 |
 |
 |
 |
Professor |
Associate Professor |
Assistant Professor |
Assistant Professor |
|
Recognition, analysis and expression of images and letters are studied in the multimedia
systems laboratory. In addition we devote positive cooperation in Japanese deep space exploration with Aizu Research Cluster for Space Science (ARC-Space), Research Center for Advanced Information Science and Technology (CAIST) established in this year, and aim to be one of the kernel organizations in this research field near future. The 3-D motion and the 3-D shapes of the object are analyzed, understood and expressed by computer from the images taken by multi TV camera or video camera in the study of computer vision and/or the 3-D stereovision. Our work has greatly contributed in Hayabusa project. The succession of landing on Itokawa by Hayabusa in November, 2005 owed to preciseness of 3D shape model of Itokawa by University of Aizu very much. And also development of HARMONICS (HAyabusa Remote MONItering & Commanding System) has contributed very much in operation. Three lab members are also energetically contributing in KAGUYA (SELENE) project, the Japanese lunar exploring mission and playing a major role in LISM, the remote sensing camera system. The major research targets are centered on lunar shape recognition, such as lunar terrain analyses, crater counting, understanding and detailed whole lunar geographic mapping. Furthermore, they are engaged in analyzing the lunar mineral composition using the category classification technique from color information of lunar images and investigating the future moon surface land usage. We are considering almost all kind of computer method to contribute lunar exploration, such as automatic crater counting, operation plan and log managing system, integration of lunar topological map from both Terrain camera (TC) data and Laser Altimeter (LALT) data, and so on. Furthermore, we are engaged also in space exploration programs in Japan including planetary and an asteroid exploration inquiry plan and contributing in research in lunar and planetary science. In addition, we are supporting Japanese deep space exploration with our original conception and cooperating with both domestic and international organization, while the computer technology becomes necessary in this research field. In the on-line handwriting character recognition system, the fundamental study to use the handwriting letter as the input system of the computer is investigated. The character recognition is one of the most important fields on the image processing. And also collaborations with the Republic of Korea are implemented by this lab. Laboratory members have participated actively in scientific meetings, both in Japan and abroad. They have presented and participated in seminars, and in presentation of scientific results in fully refereed publications. |
Refereed Journal Papers
| [asada-01:2009, demura-01:2009, naru-01: 2009] |
M. Ohtake, T. Matsunaga, J.
Haruyama, Y. Yokota, T. Morota, C. Honda, Y. Ogawa, M. Torii,
H. Miyamoto, T. Arai, N. Hirata, A. Iwasaki, R. Nakamura, T. Hiroi,
T. Sugihara, H. Takeda, H. Otake, C. M. Pieters, K. Saiki, K. Kitazato,
M. Abe, N. Asada, H. Demura, Y. Yamaguchi, S. Sasaki, S. Kodama,
J. Terazono, M. Shirao, A. Yamaji, S. Minami, H. Akiyama, and J.-L.
Josset. The global distribution of pure anorthosite on the Moon. Nature,
461:236–240, 2009. |
| It has been thought that the lunar highland crust was formed by the crystallization
and floatation of plagioclase from a global magma ocean, although the actual generation
mechanisms are still debated. The composition of the lunar highland crust is
therefore important for understanding the formation of such a magma ocean and the
subsequent evolution of the Moon. The Multiband Imager on the Selenological and
Engineering Explorer (SELENE) has a high spatial resolution of optimized spectral
coverage, which should allow a clear view of the composition of the lunar crust. Here
we report the global distribution of rocks of high plagioclase abundance (approaching
100vol.%), using an unambiguous plagioclase absorption band recorded by the
SELENE Multiband Imager. If the upper crust indeed consists of nearly 100vol.%
plagioclase, this is significantly higher than previous estimates of 82-92vol.% (refs
2, 6, 7), providing a valuable constraint on models of lunar magma ocean evolution. |
|
| [asada-02:2009, demura-02:2009, naru-02:2009] |
N. Asada, N. Miura, H. Demura, and
N. Hirata. Automatic tracking of impact fragments. World Review of Science,
Technology and Sustainable Development, 7(1/2):181–194, 2010. |
| The automation of the motion analysis of impact fragments has been requested in
the field of hypervelocity impact experiments. Some fragments were automatically
tracked on images cut from an impact experiment moving picture. A combination
method of the two dimensional continuous dynamic programming (2DCDP) method
proposed by Oka (1998) and the Helmert transform is proposed and applied in
tracking fragments. After some improvements, tracking of fragments was performed
sufficiently and the effectiveness of this method was confirmed. As a result, physical
quantities of impact fragments such as translation velocities, rotation velocities and
so on were derived from the analysis. |
|
| [asada-03:2009] |
N. Hirata, O. S. Barnouin-Jha, C. Honda, R. Nakamura, H. Miyamoto,
S. Sasaki, H. Demura, A. M. Nakamura, T. Michikami, R. W. Gaskell, and
J. Saito. A survey of possible impact structures on 25143 Itokawa. Icarus,
200:486–502, 2009. |
| We determined the morphologies and dimensions of possible impact craters on the
surface of Asteroid 25143 Itokawa from images taken by the Hayabusa spacecraft.
