H. Choi and Research

connectome...

2010-12-28T10:45:00.001-06:00

now in nyt, connectome is getting more attention... :)
http://www.nytimes.com/2010/12/28/science/28brain.html

in addition to the questions stated in the article, i got some more...

1. structure at one point to functions?

2. embodiment? each brain is connected to its own body... so probably we might

have to slice all the body... otherwise, the difference from different brain structure

may be from different sensory input or different environment...

3. overfitting? each brain has too many millions neurons and we can have "some" data

(like a few data points in a very high dimensional space)...

consciousness meter.

2010-09-21T19:09:00.001-05:00

http://www.nytimes.com/2010/09/21/science/21consciousness.html

this is awesome if we could measure the degree of consciousness like temperature...
they try to measure it based on the information amount in the subject's brain.
if lots of information flows, the brain is very conscious, otherwise, not so much.
i guess this idea or approach is closely related to Dr. Olaf Sporns' research,
which is to make a map of the brain network based on information flow.

anyway, recently, i see a lot of application of information theory to brain science
or even psychology...

maybe i am on the right track... ^^

Autonomous Vehicle Driving from Italy to China

2010-09-21T12:20:00.000-05:00

Autonomous Vehicle Driving from Italy to China
http://spectrum.ieee.org/automaton/robotics/robotics-software/autonomous-vehicle-driving-from-italy-to-china

a very interesting article about an autonomous vehicle testing...

but, do you believe that we are going to have a real autonomous vehicle in, say, 10 or 20 or years?
or even in your life time? or even in your grandchildren's life?

i am sorry but without a big break through from a super genius, i respectfully doubt that....

Philosophy of Science.

2010-06-09T20:43:00.001-05:00

"Philosophy of Science: a very short introduction"
by Samir Okasha

i learned a lot from this book, a really interesting and well written book.
if you consider yourself as a scientist (or to-be) and have never read any book
on 'philosophy of science', try this one. it's easy and worth....

In Search of Memory

2010-05-16T02:56:00.001-05:00

"In Search of Memory" by Eric R. Kandel, winner of the Nobel prize.

a well written summary of neuroscience... with focus on memory.
and his life experience and wisdom.

i should have read this book earlier...
then it could have changed my research and even my life.

this is a must read to engineering or science students...

Henri Poincaré

2010-05-08T17:18:00.000-05:00

http://en.wikipedia.org/wiki/Henri_Poincaré

"creativity and invention consist of two mental stages,
first random combinations of possible solutions to a problem, followed by a critical evaluation."
according to Poincaré's two stages.

prosthetic fingers...

2010-04-11T21:53:00.001-05:00

http://www.nytimes.com/2010/04/11/business/11novel.html
artificial hand... (prosthetic fingers). pretty cool!

Paul Erdos...

2010-04-07T11:26:00.002-05:00

the followings are copied from http://en.wikipedia.org/wiki/Paul_Erdős

Other idiosyncratic elements of Erdős' vocabulary include:

children were referred to as "epsilons";
women were "bosses";
men were "slaves";
people who stopped doing math had "died";
people who physically died had "left";
alcoholic drinks were "poison";
music was "noise";
people who had married were "captured";
people who had divorced were "liberated";
to give a mathematical lecture was "to preach" and
to give an oral exam to a student was "to torture" him/her.

Animation about Searle's Chinese Room Argument

2010-02-27T23:20:00.002-06:00

http://www.mind.ilstu.edu/curriculum/searle_chinese_room/searle_chinese_room.php

one nice animation is way much better than 100 pages' text... ^^

R.I.P. Sam Roweis

2010-02-02T23:05:00.003-06:00

http://www.huffingtonpost.com/2010/01/14/sam-roweis-nyu-professor-_n_421500.html

What a tragic loss to us all in machine learning including manifold learning.

Rest In Peace... Dr. Roweis....

Bees can recognize faces?

2010-02-02T09:59:00.002-06:00

http://www.nytimes.com/2010/02/02/science/02bees.html?emc=tnt&tntemail1=y

They say bees can recognize human faces... Can you believe it? :)

I am not sure about it, but as Dr. Forsyth said, we definitely have to have animal studies

on face recognition research. That's for sure.

- H. Choi

HMAX

2010-01-27T16:38:00.012-06:00

M. Riesenhuber and T. Poggio,

"Hierarchical Models of Object Recognition in Cortex,"

Nature Neurosciece, Vol. 2, No. 11, November 1999. pp 1019-1025.

