3D Reconstruction of a face from a single image

I don’t know if scary, jaw-dropping or simply impressive, but it turns out that there is already an algorithm developed here in Germany by Professors Volker Blanz and Thomas Vetter, that reconstructs a face in 3D from one image. Yes! out of a single image!

Maybe it wouldn’t sound that amazing at first sight, but you have to think about all the possible applications. Besides identifications, you can entirely play around with the information out of peoples’ faces, prediction, tracking, augmented reality, medical procedures, etc.

Is it something new? No way! It was presented in the International Conference on Computer Graphics and Interactive techniques of 1999! That’s right, fella, 14 years ago!

But why nobody used this impressive technique? Well, my guess is, of course, because of the computation times of it. Yes yes, very good, looks great and reconstructs faces pretty good, BUT took 50 minutes to reconstruct a face.

But wait a second! It was 14 years ago, right? With slower computers. Certainly, according to their paper, they used an SGI R10000 processor, which at that time was as powerful as 250 MHz… Well, I think is time to try it again with our new multi-core processors at several GHz.

Is it still on development? Did the creators give up? Are they preparing some new surprises? Well, we don’t know; but so far I can say that this technique has tons of applications with the new devices focusing in computer vision applications.

Just check the demo about this great procedure and the explanation of its development:

Everything about Finance and Investment

For some weeks now, I’ve been learning about Finance and Market, it is a very challenging field for me and, as usual, has given me a lot of new knowledge.

This time, through the great group “Big Think“, Bill Ackman, CEO of Pershing Square Capital Management, explains fast but on detail everything you need to know about Finance and Investment.

Taking us by the hand and with really simple examples, his very graphical explanation gets rid of any common mistake we could have.

Highly recommended to learn a bit more. Less than an hour but a lot to catch.

Predator Algorithm

The more I go into Machine Vision, the more I get amazed by the Engineering behind the most common thing around me.

Now, this post is not abut something that we can see daily now, but I’m sure it’s gonna be soon among us. Very soon. I’m talking about the Predator Algorithm (originally named TLD), developed by czech scientist Zdenek Kalal. This algorithm is implemented in such a way that the computer learns continuously detecting the features and objects in it.

Yes, it learns and with time detects easily every object. But well, nothing better than a graphical explanation of what I’m trying to explain, by the inventor himself:

The creator of this algorithm had such a success that he already started his own company to start the implementation of this great Engineering tool: TLD Vision.

These are the kind of things that really inspire.

The Fundamental Matrix song

Annoying, exciting, boring, awesome… Computer Vision and its applications might be sometimes a roller-coaster of emotions, but it is always a pleasure to work with. Some of those familiar with Vision systems, might be aware of some nice properties and most of all, some fancy tools that help us to play around with images and computers; but one important thing that no one should forget in this field is the so-called Fundamental Matrix. If you have still some doubts about its development, then here you have a bit of its application:

Looking for the lyrics. Well, I totally recommend you to go to the website of Daniel Wedge, the creator of this totally entertaining song.

Build your own 3D Scanner!

Yes, it is possible and you can do it. Actually you don’t have to be a total expert in programming or Maths. Yes yes, you have to know some good stuff, but being a nerd or a genius is not the point.

Gabriel Taubin, an Argentinian Mathematician researching in Brown University is in charge of this project and made it available for everyone, so if you have 3D Computer Vision as your hobby, then this is the perfect start. As I said, you don’t have to be an expert but you need to go deep into it and it will be totally amazing, I promise. Just have a look to the website:

BYO3S

The final results would be amazing and they provide every kind of tool that you may need. It seems that the used methods vary, but that’s just extra fun. I really encourage you to try it, because it’s cheap, fun and totally useful.

The following video is NOT of the project, but it shows you how accessible is to build your own 3D scanner.

But don’t forget the Kinect, boy!

Language Immersion

In my daily struggling trying to learn the German language I use to try new tools and techniques to improve my skills and be more understandable, but of course many times it doesn’t work just because “Deutsch ist eine verkackte Sprache” as my flatmate says.

