You are currently browsing the monthly archive for October 2007.

Software developer Noldus Information Technology has launched FaceReaderTM, a product billed as ‘the first automated software system capable of automatically detecting and analyzing human facial expressions’.

The system claims to recognise specific properties in facial images and interpret them according to ‘the six fundamental human emotions’ – happy, sad, angry, surprised, scared, and disgusted – and a ‘neutral state’. It also automatically classifies faces according to gender, age, ethnicity, and facial hair, all ‘without the need for markers, calibration or training.’ The system promises applications for human-computer interaction, usability testing, behavioral science, medicine, communication and education.

Inventor Marten den Uyl, of development partner VicarVision bv, says the grail of a ‘robust marker-free facial expression recognition tool’ has been sought by many groups around the world. ‘We are proud to be the first who have succeeded.’The new functionality can be combined with The Observer® XT, Noldus’ tool for the collection, analysis, and presentation of observational data, tying facial expression information in with event logging data, captured computer screens, physiological signals such as heart rate, and more. For example, an eye-tracker could be used to find out which picture a person was looking at when showing the emotion ‘disgusted’.

It also promises new applications in ‘affective computing’, whereby other software programs can respond instantaneously to the emotional state of the user. Noldus has global headquarters in the Netherlands and offices across Europe and the United States. Web site: .

from Daily Research News Online

Aaron T Stephan, Wittgenstein, mixed media, 2006


30. Don’t be too hard on theory in philosophy. A broken clock still tells the time right twice every day.

31. Every theory in philosophy has a safety valve. It alone knows the worst truth.

From today, I will post more on my research topic, the human face and the meaning of human facial expression. In each post on this topic, I will contribute a philosophical point, and explore it in some detail with particular reference to Wittgenstein. Comments are always very welcome.  


Can ‘facial recognition’ help Madeleine McCann police analyse picture? by Jonathan Richards (Times Online, September 26, 2007)


A picture taken by Spanish tourist Clara Torres, in north Morocco, which she believes shows Madeleine McCann.

Computer analysis of a picture allegedly taken of Madeleine McCann in Morocco is unlikely to provide more evidence that it is her than simply looking at it, experts said today.

So-called ‘facial recognition’ technology – which analyses an image of a face and seeks to match it with existing images of the subject – was not capable of making a more accurate assessment of a photograph than a human.

At best, all that a computer might conclude was that “this was a photo of a person who resembles Madeleine McCann a bit,” Dr Simon Prince, a senior lecturer in the Department of Computer Science at University College London, said.

The quality of the image was not even good enough to allow for a match – or what referred to as a “facial verification” – using the criteria that are typically applied in the analysis of, say, CCTV footage, Dr Prince said.

The number of ‘pixels’ between the centres of the girl’s eyes – a standard measurement in facial recognition – was 10, whereas usually 20 would be the “bare minimum” required in order for a computer to determine that two subjects matched.

“A typical digital camera might have 5 megapixels, meaning there are 5 million pixels in each image,” Dr Prince said. “In this photo, the area covered by Madeleine’s face makes up about 200 pixels, of which 10 are between her eyes, and that’s not enough. In addition to the resolution being too low, the face is partially occluded by the shadow coming from the woman’s arm, which further hampers identification.”

Facial recognition technology was principally used to search vast databases of pictures – for instance CCTV footage or the internet – that would take humans far longer to examine, he said.

The Child Exploitation and Online Protection (CEOP) Centre uses facial recognition to search through the thousands of photos that are seized in child sex offender investigations, and some cameras now also have facial recognition applications built-in which allow customers to organise their photo collections.

“The technology works by taking various reference points from a subject’s face – the distance between features, for instance – and then comparing those with the same measurements on different pictures,” a CEOP spokeswom said.

One common application is in building security systems, which can – by taking a picture – confirm that a person attempting to enter a certain area is who they say they are.

“Facial recognition works well when it is comparing passport-style photographs where the subject is front-on, the lighting is consistent, and the facial expressions are similar,” Dr Prince said.

“There can be problems, however, when the pose of the subject, as well as the lighting and expression, are different – that’s where all current research in the area is focused.”


Is recognizing a human face like computer analysis? Does it involve a comparison of two impressions, the current perceptual impression and an impression from prior experience? When the two match – “facial verification” – then one recognizes the face one is presently observing?

There are two conceptions at play here: a conception of memory, and a conception of recognition. First, it seems that memory preserves a picture of what has been seen before (PI, 604). This enables comparison of the perceived face with a picture of the face in one’s memory. Second, it appears that recognition consists in a fitting of the perceived face with the previously stored one. In this post, I offer two comments on the second conception. More to follow in future posts.