They say simple cells and complex cells and

complex cells are responsible for invariant properties.

Invariance can be implemented as a pooling mechanism

where there are view-invariant units and view-tuned units.

Hierarchical feedforward network is considered and

the network is based on MAX rather than linear summation (SUM).

MAX is proved to be more robust and invariant than SUM.

That is, Hierarchical MAX has view-invariant object recognition ability

and is supported by biological (physiological) facts.

Anyway, I say, this is a very similar concept to ISA, but a little more flexible.

But this paper doesn't say much of implementation such as

how to get the simple cells or complex cells,

and how to construct the network structure.

See [1] for a specific implementation and examples of HMAX.

In [1], interestingly, simple and complex cells are not learned from data

but designed by second derivative of Gaussians.

[1] T. Serre and M. Riesenhuber,

"Realistic Modeling of Simple and Complex Cell Tuning in the HMAX Model,

and Implications for Invariant Object Recognition in Cortex,"

AI Memo 2004-017, CBCL Memo 239, MIT, July 2004.

- H. Choi

"models of object recognition"

2010-01-26T16:26:00.000-06:00

M. Riesenhuber and T. Poggio,

"Models of Object Recognition,"

Nature Neurosciece Supplement, Vol. 3, November 2000. pp 1199-1204

It's a review paper about object recognition models.

Here is what I got from the paper.

"the distinction between identification and categorization is mostly semantic."

There are two kinds of models for object recognition.

1. view-based model: "objects are represented as collections of view- specific features"

It is something like ICA.

2. object-centered model: there is 3-D model of the object.

It's something like Geon theory.

They took "view-based model" in this paper.

Considering the speed of processing in the brain,

feedback model cannot be the prime model for object recognition.

It should be more like feedforward processing

where invariant properties can be obtained by hierarchical structure.

Making the connections between input image to higher level units as in Fig. 3,

the different tasks (categorization and identification) can be achieved by learning.

- H. Choi

Defense!!!

2010-01-15T16:49:00.000-06:00

DISSERTATION DEFENSE OF

HEEYOUL "HENRY" CHOI

TITLE: Manifold Integration: Data Integration on Multiple Manifolds

Advisor: Dr. Yoonsuck Choe

2:00 p.m. Room 307 HRBB

- H. Choi

two papers accepted!!!

2009-12-11T21:51:00.005-06:00

Thank God! Finally!

Thank the coauthors!

- Heeyoul Choi, Seungjin Choi, Anup Katake and Yoonsuck Choe,

"Learning Alpha-Integration with Partially-Labeled Data,"

in Proc. IEEE Int. Conf. Acousitcs, Speech and Signal Processing (ICASSP),

Dallas, Texas, March 15-19, 2010.

- Heeyoul Choi, Anup Katake, Seungjin Choi and Yoonsuck Choe,

"Alpha-Integration of Multiple Evidence,"

in Proc. IEEE Int. Conf. Acousitcs, Speech and Signal Processing (ICASSP),

Dallas, Texas, March 15-19, 2010.

- H. Choi

"Boom! Hok! A Monkey Language Is Deciphered"

2009-12-08T11:36:00.003-06:00

http://www.nytimes.com/2009/12/08/science/08monkey.html?emc=tnt&tntemail1=y

Monkey is actually speaking!!! ???

interesting...

one more interesting point would be,

we analyze all the video/audio input and speak a lot about the understanding,

while other animals can analyze a lot of input but speaking not so much about it...

is it because their understanding is worse than ours? or just syntax is not enough?

or their memory system is worse?

think about "a dog never barks about yesterdays' burglar." (it might be not so true though)

- H. Choi

tensor analysis

2009-11-09T03:22:00.002-06:00

"General relativity is formulated completely in the language of tensors.

Einstein had learned about them, with great difficulty, from the geometer

Marcel Grossmann. Levi-Civita then initiated a correspondence with Einstein

to correct mistakes Einstein had made in his use of tensor analysis."

- from http://en.wikipedia.org/wiki/Tensor_analysis

Einstein had learned about tensors "WITH GREAT DIFFICULTY."

And Levi-Civita wanted to correct Einstein's misunderstanding.

Hm... interesting... :)

- H. Choi

paper accepted...