But well, I love the goddamn language and I will always learn it. So I decided to install an extension for Chrome called “Language Immersion”, which is an experimental extension that changes randomly the words in the text of the websites that you are visualizing, so it mixes the normal text of your language with some words in the language you wanna learn. You can manage how deep you wanna be into the language ranging from Novice to Fluent (5 different levels)

Simple but an effective idea, isn’t it? Let me post the video that explains how this works:

I’ve tried it and after 5 minutes I stopped it. I think it was going worse than it should. Wasn’t helping at all. Now, I don’t consider myself an expert in German or that I express myself perfectly (nor in English) but I certainly find the translations really shitty. I can say it by now for German, which is a complex language that depends so much in the context and every word in a sentence makes sense when you know the other words too. If you have a sight of what Dativ, Akkusativ and other related things are, then you can get my point. The translation in Google Translate is not optimal and when the context is cut, it falls instantly like a drunk bitch with heels. I don’t wanna imagine it with Hungarian!

Is good that they are using the translation tool from Google, it is pretty massive. They even have Swahili and Yiddish available… but not Japanese! I know is another alphabet, but come on! They have Chinese!

Only 5 levels of immersion don’t give too much to play with. I was in the 4th and around 20 or 25% of the words were translated. Changed to the 5 and then all of them were translated.

A good thing is the possibility to highlight the translated words and when you don’t know the meaning you just click on the highlighted word or expression and it shows it back in the original language. But even better, if you wanna know how is it pronounced, you just hold the pointer over and it says it automatically. Of course you can disable all these features and even the extension itself whenever you want.

But yeah… is a shit and it actually could confuse more than it helps. A good idea with bad translations, few options to choose and a lack of intuition; but as I stated, it’s still experimental, the creators said. I hope gets better soon. By the moment I’ll kick it out of my Chrome.

The infinite monkey cage

Science and Comedy have been always connected everywhere because for radical and revolutionary ideas, it is needed a bit of humor and consideration. Both are groundbreaking and quite entertaining if you are in the proper mood.

However only few have had the balls to mix them, play around with them and success with it. One of them is the case of The infinite monkey cage, a comedy series produced by the BBC, where physicist Brian Cox and comedian Robin Ince discuss about the relevant topics in Science, such as the origin of life, Probability, Sound, Chemistry, etc.

Before the only science and rational debates mixed with comedy that worth watch were the ones of Bill Maher in his show, where in a round table he discusses different topics of the daily American lifestyle with many personalities. And it was good, politics, religion, science and other disciplines were part of this round table. However, the truly scientific point of view was some times missing due to… well… Bill Maher, although a really good and critical personality, has no scientific background.

This time TIMC offers us Profr. Brian Cox, a guy with an awesome personality and a complete understanding of “the stuff called Science”, and Robin Ince, the acid debater that pulls the attention of the public.

You can check them in the Apple Store if you wanna download their Podcasts, I highly recommend them to those who wanna embrace Knowledge and Reason in a funny way. Otherwise, you can also visit their channel in the BBC podcast website.

Long life TIMC!

My first day in Computer Vision

A new semester in the Uni has begun and in this second week I am already feeling the first pressured tasks. No probs, this time planning and hard work will be a constant besides a good health caring and exercise. Perhaps less Internet Facebook is what I need.

This semester I will struggle a bit with two very interesting courses: 3D Computer Vision and Image Understanding in English and German, respectively. Before I had “Machine Learning Method for Computer Vision Applications” in the same responsible chair but it was so few application and had other courses to attend that required more attention, so I couldn’t experience more in it. That’s gonna change in this semester.

Both courses are held by two very experienced professors. 3D CV is taught by Nassir Navab, whose experience in research is impressive, winning international awards and being a top recognized researcher in the world. He is going to be my lecturer in this Semester. He already began giving some introductory class showing the great advantages of 3D Computer Vision and, most of all, its applications. I was hypnotized, it was great and that’s why now I’m willing to share everything I learn and find in Internet about this matter. It’s really cool and exciting for me.