Circular depressions, circular features with flat floors or convex floors, and circular
features with smooth surfaces were identified as possible craters. The survey identified
38 candidates with widely varying morphologies including rough, smooth and
saddle-shaped floors, a lack of raised rims and fresh material exposures. The average
depth/diameter ratio was 0:08±0:03: these craters are very shallow relative to craters observed on other asteroids. These shallow craters are a result of (1) target
curvature influencing the cratering process, (2) raised rim not being generated by
this process, and (3) fines infilling the craters. As many of the crater candidates have
an unusual appearance, we used a classification scheme that reflects the likelihood of
an observed candidate’s formation by a hypervelocity impact. We considered a variety
of alternative interpretations while developing this scheme, including inherited
features from a proto-Itokawa, spall scars created by the disruption of the proto-
Itokawa, spall scars following the formation of a large crater on Itokawa itself, and
apparent depressions due to random arrangements of boulders. The size-frequency
distribution of the crater candidates was close to the empirical saturation line at
the largest diameter, and then decline with decreasing diameter. |
|
| [demura-04:2009, naru-03:2009] |
T. Noguchi, A. Tsuchiyama, N. Hirata, H. Demura,
R. Nakamura, H. Miyamoto, H. Yano, T. Nakamura, J. Saito, S. Sasaki,
T. Hashimoto, T. Kubota, M. Ishiguro, and M. E. Zolensky. Surface morphological
features of boulders on Asteroid 25143 Itokawa. Icarus, 206:319–326,
2010. |
| On the sub-kilometer S-type asteroid, 25143 Itokawa, some boulders on rough terrains
seem to be exposed without any powdery material covering. Based on surface
morphological features, there are two major types of boulders: one has rounded
edges and corners (rounded boulders), while the other has angular edges and corners
(angular boulders). The surface features of the rounded boulders suggest that
they have hardness heterogeneity and that some may be breccias. The angular boulders
appear to be more resistant to impact disruption than the rounded ones, which
may be due to a difference in lithology. The major constituents of Itokawa may be
LL chondrite-like brecciated lithology (rounded boulders) along with a remarkable
number of boulders suggesting that lithology is atypical among LL chondrites (angular
boulders). Some of both types of boulders contain intersecting and stepped
planar foliations. Comparison with meteorite ALH76009 suggests that the planar
foliations may be marks where rocks were torn apart. As lithified breccias cannot be
formed on present-day sub-kilometer-sized Itokawa, it is reasonable that boulders
with various lithologies on Itokawa were formed on its large ancestor(s). The rubblepile
structure of Itokawa suggested by its low density (∼ 1:9g=cm3) indicates that
boulders on Itokawa are reassembled fragments formed by catastrophic disruption
of large ancestor(s). |
|
| [demura-05:2009, naru-04:2009] |
T. Morota, J. Haruyama, H. Miyamoto, C. Honda,
M. Ohtake, Y. Yokota, T. Matsunaga, N. Hirata, H. Demura, H. Takeda,
Y. Ogawa, and J. Kimura. Formation age of the lunar crater Giordano
Bruno. Meteoritics and Planetary Science, 44:1115–1120, 2009. |
| Using the Terrain Camera onboard the Japanese lunar explorer, SELENE (Kaguya),
we obtained new high-resolution images of the 22-kilometer-diameter lunar crater
Giordano Bruno. Based on crater size-frequency measurements of small craters
(< 200 m in diameter) superposed on its continuous ejecta, the formation age of
Giordano Bruno is estimated to be 1 to 10 Ma. This is constructive evidence against
the crater ’s medieval age formation hypothesis. |
|
| [demura-06:2009, naru-05:2009] |
T. Morota, J. Haruyama, C. Honda, M. Ohtake,Y. Yokota, J. Kimura, T. Matsunaga, Y. Ogawa, N. Hirata, H. Demura,
A. Iwasaki, H. Miyamoto, R. Nakamura, H. Takeda, Y. Ishihara, and
S. Sasaki. Mare volcanism in the lunar farside Moscoviense region: Implication
for lateral variation in magma production of the Moon. Geophysical
Research Letters, 36:L21202, 2009. |
| Accurate estimates of the duration and volume of extrusive volcanism of the Moon
are essential for understanding the lunar thermal evolution. Here, using new highresolution
images obtained by the SELENE Terrain Camera, we determined the
thicknesses and ages of basalts in Mare Moscoviense, one of the most prominent mare
deposits on the farside. Mare volcanism in Mare Moscoviense was active for at least -
1.5 Ga following the formation of the Moscoviense basin. Mare basalts are estimated
to be at least 600 m thick, corresponding to a total volume of 9; 500 − 16; 000km3.