2009-08-20T13:57:00.007-05:00

I got a paper accepted to ICONIP2009 as follows... FINALLY... it's like million years ago
when we wrote it ...

Heeyoul Choi, Anup Katake, Seungjin Choi, Yoonseop Kang and Yoonsuck Choe,
"Probabilistic Combination of Multiple Evidence,"
in Proc. 16th Int. Conf. on Neural Information Processing (ICONIP),
Bangkok, Thailand, December 1-5, 2009. (to appear in LNCS)

Thank you all... and thank God...

- H. Choi

Statistics also rules!

2009-08-06T01:58:00.001-05:00

yeap!

http://www.nytimes.com/2009/08/06/technology/06stats.html?hp

- H. Choi

machine learning rules!!!

2009-07-07T18:35:00.004-05:00

http://tech.slashdot.org/story/09/07/03/0143233/IBM-Releases-Open-Source-Machine-Learning-Compiler

machine learning in future will be like computers today.

almost everywhere, there are computers.

now, computers are not just for computer scientists

who btw i don't think "scientists" though even i am a computer science student. :(

likewise, within decades, machine learning will be everywhere.

machine learning will rule :)

- H. Choi

superintelligence

2009-07-07T18:23:00.000-05:00

http://www.forbes.com/2009/06/22/singularity-robots-computers-opinions-contributors-artificial-intelligence-09_land.html

http://www.forbes.com/2009/06/18/superintelligence-humanity-oxford-opinions-contributors-artificial-intelligence-09-bostrom.html

when computers get smarter than us in every thing, it seems to me the end of the world...

computers will get better (or at least same as the before) every single seconds...

and computers will never take a rest.... and they are supposed to be much faster than us...

so, once they get to have the human-level intelligence,

they will be able to prove every theories pretty soon and invent every possible machines...

so that there will be no more questions....

there is no more adventure... no more struggle, no more curiosity...

every stock market will be controlled by computers... every research will be done by computers...

computers will be much better entertainers, so that human entertainers will get fired...

basically, all the work will be done by computers... all the people will get fired...

all that we are going to do is just for fun...

but unfortuately, computers know better way how to make our pleasure...

so we will just sit and eat...and push a button for pleasure...

finally, we will be like pets to computers...

they will feed us with food and pleasure... and they do all the real fun stuff like adventure, research and enterainment...

even though they won't feel that way working on those stuff as we are not feeling fun when we work.

it means ending "the world" and starting a new world where there is no more fun... no more pain... just like a timeless space...

- H. Choi

statistical mechanics

2009-06-29T21:26:00.000-05:00

"statistical mechanics can be viewed as a reconciliation of macroscopic thermodynamic laws with the reductionist approach of explaining macroscopic properties in terms of microscopic components."

- from wikipedia http://en.wikipedia.org/wiki/Reductionism

This is a nice explanation... :)

- H. Choi

history on manifold

2009-05-24T18:16:00.008-05:00

history is on a manifold of space and time or we can say history is a manifold.
that's one of the reasons why we cannot understand the meaning of current
issues clearly. in that sense, the current time is on the edge of the manifold.
that's the reason why we have to look at the "past" to estimate (understand)
the meaning of "present."

still we cannot understand "present" perfectly until long time later when we can
see the issues on the manifold. then we will get to know the meanings more clearly.
unless we lose the facts, just it takes time .

- H. Choi

mirror neurons and motor theory

2009-03-09T17:39:00.005-05:00

"Thus, to this point, whereas the exact nature of the link between speech production and perception remains to be discovered, existing evidence strongly indicates that perceptual systems have a much stronger influence on production than motor systems have on perception."

"We conclude that, rather than providing support for MT, mirror neurons are actually inconsistent with MT and are unlikely to have a central role in speech perception."

from A. J. Lotto, G. S. Hickok and L. L. Holt, "Reflections on mirror neurons and speech perception," Trends in Cognitive Sciences Vol.13 No.3, 2009. pp 110-114.

so, how about other perception tasks rather than speech?

still motor theory is attractive for perception at least to me, and mirror neuron theory seems like a bridge between motor theory and perception.

- H. Choi

Uncertainty and Perception

2009-02-23T11:08:00.000-06:00

Heisenberg Uncertainty Principle says when we observe something, our observation disturbs it. (It sounds weird.)

Neuroscientists say the object exists only while we are observing it. (It is also weird.)