The second lecturer is Carsten Steger, who’s in charge of the class “Bildverstehen” (Image Understanding) that, as you may suppose, is in German. He is another experienced guy but his field is not in the Universities, it is the industry. He gives solution to real-life problems and that experience is shared in his class. My first impression of him is really good, he’s an open guy with a relaxed style and a very good idea of what he is talking about, besides he can truly explain himself.

Both good professors, both great courses, and an excellent semester to start experimenting with the sources of the student life. From now on you will probably see more often some posts related to Computer Vision, my new bitch (and vice versa).

But we will start with Computer Vision Online, the largest website about CV out there, I think. They offer the newest stuff about CV and its applications, besides some other curiosities and interesting sources, where you can find books, software and even you might find a suitable job for you if you are really into Computer Vision. There are tons of positions in many Universities and Labs. I recommend you to check it out!

And finally I share this video from the chair of Computer Aided Medical Procedures & Augmented Reality (CAMPAR) in the TUM, where the researchers just adapted a Kinect sensor and started to track a guy’s body to virtually visualize it as in a magic mirror. Watch it!

¡Ahí se ven!

Sweet Home Alabama (Electric Version)

All of us know this song, all of us like it, all of us recognize it when we hear it (always played in Oktoberfest), but never in my life I would think to play it as in the following video. The creators Eric Goodchild and Steven Caton built two gigantic tesla coils to generate different sounds with the sparkles and stuff… well, the result is very impressive and absolutely fun:

According to the description of the video:

The primary drive system for the coils consists of high power semiconductors arranged into an H-Bridge switching configuration. During a spark event, the coil is pulsed on for a few hundred millionths of a second. During this short time, thousands of amps circulate within the primary tank circuit and the energy is coupled into the secondary resonator through magnetism.

So what appears to be a continuous burst of sparks is actually a specific number of sparks generated per second. By modulating the number of sparks that emit from the coil each second, different tones can be produced by the coils.

Have a look to their videos, they’re not only playing that song, but also have many other different hits such as In the Hall of the Mountain King, Pirates of the Caribbean, House of the rising sun, Dueling Banjos, etc. Check also their channel, they have cool shit with lasers and stuff.

Science fucking rocks!

dotSUB

En un rato de relax de la clase de Inteligencia Artificial de Stanford, me puse a curiosear cómo es que llevan a cabo la transmisión de la clase por internet y me di cuenta que andan en busca de traductores para poner el contenido de la clase en varios idiomas y así poder compartir más eficazmente el material.

¿Pero cómo traducirlo? De eso me di cuenta cuando en un comentario, el encargado de la clase menciona que usan la tecnología de dotSUB ¿De dot… qué?

Pues resulta que existe una herramienta en internet que nos permite traducir de forma conjunta nuestros videos favoritos. ¿Haz visto la opción CC que tiene youtube en la parte inferior de la ventana de los videos? Ajá esa herramienta que sirve para transcribir el audio y en algunos casos traducirlo a otros idiomas. Bueno, pues esa herramienta en youtube usa algoritmos para identificar el audio y transcribirlo. Bueno, pues al ser algoritmos de aprendizaje parcialmente supervisado, están llenos de errores y hay más videos en youtube subiéndose que gente supervisándolos, así que todavía un buen rato para tener un sistema de traducción bien organizado.

Sin embargo, existe una herramienta que nos ayuda con eso: dotSUB, una página en donde podemos acceder a videos en diferentes idiomas, para así ayudar a traducirlos a nuestro propio idioma. Si eres de las personas que dominan dos o más idiomas, facilmente puedes crear tu cuenta, acceder a los videos y sencillamente transcribirlos a tu idioma. Si no sabes ningún idioma, puedes disfrutar del trabajo de los otros.

Lo mejor de este proyecto es que se trata de un trabajo en equipo, en el que varias personas pueden estar editando la transcripción y subtítulos de los videos. Como muestra está el siguiente video.

Ya saben, morros. Ayuden a la banda y transcriban.