The long duration and large volume of extrusive volcanism are plausibly attributed
to the thinner crust of the Moscoviense basin relative to those of other farside
basins. From a comparison with mare volume within a same-sized nearside basin,
we concluded that a magma production in the farside mantle was 3-10 times less
than that of the nearside. |
|
| [demura-07:2009, naru-06:2009] |
M. Ishiguro, R. Nakamura, D. J. Tholen, N. Hirata,
H. Demura, E. Nemoto, A. M. Nakamura, Y. Higuchi, A. Sogame, A. Yamamoto,
K. Kitazato, Y. Yokota, T. Kubota, T. Hashimoto, and J. Saito.
The Hayabusa Spacecraft Asteroid Multi-Band Imaging Camera: AMICA.
ArXiv e-prints, 0912:4797, 2009. |
| The Hayabusa Spacecraft Asteroid Multiband Imaging Camera (AMICA) has acquired
more than 1400 multispectral and high-resolution images of its target asteroid,
25143 Itokawa, since late August 2005. In this paper, we summarize the design
and performance of AMICA. In addition, we describe the calibration methods, assumptions,
and models, based on measurements. Major calibration steps include
corrections for linearity and modeling and subtraction of bias, dark current, readout
smear, and pixel-to-pixel responsivity variations. AMICA v-band data were
calibrated to radiance using in-flight stellar observations. The other band data were
calibrated to reflectance by comparing them to ground-based observations to avoid
the uncertainty of the solar irradiation in those bands. We found that the AMICA
signal was linear with respect to the input signal to an accuracy of ≪ 1% when
the signal level was 3800 DN. We verified that the absolute radiance calibration of
the AMICA v-band (0.55 micron) was accurate to 4% or less, the accuracy of the
disk-integrated spectra with respect to the AMICA v-band was about 1%, and the
pixel-to-pixel responsivity (flatfield) variation was 3% or less. The uncertainty in
background zero-level was 5 DN. From wide-band observations of star clusters, we
found that the AMICA optics have an effective focal length of 120.80 mm +=− 0.03
mm, yielding a field-of-view (FOV) of 5.83 deg x 5.69 deg. The resulting geometric
distortion model was accurate to within a third of a pixel. We demonstrated an
image-restoration technique using the point-spread functions of stars, and confirmed
that the technique functions well in all loss-less images. An artifact not corrected
by this calibration is scattered light associated with bright disks in the FOV. |
|
| [jpshin-01:2009] |
Yejin Kim, Yuga Ahn, Jungpil Shin, and Changwon Kim. Detection of Denitrification Completion Using Pattern Matching Method in Sequencing
Batch Reactor(SBR). Korean Society of Environmental Engineers (KSEE),
29(8):944–949, Aug 2007. |
| The profiles of on-line sensors such as DO, ORP and pH can provide useful information
about pollutant removal reaction in sequencing batch reactor. For detection of
denitrification completion, the nitrate knee point from ORP profile has been considered
as a main indicator of denitrification completion. However, many researchers
pointed out that the nitrate knee usually disappeared when the progress of denitrification
is so fast and it makes the fault at detection of denitrification completion.
In this paper, dynamic time warping(DTW) method and discriminant analysis were
used to detect and isolate the profiles of two cases, denitrification completed and
uncompleted. As the results, proposed mehtods can detect state of denitrification
successfully. |
|
| [jpshin-02:2009] |
Yejin Kim, Yuga Ahn, Hyosoo Kim, Jungpil Shin, and Changwon Kim.
Development of a Diagnosis Algorithm of Influent Loading Levels Using Pattern
Matching Method in Sequencing Batch Reactor (SBR). Korean Society
of Environmental Engineers (KSEE), 31(2):102–108, Feb 2009. |
| DO, ORP and pH values measured during SBR operation can provide information
about removal reaction of organic contaminants and nutrient materials in the reactor.
It is already generalized control strategy to control reaction phase time using
their special patterns indicating the end of the removal reactions. However, those informations
are limited to point out the end time of oxidative reaction in the aerobic
phase or reductive reaction in the anoxic phase without giving quantitative value
of influent loading level. In this research, a diagnosis algorithm which can estimate
the loading level of carbon and ammonia as high, medium and low was developed
using the basic measurements like DO, ORP, and pH. It will be possible to know the
level of influent loading rate from those online measurements without experimental
analysis. |
|
| [jpshin-03:2009] |
Wondu Chang and Jungpil Shin. Dynamic Positional Warping: Dynamic
Time Warping for Online Handwriting. International Journal of Pattern
Recognition and Artificial Intelligence (IJPRAI) (SCI), 23(5):967–986,
July 2009. |
| This paper addresses the problem of dynamic time warping (DTW) causing unintended
matching correspondences when it is employed for online two-dimensional
(2D) handwriting signals, and proposes the concept of dynamic positional warping
(DPW) in conjunction with DTW for online handwriting matching problems. The
proposed DPW allows sub-signal translations without any additional costs when
their starting points are matched to other points through the matching process.