So~ what do you say? :)

Apr. 09, 2008

- H. Choi

being on a manifold.

2009-02-23T11:05:00.003-06:00

Descartes said, 'I think, therefore I am.'

How can we reach to 'therefore I am' from 'I think'.

To present data points, we need data space. Likewise, in order to reach the
conclusion 'therefore I am' we need to find the space for the existence.
Moreover, the 'being' should have any relationship with the space as in set theory.

Thinking is not enough to be 'being' without any relationship with space
(or at least with other data points which makes the relationship with space.)

A data point is in a data space and the manifold gives more meaning to it.

Descartes said, 'I think, therefore I am,' but God said, 'I am who I am.'

Dec. 03, 2006

- H. Choi

Florida! Yeah~

2008-12-02T20:23:00.003-06:00

I am off to Florida tomorrow for two conference to present my papers as below.
(from Dec. 3 to Dec. 12)

Heeyoul Choi, Brandon Paulson and Tracy Hammond,
"Gesture Recognition based on Manifold Learning,"
in Proc. 12th International Workshop on Structural and Syntactic Pattern Recognition (SSPR-08),
Orlando, Florida, Dec. 4-6, 2008 (LNCS 5342 pp. 247-256).

Heeyoul Choi, Ricardo Gutierrez-Osuna, Seungjin Choi and Yoonsuck Choe,
"Kernel Oriented Discriminant Analysis for Speaker-Independent Phoneme Spaces,"
in Proc. 19th International Conference on Pattern Recognition (ICPR-08),
Tampa, Florida, Dec. 8-11, 2008.

Papers are available at my web page.

Thank you,

- H. Choi

"Thank you" mail.

2008-11-16T15:14:00.008-06:00

...
Kernel isomap is a very powerful technique to visualize these nonlinear relations among variables. Thank you for letting us use your MatLab code all these years.
...
- Karl

I'm so glad and honored that somebody is enjoying my work...

Thank God.

- H. Choi

p.s.) All the codes as well as the papers are available at my web page http://people.cs.tamu.edu/hchoi/

Paper accepted :)

2008-08-31T23:09:00.007-05:00

Thank God!
I got a paper accepted to SSPR 2008.
Thank you all.

Heeyoul Choi, Brandon Paulson and Tracy Hammond,
"Gesture Recognition based on Manifold Learning,"
LNCS, International Workshop on Structural and Syntactic Pattern Recognition (SSPR 2008),
Orlando,FL 2008 (Accepted)

- H. Choi

a response to my review...

2008-07-30T16:06:00.005-05:00

Dear reviewer,

This is just to inform you that the author of the above manuscript, for which you have provided a review, has asked us to convey their thanks for your valuable comments.

It's my pleasure. :)

Actually I have reviewed journal papers since 2006, but I've never got this kind of response.
It's so kind of the author and I hope the paper gets published soon.. :)

- H. Choi

AAAI 08

2008-07-16T22:41:00.005-05:00

AAAI 08 is almost over...we have one more day.... but it is a little disappointing...

First of all, the conference place is isolated from real Chicago... To get to the downtown, we have to take a bus and a train... it takes more than half an hour. Moreover, it is kind of dangerous around this place.
Second of all, the focus is different from my research interest... So i couldn't find any nice paper which I am interested in...
Third of all, the foods are not good... The snacks during coffee breaks are not good... and even reception foods look like just snacks.... not real food... (we had 3 reception... 2 of them were like just snacks). When it comes to food, IJCNN2004 in Budapest was perfect... I cannot forget it.
Last, but not least, there are not so many female students.... :(
One more thing, hotel does not have free internet... and everything is soooooo expensive here...

But the Chicago weather is fantastic... :) and I am having really good experiences...
Thank God... :)

- H. Choi

Lipschitz Global Optimization Algorithms

2008-07-09T16:29:00.007-05:00

Dr. Sergeyev gave one interesting talk... check the below announcement.

Lipschitz constant can be used for function optimization. Curvature also can help...
According to Dr. Segeyev, his new method is much faster than DIRECT algorithm. But I don't buy it... because it seems like it depends on how the function looks...
Anyway, it was a really interesting seminar.

