can be found, which gives rather low stress values.

In order to mitigate or altogether annul the effect/artifact of flipping, I have made the two surfaces asymmetric, with centres of the eyes removed because there’s too much noise there, depending where the eyes look and how open they are (in some surfaces, the eyes are deliberately moved to challenge algorithms).

Several empirical results show that increasing the number of vertices, even doubling them, still seems not to help much in any way. So, I have isolated some difficult cases and I am trying to cut out the sources of ambiguity.

EVERAL years ago I wrote about an old backup procedure of mine. Sometimes people set up a job to make a backup, but what about removing backups that are too old to matter? If a directory/file needs deleting based on age, with wildcards one could run something like:

rm ~/some_file-`date -d "7 day ago" +%d%m%Y`*
rm ~/some_file-`date -d "6 day ago" +%d%m%Y`*

Or quick and dirty (risky if there’s a mixture of files in the said location):

find . -atime +7 -exec rm {} \;;

There’s nothing complicated to it. Once it’s done once, it can be modified thereafter.

EOPLE often fail to understand that a troll will strive to be inflammatory so as to push for censorship, then play the “victim” card. This is one of the most effective ways for the troll to discredit its target — to claim to be suppressed and then see how far it can be pushed. The solution to this is not easy; one is to let the troll do the trolling and another is to actually censor the troll. Does anyone have good advice on the matter?

ut crudely, government is a structural entity that helps others organise under the assumptions that without supervision from above people would act most ruthlessly among their species, unlike almost any other species. The following video from 2 months ago is about government. The key point is at the end — about Obama making it legal to assassinate US citizens whom he views as dangerous.

ACK in 2004 I set up this Web log where I posted every day, and almost without a single exception (usually I posted around 3 posts per day). It was only in 2006 that I started to focus on more specific issues and developed an expertise in particular subjects. Techrights was a lot more focused than this personal blog, which has not produced about 2,000 posts.

Last Thursday I crossed the 15,000-article milestone over at Techrights. It still serves a lot of requests owing (for the most part) to the huge archives. Now, just to clarify, there is also a lot of traffic in some other sites such as this one, but when I stopped writing on a regular basis here in schestowitz.com the traffic dropped from about 20,000 hits per day (gradual decline). I wrote 15,000 articles/posts in Techrights, which now serves about a quarter of a million hits per day (since 2010), giving me little reason to post in this personal blog any longer. At Techrights, over the course of 5+ years, I have been posting at the pace of almost 8 posts a day for 5 years (but at the highest points a lot more than the average, with a peak of 31 posts in one day).

Techrights has reached a sort of plateau now — a point where it stays about the same when it comes to traffic, despite expansion in content. The visitors count stopped growing some time around 2009 when I was entering Twitter and was on Twit TV, a TV show I was invited to be in for 1.5 hours or so, speaking for the site. These days I am busier with my jobs and my fiancée, but I still find a lot of time to dent, tweet, blog, and occasionally record shows (although not as much as of late because my co-host and I are exceedingly busy). Thanks to all those who are supporting my work and spreading the key points (even contributing time, HT to “wallclimber” among others). I will carry on doing this for a long time to come. Activism, to me, always comes first (well, family comes first, but it’s a close second).

2009

2012

espite the fact that I cannot rollback to old versions of the algorithm — those that worked much better — I have run experiments on half of the entire Texas database. The performance was vastly inferior because of changes that I have made over the past couple of months.

Over the past few days I experimented with other smoothing schemes, as a colleague once suggested that I do. The improvements were very minor once performance was assessed with some ROC curves (few dozens of pairs). The general idea was, by removing areas or artifacts that distract from identity-related entropy, we can improve overall performance. The impediment has always been that, given too lenient and sensitive a measure, the items being compared are not identity-related but pose-related, noise-related, etc.

In my most recent experiments I have been looking into more kinds of masks, but none so far offers a magic solution with state-of-the-art performance.

Symmetric mask where eyes are removed and the nose tip too, in order to accentuate topology and delve into areas more “stable” than eye surface

Examples of correct matches where the mask is symmetric (the “classic” mode)

Examples of correct matches where the mask is cut at nose level

Examples of correct matches where the mask is intentionally asymmetric (to avoid flipping over)

I decided to tweak this further, testing GMDS for surfaces with holes.

Dealing with the existing algorithm, which performs more weakly than months ago (due to experimental changes that are hard to selectivity rollback), I have some new results. I have tested it with and without support (difference in dilation/distance for FMM cutoff), but in both cases the ROC curves were too disappointing to be worth plotting and showing. The approach does not seem suitable for good performance to be reached. With or without the most performance-promising algorithm, the general observation is that GMDS does not deal well with these holes (connected torus-like shapes).

Example of pairs of surfaces where eyes and nose tip got removed

An increasing level of geodesic dilation where eyes are cropped out but not the nose tip

ROC curves for the above