Because the movement of sub-signals is cost-free, except for the distance between
the two starting points, an adequate movement-finding and matching similar subsignals-
could significantly reduce the matching cost. This feature causes a tendency
to match with the least amount of sub-signal movement in the result. In order to
evaluate the proposed method of solving this problem, two experiments were conducted:
an accuracy test for matching similar handwriting and a utility test for signature verification. For the former, we proposed the new concept of ideal matching
between two handwriting signals using the affine transformation; the results of
this test verified the superiority of the proposed DPW over conventional methods
in reducing matching errors. Further, DPW significantly outperformed the conventional
methods in the latter test. |
|
| [jpshin-04:2009] |
Yejin Kim, Hyeon Bae, Hyosoo Kim, Jungpil Shin, and Changwon Kim.
Settling state detection of SBR based on DO profile analysis using Dynamic
Time Warping. The Korean Journal of Chemical Engineering (SCI),
27(2):504–510, March 2010. |
| Settleability of activated sludge is one of the most important variables for stable
solid-liquid separation of the biological wastewater process. Moreover, effective decanting
is a sensitive work at sequencing batch reactor (SBR) which has a settleability
fault, such as filamentous/non-filamentous bulking, deflocculation and sludge
rising. It is not easy to monitor sludge settleability directly without any specified
measurement system, but the values of settling phase can be measured by installing
basic measuring instruments for monitoring the process in the reaction stage of SBR.
In this study, patterns of DO profiles measured at settling phase showing significant
difference according to the process status were used to explore whether a problem
occurs or not. To use this information, an online algorithm was developed to detect
and diagnose the settling fault. A dynamic programming method that is one of the
pattern recognition methods was used to detect and classify the patterns of the DO
profiles. Based on the discriminant function made by dynamic time warping results
and an extracted variable from DO profiles, the classification rules were generated.
With the discriminant function, the settleability fault was detected and classified
successfully. |
|
| [naru-07:2009] |
T. Michikami, A. M. Nakamura, and N. Hirata. The shape distribution
of boulders on Asteroid 25143 Itokawa: Comparison with fragments from
impact experiments. Icarus, 207:277–284, 2010. |
| Laboratory impact experiments have found that the shape of fragments over a
broad size range is distributed around the mean value of the axial ratio 2:sqrt(2):1,
which is independent of a wide range of experimental conditions. We report the
shape statistics of boulders with size of 0.1-30 m on the surface of Asteroid 25143
Itokawa based on high-resolution images obtained by the Hayabusa spacecraft in
order to investigate whether their shape distribution is similar to the distribution
obtained for fragments (smaller than 0.1 m) in laboratory impact experiments. We
also investigated the shapes of boulders with size of 0.1-150 m on Asteroid 433 Eros
using a few arbitrary selected images by the NEAR spacecraft, in order to compare
those with the shapes on Asteroid Itokawa. In addition, the shapes of small- and
fast-rotating asteroids (diameter <200 m and rotation period <1 h), which are
natural fragments from past impact events among asteroids, were inferred from
archived light curve data taken by ground-based telescopes. The results show that
the shape distributions of laboratory fragments are similar to those of the boulders
on Eros and of the small- and fast-rotating asteroids, but are different from those on
Itokawa. However, we propose that the apparent difference between the boulders of
Itokawa and the laboratory fragments is due to the migration of boulders. Therefore, we suggest that the shape distributions of the boulders ranging from 0.1 to 150 m
in size and the small- and fast-rotating asteroids are similar to those obtained for
the fragments generated in laboratory impact experiments. |
|
| [naru-08:2009] |
R. Nakamura, T. Matsunaga, Y. Ogawa, S. Yamamoto, T. Hiroi, K. Saiki,
N. Hirata, T. Arai, K. Kitazato, H. Takeda, T. Sugihara, S. Kodama,
M. Ohtake, J. Haruyama, and Y. Yokota. Ultramafic impact melt sheet
beneath the South Pole-Aitken basin on the Moon. Geophysical Research
Letters, 36:22202, 2009. |
| The Spectral Profiler onboard the Japanese lunar explorer Kaguya conducted the
first hyperspectral survey around the South Pole-Aitken basin (SPA) on the Moon
that is one of the largest impact structures in the Solar System. The radiative
transfer modeling revealed that fresh crater central peaks inside SPA are commonly
composed of an ultramafic assemblage dominated by Magnesium rich orthopyroxene,
suggesting a homogeneous layer buried under SPA. The extensive ultramafic layer
could be a relic of a gigantic impact melt pool produced by the SPA-forming impact.