BTW, one other thing is he is not going to make his code publicly available... instead, he wants to sell it... :)
And, tomorrow morning, he is talking about a new computer machine which can handle infinite numbers, which sounds weirdly great. :)

-----------------------------------------------------------------------------------------
Industrial & Systems Engineering Seminar

Yaroslav Sergeyev
Distinguished Professor
Dipartimento di Elettronica
Informatica e Sistemistica Universita della Calabria, Italy

3:00 p.m., Wednesday July 10, 2008
Room 203, Zachry

TITLE: "Lipschitz Global Optimization Algorithms"

ABSTRACT
Global optimization problems with multidimensional objective functions satisfying the Lipschitz condition over a hyperinterval with an unknown Lipschitz constant are considered. It is supposed that the objective function can be "black box", multiextremal, and non-differentiable. It is also assumed that evaluation of the objective function at a point is a time-consuming operation. Different techniques based on various adaptive partition strategies are analyzed. The main attention is dedicated to diagonal algorithms, since they have a number of attractive theoretical properties and have proved to be efficient in solving applied problems. In these algorithms, the search hyperinterval is adaptively partitioned into smaller hyperintervals and the objective function is evaluated only at two vertices corresponding to the main diagonal of the generated hyperintervals. It is demonstrated that the traditional diagonal partition strategies do not fulfill the requirements of computational efficiency because of executing many redundant evaluations of the objective function. A new adaptive diagonal partition strategy that allows one to avoid such computational redundancy is described. Some powerful multidimensional global optimization algorithms based on the new strategy are introduced. Results of extensive numerical experiments performed to test the methods proposed demonstrate their advantages with respect to diagonal algorithms in terms of both number of trials of the objective function and qualitative analysis of the search domain, which is characterized by the number of generated hyperintervals.

- H. Choi

Chicago Travel, AAAI 08

2008-07-09T16:19:00.006-05:00

I am going to Chicago for a week from this Saturday. AAAI 08.
I have two papers to be published... (both will be available on my homepage
right after the conference)

Heeyoul Choi, Seungjin Choi and Yoonsuck Choe,
"Manifold Integration with Markov Random Walks,"
in Proc. 23rd Association for the Advanced of Artificial Intelligence (AAAI-08),
Chicago, Illinois, July 13-17, 2008.

Heeyoul Choi and Tracy Hammond,
"Sketch Recognition based on Manifold Learning,"
in Proc. 23rd Association for the Advanced of Artificial Intelligence (AAAI-08),
Chicago, Illinois, July 13-17, 2008.

Both are about manifold learning, though the first one is about integration
which is kind of a new concept and the second one is an application of
kernel Isomap to sketch data set.

Thank you,
- H. Choi

paper accepted :)

2008-06-30T00:44:00.005-05:00

Thank God... I got a paper accepted to ICPR 08.

Heeyoul Choi, Ricardo Gutierrez-Osuna, Seungjin Choi and Yoonsuck Choe,
"Kernel Oriented Discriminant Analysis for Speaker-Independent Phoneme Spaces,"
in Proc. 19th International Conference on Pattern Recognition (ICPR-08),
Tampa, Florida, Dec. 8-11, 2008. (Accepted)

Thank you all,
- H. Choi

Brain-Computer Interface...

2008-05-30T10:23:00.007-05:00

Recently, all the media all over the world are talking about World Science Festival on Wednesday, especially about brain-computer interface, which is so fascinating if we have.

http://www.forbes.com/technology/2008/05/29/mind-control-festival-tech-science-cx_ag_0529mind.html
According to this linked article above, basically the results are from invasive ways, which are relatively so easy...

Anyway, it is going to be amazing if we can control a computer or a car with just thinking. Someday, it will be...

- H. Choi

Q Gospel and Intelligent Design

2008-05-21T16:31:00.007-05:00

It seems like Q Gospel and Intelligent Design (ID) are very similar.

Q Gospel says there might be some original source (Q gospel) which might have affected to other gospels so that the other gospels look similar, even sometimes some parts are same. On the other hand, ID says there might be some original source which might have affected to the whole universe so that a lot of phenomena or biological organs look similar, even sometimes some parts are same.

I know these are supported by totally different groups and there is no connection between these two discussions. But what I am saying here is the way how they are accepted by people. Q gospel is treated as a logical (or even scientific) argument and ID is treated as a religious faith (definitely not scientific) .

Of course, the level of the original sources are different. Q gospel is just one imaginary book and ID has one supernatural being as an original source. Here, I am just saying about the approach and the intention.