1. Need facial recognition involve a mental image of what is recognized?

Ordinarily not. It is atypical that people have memory-images when they recongize someone. Sometimes, a memory-image occurs after one has recognized someone. Or, the image may be of someone else associated with the person one is currently perceiving. Rather, the conception of recognition with fitting a picture to what it represents is applicable when “I look at the act of recognition (individual recognition) after the event; and not so much when I look at it to see what actually happened, as when I look at it through a preconceived schema” (PG, 182).

2. Is recognizing comparing what one perceives with a picture of it?

It seems that this metaphor leads to a regress. Even supposing that one’s memory-image and the perceived face fit, one needs to recognize the relation of image and face as a relation of fitting or agreement. One needs therefore to have a memory-image of the fit between the image and the face, and to judge that the image of the fitting fitted with the fitting. Does this even make sense? Is it an essential component of every case of facial recognition? It seems not (BB, 88).

More analysis on this topic to follow later this week and next.

29. If you want to undo a knot it doesn’t help to pull on the ends of the rope. This only makes the knot more intractable. It seems to me that something like this happens in philosophy when conducted in terms of the clash of steel upon steel: realism versus idealism, cartesianism versus materialism, etc, etc. Doesn’t it occur to either party to examine the knot itself? But they just keep pulling on their own end. The result is a diminishing of the philosophical problem, which becomes increasingly difficult to survey under the steely pressure exerted on it at either end. The knot actually becomes smaller and tighter. In some cases, the knotted rope is strained to its breaking point.

Once both parties agree to relinquish their end of the rope it seems natural to meet in the middle to attend to the knot. At this stage, they understand the problem cannot be solved by straightening out the knot. What remains therefore is to attend to the problem by unravelling the knot. This is none too easy, and is not a foregone conclusion. For a knot always weakens the rope it is made in. The crushing, bending, and chaffing forces which hold a knot in place also unevenly stress the rope fibres and diminish its strength. Suppose that the knot is undone, what of it? – the cordage is so battered and over-stretched that it is almost quite unusable; certainly, it was transformed in the process, and not well tied to begin with, but at least now there is awareness on the part of the handlers of the configurations of the knot, its curves, tucks, parallel and non-parallel strands, and so on, and of how they interact.

The rope is supposed to be discarded with once the knot is undone. In philosophy, one is in effect learning to develop one’s own image of thought and thinking and make it available as a conscious critical resource, so that one comes to feel one’s thought as visible.

Alexander Cuts the Gordian Knot (Jean-Simon Berthelemy, 1743-1811)

Excellent new Wittgenstein blog Philosophical Practice/Wittgenstein Reconceived here. It is hosted by Brian Sorrell. For more on Brian, go here.

Here is an excerpt from the October 2 post The Metaphysics of Thought which I hope to comment on shortly.

When we say to each other “I have a thought,” what do we mean by this? We do not mean that we are in possession of a tangible item; rather, we mean that we are prepared to talk or act in a situationally appropriate manner. (Examples: brainstorming about bicycle commuting). (At issue, fundamentally, is what it is like to be an “agent”a rational and social creature engaged in ordinary human activities.)

Compare: I have a belief, reason, joke, idea, dream, desire, secret, wish, opinion, etc. Possession plays out in “demonstration” there is no “having a joke” unless there is also “telling a joke”. If a friend tells us, out of nowhere, that he has a dream, but leaves it at that, we do not know exactly how to react; we expect that he will tell us about his dream and what effect it might have had on him. Sometimes we “make a wish” and it is supposed to remain silent, else we might jinx the wish: this is a behavior we expect, under appropriate circumstances. If a friend said, “I have a secret”, then went on to tell us the intimate details, we would think that something had gone wrong with how they treat secrets.


“Tracing Wittgenstein” is an international research project exploring the Nachlass of Ludwig Wittgenstein while using and developing new tools for net-based scholarly collaboration.

Up to now digital editions have primarily been used on single computers. Compared to traditional books they provide more convenient ways to handle texts and to perform keyword searches on large copora. The Bergen Electronic Edition (BEE) is a significant achievement in this respect.

Yet, the availability of classical texts in digital form is just the beginning of a new kind of philological enterprise. Tracing Wittgenstein expect considerable progress by shifting the focus from local computers to net-based systems. Their goals include: (i) to produce new paradigms, standards, tools and techniques for distributed digital environements (ii) to explore and demonstrate their benefit in practice while commenting on and analyzing manuscripts from Wittgenstein’s Nachlass.

Go here for more information.

The header above is taken from this image:


28. The sound of a musical instrument can be as little disengaged from the instrument itself as expressive singing can be separated from the sung melody that carries it. The sound a paino makes when played is not like singing and accompanying it by the paino, but like “singing with expression”, to use Wittgenstein’s phrase. There are not two objects here. Just as happiness is alive in the facial features of the one who gives it expression, the sound of a musical instrument is lodged in the instrument itself and is what irradiates the  person whose expressive playing ‘calls it forth’.


Paul Wittgenstein

October 2007
« Sep   Nov »

Blog Stats

  • 341,269 hits