The preponderance of orthopyroxene could have resulted from significant fractional
crystallization of the lunar magma ocean prior to the onset of plagioclase floatation. |
Refereed Proceeding Papers
| [asada-04:2009] |
W. Kawamae, N. Hirata, K. Kitazato, N. Asada, H. Demura, Y. Ogawa,
C. Honda, and J. Terazono. Development of 3D Web-based Data Archive for
Hayabusa Mission. In 41th Lunar and Planetary Science Conference (LPSC
2010), page 1687, Houston, March 2010. LPI and NASA JSC. |
| Data archive with more interactive interface for searching the data of Hayabusa mission
is desired. The three-dimensional model allows users to search the specific area
data of irregular shape body. |
|
| [asada-05:2009] |
S. Morita, N. Asada, H. Demura, N. Hirata andJ. Terazono, Y. Ogawa,
C. Honda, and K. Kitazato. Approach to Crater Chronology with Fourier
Transform of Digital Terrain Model. In 41th Lunar and Planetary Science
Conference (LPSC 2010), page 1687, Houston, March 2010. LPI and NASA
JSC. |
| We validated the effect of crater position, diameter and number using the transformed
images and their average values. As a result, it showed fourier transform of DTM may
be able to be used for geological age estimation instead of crater counting. |
|
| [asada-06:2009] |
T. Matsunaga, M. Ohtake, J. Haruyama, S. Yamamoto, Y. Ogawa,
R. Nakamura, Y. Yokota, T. Morota, C. Honda, M. Abe, T. Nimura, T. Hiroi,
T. Arai, K. Saiki, H. Takeda, N. Hirata, S. Kodama, T. Sugihara, H. Demura,
N. Asada, J. Terazono, and H. Otake. Updates on Scientific Results and
Products of SELENE Spectral Profiler. In 41th Lunar and Planetary Science
Conference (LPSC 2010), page 1687, Houston, March 2010. LPI and NASA
JSC. |
| pdates on scientific results and products of the SELENE Spectral Profiler (SP) will
be given. Scientific results highlight recently published papers and ongoing research.
Status of available products and a plan for future products will be presented. |
|
| [asada-07:2009] |
N. Hirata, J. Haruyama, M. Ohtake, T. Matsunaga, Y. Yokota,
T. Morota, C. Honda, Y. Ogawa, K. Kitazato, Y. Shibata, T. Sugihara,
H. Miyamoto, H. Demura, and N. Asada. Remote Sensing Study of a Large Lunar
Crater Jackson. In 41th Lunar and Planetary Science Conference (LPSC
2010), page 1585, Houston, March 2010. LPI and NASA JSC. |
| We investigated a large lunar crater Jackson with LISM/SELENE data to reconstruct
the impact event forming the crater from distributions of its ejecta and other
associated features. |
|
| [demura-08:2009] |
J. Terazono, R. Nakamura, S. Kodama, N. Yamamoto, H. Demrua,
N. Hirata, Y. Ogawa, S. Sobue, and H. Okumura. Lunar and Planetary Informatics
System Based on Geographical Information. In ISPRS Working Group
IV/7 Extraterrestrial Mapping & Advances in Planetary Mapping 2009, 2009. |
| Lunar and Planetary Informatics System Based on Geographical Information |
|
| [jpshin-05:2009] |
Tetsuya Takanashi, Won-Du Chang, and Jungpil Shin. The Use of Pen
Inclination and Pressure Information to Improve On-line Signature Verifcation.
In Proceedings of The 1st International Workshop on Aware Computing
(IWAC09), pages 644–647, Aizu-Wakamatsu. Japan, Sep. 2009. Japan Society
and Fuzzy Theory and Intelligent Informatics, Japan Society and Fuzzy
Theory and Intelligent Informatics. |
| In this paper, the features that have personal characteristic using pen inclination and
pressure information are discussed. Forging a pen inclination and pressure information
is difficult because it is not visible. Four features using invisible information are proposed
and their characteristics are discussed. Proposed features calculated by physical
vector analysis are verified by SVC2004 database using DP matching algorithm. As
a result, the new feature named Down improves the recognition rate and reliability.