- H. Choi

Complex Cells and Object Recognition

2008-05-19T13:42:00.006-05:00

S. Edelman, N. Intrator and T. Poggio, "Complex Cells and Object Recognition," NIPS97.

Note that this paper was published in 1997, which is 'long time ago.'
It says complex cells-like filter has invariant recognition. And, actually, it is really simple. Apply one filter for complex cells and check the correlation of the filter output to classify.

The problem is how to implement the complex cells-like filters. And we have one answer, which is independent subspace analysis (ISA) which is kind of a generalization of independent component analysis (ICA). BTW, ICA is a filter like simple cells.
The real problem is these theories are not like math theories. So the performance really depends on the situations such as noise or background or the shape of object.

Our brain is sooooo amazing... How does it do all these complicated stuffs?

- H. Choi

Active Control..

2008-05-17T22:53:00.003-05:00

K. L. Harman, G. K. Humphrey, and M. A. Goodale, "Active Manual Control of Object Views Facilitates Visual Recognition," Current Biology, Vol. 9, No 22. pp1315-1318. 1999.

To sum up, first, observers who have active control on the object have better recognition than others who see the same sequence passively. The response time is shorter but accuracy is the same which is a little ackward. Second, active observers concentrate on certain angles than others. That is, this paper is kind of the first paper to emphasize on the active control.
But the reason why it is efficient is still a research topic to go.

In a word, active control is important on recognition, which now we all know and agree to... :)

- H. Choi

3D Geon Classification

2008-05-17T00:46:00.007-05:00

W. Xing, W. Liu and B. Yuan, "A Novel Integrated Scheme for Extracting Superquadric-based Geons from 3D data," in Proc. of ICSP'04, 2004.

To my knowledge, this paper is the first paper to try to implement Geon Theory, even though this is just about Geon classification. They build up a superquadric-based model for 3D object data and optimize the parameters. And then they apply SVM to the extracted features from the parameters of the model to classify the object into geon classes.

This is not about 2D image but 3D data. And this makes a model for each 3D data and extract some features from the model parameters, which might be rotation and transition invariant. This does not sound natural and not a visual recognition.

- H. Choi

Geon Theory and Its Implementation (?)

2008-05-16T23:35:00.007-05:00

K. Casey and C. Exton, "A Java 3D Implementation of a Geon Based Visualisation Tool for UML," PPPJ 2003, Kilkenny City, Ireland, 16-18 June, 2003.

I was googling to check if there has been any kind of implementation of Geon Theory. So, when I typed in 'goen' and 'implementation,' this paper popped up to my surprise. I was thinking this theory was too hard to be implemented.

But... it turned out that this paper is just about the implementation of a visualization tool based on geon theory... not implementation of geon theory, in that the geons and their relations are equivalent to ULM diagram, which is a visual language for modeling software designs.

Anyway, so far, to my knowledge, there has been no successful implementation of Geon Theory. If you know any implementation, plz let me know. :)

- H. Choi

Three-dimensional object recognition

2008-05-16T00:13:00.002-05:00

M. J. Tarr, P. Williams, W. G. Hayward and I. Gauthier, "Three-Dimensional Object Recognition is Viewpoint Dependent," Nature Neuroscience, Vol. 1, No 4, 1998. pp275-277.

It is a little against Biederman's RBC (recognition-by-components) which is based on geons and their relations. Biederman's geons are viewpoint independent. This paper says they are not independent.

Obviously, object recognition is a viewpoint-dependent process. So this paper makes more sense. And this paper makes a way to connect this whole things to X which means a lot to me*.
One thing more interesting is one of the assumptions of whole this geon theory, which is that recognition of individual geons are equally accurate. Actually in real pattern recognition, it is a big deal. We should handle this first, if we want this theory.

* X refers to something that I am currently working on.

- H. Choi

Visual Recognition

2008-05-15T23:57:00.003-05:00

K. Grill-Spector and N. Kanwisher, "Visual Recognition: As soon as you know it is there, you know what it is," Psychological Science, Vol 16, No 2, 2005. pp152-160

It tests two hypotheses about processing order between detection and recognition, between basic level recognition and other level recognition. To sum up, detection (or segmentation) and recognition work at the same time and general categorization is faster than finer level identification. And we can not tell nothing more than these, which are still hidden mysteries.

It is really amazing and intuitive that detection and recognition are not independent and work together. We should try to recognize an object and the class information should be applied to segment the object and the segmentation result should be used to classify the object again and again. Does it sound familiar to you? Yes!!! It sounds like the EM algorithm. How beautiful!!!

- H. Choi

Visual Object Recognition

2008-05-09T23:08:00.001-05:00

Chapter 4 Visual Object Recognition, Irving Biederman
in An Invitation to Cognitive Science, 2nd Edition, Visual Cognition, Vol2.

It's about a psychological understanding on viewpoint-invariant object recognition. Especially it says about Geon Theory. Geon is a component of an object, which is viewpoint-invariant and object recognition is based on geons and their relations with other geons.

So far so good...
As always in some psycological research, however, we don't know how to find these geons and the relations from image inputs. With different illuminations, different angles and noise and background, finding geons is a big deal itself in machine-based object recognition. Even the experiments in this book were conducted with human brain. It says just what the result of brain function on visual input is, not how it works in details. So it doesn't say that much about how to implement this concept in machine.

- H. Choi

Programming the Universe

2008-05-05T14:49:00.001-05:00

Seth Lloyd, "Programming the Universe," Knopf, 2006

He tries to explain everything of this universe including the origin based on information. In order to do that, he covers broad areas such as information theory, computational theory and quantum computing theory as well as physics, chemistry and biology... almost everything around me... :)
It's a really interesting book... and I learned a lot from it, though some parts are hard to get...

Anyway, my first thought right after wrapping it up is the Fourier series... Say, there is a function, f, in nature, then some basis functions can approximate it. If the number of basis functions goes infinite, the approximation approaches to the function f. In other words, if it is not infinite, it always has some error between the true function and the approximation. Interestingly, I feel like the 'infiniteness' belongs to kind of a supernatural being.

So, always, we have error to explain something, as long as we don't know the true shape. Even the general relativity theory has some errors to explain the true principle in the universe. (It is really really good approximation.) Finally, we never get to the true principle never.. but get to have a just approximation which is most plausible... I mean, the historical truth is totally hidden from scientists... forever.

This book tries to explain the universe in a new way, and it is really nice...
But still in my head I have stupid questions like "So what?" still confused...

- H. Choi

Robust Kernel Isomap

2008-05-04T13:31:00.002-05:00

Thank God...
Thank Dr. Seungjin Choi...

One of my papers below is ranked first in the hottest articles of Pattern Recognition
journal (Oct - Dec. 2007) by sciencedirect.com.

Heeyoul Choi and Seungjin Choi,
"Robust Kernel Isomap,"
Pattern Recognition, vol. 40, no. 3, pp. 853-862, 2007.

Check this out.
http://top25.sciencedirect.com/index.php?journal_id=00313203

Thank you all...

- H. Choi

On-Orbit Calibration

2008-05-02T18:12:00.005-05:00

D. T. Griffith, P. Singla, J. L. Junkins, "Autonomous On-Orbit Calibration Approaches for Star Tracker Cameras," AAS/AIAA Spaceflight Mechanics Meeting, No. 02-102, AAS, San Antonio, TX, Jan 27-30, 2002.

In addition to a batch calibration, we need on-orbit calibration because of the environmental changes over the life of the camera film. This paper describes the star tracker camera and proposes a way to estimate the distortion map of the star locations on-orbit (almost same word as the 'online' in machine learning), assuming the offsets and the focal length are given.
Basically they use the least square method with a couple basis function sets such as polynomials, sinusoidal functions or radial basis functions. By the health monitoring process, it updates the map only when the error is greater than a threshold.

It also includes a review of the least square method and the recursive least square method, which, by the way, looks like Kalman filter. The piecewise approximation is not an interesting part because usually the map would be smooth enough so that a few basis function might be good enough. And, this piecewise approximation needs a lot of basis functions which is computationally so expensive.

Nice paper for novices like me in the on-orbit calibration problem.

- H. Choi

Finding offsets and the focal length of a camera

2008-05-02T14:18:00.004-05:00

M. A. Samaan, "Toward Faster and More Accurate Star Sensors Using Recursive Centroiding and Star Identification," Ph.D. Thesis, Texas A&M University, August 2003.

Chapter 3 is titled 'Ground Calibration for the Bore-Sight Offsets and the Focal Length.'

He uses the least square minimization (LSM) method recursively to find optimum offsets and the focal length which minimizes the error between inner product of reference stars and the estimated inner product of measured stars.

- H. Choi