Average of correct verification rate is 94.57 % and variance is 0.667. |
|
| [jpshin-06:2009] |
Wondu Chang and Jungpil Shin. A Stochastic Stroke Model for Variable
and Personalized Handwriting Synthesis. In Ibrahiem M. M. El Emary, editor,
Proceedings of Fourth International Conference on Intelligent Computing and
Information Systems, pages 705–711, Cairo, Egypt, March 2009. Ain Shams
University, Egypt, ACM SIGMIS. |
| This paper proposes a stochastic stroke model which synthesizes variable handwritten
characters preserving one’s writing style. Our fundamental concept of the stochastic
model is thinking a stroke as consecutive state changes of segments. After clustering
segments into several states, a number of characters are presented as a directed
graph with probabilities of state changes. To support the model, two modifications
of dynamic time warping techniques are presented: one is allowing division to ensure
one-to-one matching between segments, not loosing detailed shape information; the
other is a method of generating a template to align segments among many signals. By
employing stochastic method at segment levels, our model enables generating various and natural handwritten characters with small number of training data. We synthesized
3,600 English alphabets and numbers from 180 training characters showing the
variance of synthesized characters, and their DP distance proved that the synthesized
characters keep one’s writing style well. |
|
| [jpshin-07:2009] |
Wondu Chang and Jungpil Shin. Fast Unsupervised Classification for
Handwritten Stroke Analysis. In Jose Cordeiro Joaquim Filipe, editor, Lecture
Notes in Business Information Processing (Proceedings of 11th International
Conference on Enterprise Information Systems (ICIES 2009)), pages 918–927,
Milan, Italy, May 2009. INSTICC, Springer Berlin Heidelberg. |
| This paper considers the unsupervised classification of handwritten character strokes
in regards to speed, since handwritten strokes prove challenging with their high and
variable dimensions for classification problems. Our approach employs a robust feature
detection method for brief classification. The dimension is reduced by selecting feature
points among all the points within strokes, and thus the need to compare stroke signals
between two different dimensions is eliminated. Although there are some remaining
problems with misclassification, we safely classify strokes according to handwriting
styles through a refinement procedure. This paper illustrates that the equalization
problem, the severe difference in small parts between two strokes, can be ignored by
summing all of the differences via our method. |
|
| [jpshin-08:2009] |
Hiroshi Naito, Wondu Chang, and Jungpil Shin. Detecting Alcohol
from On-line Handwritten Signature. In Proceedings of 14th Conference of the
International Graphonomics Society, pages 18–21, Dijon, France, Sep. 2009.
International Graphonomics Society, ACM. |
| This paper proposes a system which can detect the effect of alcohol consumption from
handwritten signatures for the purpose of strengthening on-line signature verification
systems. In spite of the popularity of the signature verification; the influence of alcohol
has not been covered very much in literature. As the preliminarily step of this research,
we examined the robustness of the current signature verification system, and the
dynamic decreases of accuracy in the cases where an intoxicated status is found.
This means that the signatures of intoxicated persons need to be separated before
the verification for stable results. Three features are introduced in this purpose: the
variance of characters ’heights and widths, average angles of curves, and average
writing times. We tested our system over a specific period of time, with our system
achieving the highest accuracy (85 |
|
| [jpshin-09:2009] |
Akira Wada and Jungpil Shin. Three Dimension Virtual Calligraphy
Simulation with Pen Table. In Proceedings of The 1st International Workshop
on Aware Computing (IWAC09), pages 628–631, Aizu-Wakamatsu. Japan,
Sep. 2009. Japan Society and Fuzzy Theory and Intelligent Informatics, Japan
Society and Fuzzy Theory and Intelligent Informatics. |
| The purpose of this study is realization of 3D virtual calligraphy simulation that is able
to do on computer with pen tablet sensuously. To do the simulation sensuously, we
propose three models. The first model is a 3D virtual writing brush model. The second
is drawing field model, and last is droplet model based on unique and artistic stroke
drawn by writing brush. These models are able to transform to the most suitable shape by information acquired from pen tablet. This simulation is very comfortable system.
Therefore, so many people of various ages were able to do simulation sensuously and
gaily in school festival. Therefore, we confirmed this simulation is the applicative
calligraphy simulation. |
|
| [jpshin-10:2009] |
Yusuke Shimizu and Jungpil Shin. Learner-Friendly Kanji Learning System
with Radical Analysis. In Proceedings of The 1st International Workshop
on Aware Computing (IWAC09), pages 632–637, Aizu-Wakamatsu. Japan,
Sep. 2009. Japan Society and Fuzzy Theory and Intelligent Informatics, Japan
Society and Fuzzy Theory and Intelligent Informatics. |
| This paper presents a novel friendly Kanji learning system using Radical Analysis to
enable foreign people and elementary school students to learn Kanji by an interesting
and efficient way. This way is for characters to analyze for each radical, to divide into
some parts, and to correct strokes for each divided part. Here, the Radical Analysis
Database (RAD) is used for dividing characters. RAD is a database to analyze characters
for each radical and divide into some parts. On the other hand, characters are
corrected by using a threshold. The threshold is a judgment value in the correction
and learners can set it freely by handling threshold bars put on the interface. Then,
the novel system is improved so that learners can set thresholds for each divided part.
Since each bar corresponds to each part, the system judges whether each part is corrected
or not according to set thresholds. Hence, since learners can freely determine
radicals or parts in which they want to be instructed intensively, they can practice
only their radicals not good or part of the character and easily master difficult characters,
too. In addition, an animation helps learners understand the order of strokes
virtually. Since each stroke used in this animation is displayed with different colors,
learners can also understand virtually where the same strokes are from and to at once. |
|
| [jpshin-11:2009] |
Yang Koo Lee, Jungpil Shin, and Keun Ho Ryu. Historical Data Management
for Sensor Network Applications. In Proceedings of The 1st International
Workshop on Aware Computing (IWAC09), pages 685–690, Aizu-
Wakamatsu. Japan, Sep. 2009. Japan Society and Fuzzy Theory and Intelligent
Informatics, Japan Society and Fuzzy Theory and Intelligent Informatics. |
| Sensor networks and modern hardware technologies have made it possible to introduce
the concept of ubiquitous computing to the real world applications. In sensor network
applications, sensor node hardly manages a large volume of accumulated data in a
local storage. There are some cases in which several range queries issued by user
overlap to some extent. Sensors therefore may make duplicate responses to these
queries owing to the overlapping criteria. To solve this problem, in this paper, we
propose an integration system to provide some adaptive strategies for sensor data
storage, historical query processing with an efficient energy consumption, and query
dissemination. Our system uses a proxy to handle data and queries between sensor
network and the application system. Proxy recreates a query into sub-queries, each
for a suitable query range, and merges each result from application system and sensor
network. This operation allows redefining the query explicitly to disseminate to sensor
network. In addition, sensor nodes with local storage store the collected data using
reduction strategies that combine several tuples having temporal distances close with one another. This operation helps discard redundant information in sensor nodes while
still allowing us to obtain high accuracy of query response. |
|
| [jpshin-12:2009] |
Won-Du Chang and Jungpil Shin. Text-independent and Characterdependent
Online Writer Verification: Using Personal Features of Character
in the Context of String. In Proceedings of The 1st International Workshop on
Aware Computing (IWAC09), pages 650–653, Aizu-Wakamatsu. Japan, Sep.
2009. Japan Society and Fuzzy Theory and Intelligent Informatics, Japan
Society and Fuzzy Theory and Intelligent Informatics. |
| This paper proposes a text-independent writer verification scheme by using character
level features. Four character features are introduced in the context of handwritten
string, which mainly represent a character’s relative position in its string. The scheme
is implemented by comparing character shapes and relative features of characters in
the context of string styles. The system reported 53.11filtering effect with the features
alone and dropped error rates to 1.01.7function. |
|
| [jpshin-13:2009] |
Kohei Fujiwara, Masahiro Honma, and Jungpil Shin. Segmentation and
recognition in Japanese handwritten Waseda shorthand. In Japan Society,
Fuzzy Theory, and Intelligent Informatics, editors, Proceedings of The 19th
Intelligent System Symposium (FAN09) (Best Presentation Awarded), pages
195–200, Aizu-Wakamatsu. Japan, Sep. 2009. Japan Society and Fuzzy Theory
and Intelligent Informatics, Japan Society and Fuzzy Theory and Intelligent
Informatics. |
| Shorthand is written at the speed of speech, so it has been used for meetings and
discussions to record content of them. However there is a problem of taking a long
time to read handwritten shorthand and to convert it into regular text. Although
some solutions based on computer technologies have been introduced for English and
Chinese in literatures, in this paper, an unique solution suitable for Japanese shorthand
is proposed. We basically adopt one of the previous systems, but the rules are
newly introduced for covering fundamental Japanese shorthand letters and increasing
accuracy of segmentation stage. The Yuritugi detection method is introduced in
this paper as an unique method using Freeman chain code. The accuracy of Yuritugi
detection is 95.83%. This proves our theory is suitable for Japanese Yuritugi rule. Besides,
for type classification and symbol recognition, previous system reported 93.52%
and 81.98%, respectively, showing that the solution for Chinese shorthand is also very
useful to Japanese shorthand. |
|
| [jpshin-14:2009] |
Won-Du Chang and Jungpil Shin. DPW Approach for Random Forgery
Problem in Online Handwritten Signature Verification. In J. Kim, editor,
Proceedings of 4th International Conference on Networked Computing
and Advanced Information Management, pages 347–352. Sogang University,
IEEE, Sep. 2008. |
| In this paper, we refer a phenomenon of relatively high error rates against random
forgeries in online signature verification. Though human can easily distinguish
random forgeries from genuine signatures, the most published research results during
last decades have reported high error rates against them, compared to the
error rates against skilled forgeries. This paper suggests taking DPW (dynamic
positional warping) approach for the problem, which supplies high accuracy and
robustness against affine transform of online shapes. In addition, the effects of distance
normalization and slope constraints are tested to DPW and conventional
DTW (dynamic time warping). Our approach was compared to conventional DTW
method with consequential xy difference information with SVC2004 task1 database:
0.17against random and skilled forgeries, respectively. Comparing to the best result
of the conventional approach, the proposed approach reduced the error rates into
about 27costs. |
|
| [jpshin-02:2008 |
Won-Du Chang and Jungpil Shin. A Stochastic Stroke Model for Variable
and Personalized Handwriting Synthesis. In Proceedings of Fourth International
Conference on Intelligent Computing and Information Systems,
pages 705–711, New York, Mar. 2009. ACM. |
| This paper proposes a stochastic stroke model which synthesizes variable handwritten
characters preserving one’s writing style. Our fundamental concept of the
stochastic model is thinking a stroke as consecutive state changes of segments. After
clustering segments into several states, a number of characters are presented as a
directed graph with probabilities of state changes. To support the model, two modifications
of dynamic time warping techniques are presented: one is allowing division
to ensure one-to-one matching between segments, not loosing detailed shape information;
the other is a method of generating a template to align segments among
many signals. By employing stochastic method at segment levels, our model enables
generating various and natural handwritten characters with small number of training
data. We synthesized 3,600 English alphabets and numbers from 180 training
characters showing the variance of synthesized characters, and their DP distance
proved that the synthesized characters keep one’s writing style well. |
|
Chapters in Book
| [demura-09:2008] |
J. Watanabe, H. Demura, N. Hirata, and J. Terazono. SAISHIN
TSUKI NO KAGAKU - NOKOSARETA NAZO WO TOKU - (The
newest Lunar Science -To solve remained problems- in Japanese), page 219
pages. NHK Books, 6 2008. Demura’s parts: Forewords, Chapts. 2, 3, 4, 5, and Afterwords. 1–11, 55-152, 213– 219 |
Grants
| [naru-11:2008] |
T. Mukai, A. Nakamura, Y. Okada, and N. Hirata. Grant-in-Aid for
Scientific Research 18340133, 2006-2008. |
| [naru-12:2008] |
N. Hirata. Grant-in-Aid for Scientific Research 19549003, 2007-2008. |
Academic Activities
| [jpshin-03:2008] |
Jungpil Shin, June 2008. Member of the Program Committee, The 2008 International Conference on Knowledge Generation, Communication and Management (KGCM 2008) |
| [jpshin-04:2008] |
Jungpil Shin, Jan. 2008. Conference Co-Chair, The 2008 International Conference on Ubiquitous City Technology (ICUCT 2008) |
| [jpshin-05:2008] |
Jungpil Shin, Sep. 2008. Member of the Program Committee, The 2008 International Conference on Knowledge- Based and Intelligent Information & Engineering Systems (KES2008) |
| [jpshin-06:2008] |
Jungpil Shin, Sep. 2008. Member of the Program Committee, The Tenth International Conference on Ubiquitous Computing |
| [naru-13:2008] |
N. Hirata, 2008. Member, and member of the committee for general affairs, The Japanese Society for Planetary Sciences |
Ph.D, Master and Bachelor Theses
| [asada-19:2008] |
Manabu Kanzawa. Master Thesis: Online Geographic Information System
Supporting CollaborativeWork for Multipli Users, University of Aizu, 2008. Thesis Advisor: N. Asada, Co-referee: T. Hayashi and K. Naruse |
| [asada-20:2008] |
Naoto Miura. Master Thesis: Automatic Tracking of Glass Fragments
in High-Speed Camera Movies, University of Aizu, 2008. Thesis Advisor: N. Asada, Co-referee; R. Oka and T. Hayashi |
| [asada-21:2008] |
Shota Kikuchi. Master Thesis: Development of Operation Plan and Log
Management System for LISM on KAGUYA, University of Aizu, 2008. Thesis Advisor: N. Asada, Co-referee; S. Bhalla and K. Naruse |
| [asada-22:2008] |
Tomoki Hodokuma. Master Thesis: Integration of Lunar Digital Terrain
Model and Topographic Profile Data from Kaguya, University of Aizu, 2008. Thesis Advisor: N. Asada, Co-referee; R. Oka and N. Hirata |
| [jpshin-07:2008] |
Michikazu Kikugawa. Graduation Thesis: Shape retrieval with dendrogram,
one of the clustering method, University of Aizu, 2008. Thesis Advisor: Jungpil Shin |
| [jpshin-08:2008] |
Hiroshi Naito. Graduation Thesis:Detecting Alcohol using difference
character of on-line signature, University of Aizu, 2008. Thesis Advisor: Jungpil Shin |
| [jpshin-09:2008] |
Junichi Sato. Graduation Thesis: Font Generation which use Automatic
HANE Generation, University of Aizu, 2008. Thesis Advisor: Jungpil Shin |
| [jpshin-10:2008] |
Masahiro Honma. Graduation Thesis: On-line Recognition of Handwritten
Waseda Shorthand for Faster Recording of Japanese Text, University
of Aizu, 2008. Thesis Advisor: Jungpil Shin |
| [jpshin-11:2008] |
Yukari Sato. Graduation Thesis: Random Fonts Simulation, University
of Aizu, 2008. Thesis Advisor: Jungpil Shin |
| [jpshin-12:2008] |
Tomomi Kikuchi. Graduation Thesis: On-Line Signature Evaluation
Using Fuzzy Set Theory, University of Aizu, 2008. Thesis Advisor: Jungpil Shin |
