|
|
|
|
|
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), 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. We are also contributing in the next Asteroid exploration project, Hayabusa2, where a lab member is leading it as a principal investigator (PI).
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.
H. Demura. Shape Modeling of Asteroids Based on Camera Images. Journal of the Japanese Society for Artificial Intelligence, 26(2):184-187, 2010. in Japanese
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). Icarus, 207:714-731, 2010.
The Hayabusa Spacecraft Asteroid Multi-band 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, read-out 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 um) 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 (flat-field) 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 +/- 0.03 mm, yielding a field-of-view (FOV) of 5.83x5.69 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.
T. Morota, J. Haruyama, M. Ohtake, T. Matsunaga, C. Honda, Y. Yokota, J. Kimura, Y. Ogawa, N. Hirata, H. Demura, A. Iwasaki, T. Sugihara, K. Saiki, R. Nakamura, S. Kobayashi, Y. Ishihara, H. Takeda, and H. Hiesingert. Timing and characteristics of the latest mare eruption on the Moon. Earth and Planetry Science Letters, 302:255-266, 2011.
Unraveling the timing and duration of mare volcanism on the Moon is essential for understanding its thermal evolution. The end of mare volcanism is poorly constrained, because mare basalts are incompletely sampled. In this study, employing SELENE (Kaguya) high-resolution images, we performed new crater size-frequency measurements for 49 young mare units (<−3.0 Ga) in the Procellarum KREEP Terrane (PKT), in which the latest magma eruption of the Moon occurred. Mare volcanism in this region continued until − 1.5 Ga, suggesting that volcanic activity in this region ceased − 1.0 Ga after the magma eruption had globally ceased 2.5−3.0 Ga. Volcanic activity may have peaked 1.8−2.2 Ga ago. The youngest basalts occur around the Aristarchus plateau and the Kepler crater, which are located in the central region of the PKT. It is likely that heating in the crust due to the concentration of heat-producing elements in the PKT delayed cooling of a partial-melting zone in the underlying mantle. In contrast with previous basalt dating in this region, our results indicate a higher correlation between ages and spectral types of mare basalts; the young mare units in the PKT tend to have spectral types corresponding to high titanium contents, while low titanium basalts occur mainly in the early stage. The titanium variation in mare basalts may reflect vertical heterogeneity in TiO2 content in the upper mantle beneath the PKT.
S. Kodama, M. Ohtake, Y. Yokota, A. Iwasaki, J. Haruyama, T. Matsunaga, R. Nakamura, H. Demura, N. Hirata, T. Sugihara, and Y. Yamamoto. Characterization of Multiband Imager Aboard SELENE. Pre-flight and In-flight Radiometric Calibration. Space Science Reviews, 154:79-102, 2010.
The Multiband Imager (MI) is a high-resolution, multi-spectral imaging instrument for lunar exploration. It consists of two cameras, VIS and NIR, and is carried on the SELenological and ENgineering Explorer (SELENE), launched on Sep. 14, 2007. During the observation from January 2008 to June 2009, MI acquired about 450,000 scenes of multispectral image. The radiometric properties of the cameras were characterized using the pre-flight data derived in laboratory experiments with a calibrated integrating sphere. Twelve light source sets were used to examine the S/N ratio, linearity, and saturation level of the cameras. The dark field signal is quite stable in both cameras, having a noise level of less than 1 DN (VIS) and 2 DN (NIR). The fluctuation in the light field is also low (<2 DN), indicating that the spatial nonuniformity in the camera responses can be removed using a flat field. In order to remove the smear signals due to the frame transfer in the VIS data, we developed an iterate algorithm using all bands in the VIS camera. The S/N ratio, which is critical to the precision of the product, is estimated to exceed 160 for the VIS bands and 400 for the NIR bands under low illumination conditions (5% of lunar surface reflectance). Based on the S/N ratio, the radiometric error due to the noise is calculated to be less than 0.7% for VIS and 0.2% for NIR. The relationship between input and output of the VIS camera is linear with a residual of less than 0.6 DN, corresponding to a radiometric error of 0.3%. The NIR exhibits a non-linear response to the input radiance. A cubic function best fits the pre-flight data with an average residual of 8 DN (corresponds to an error of 0.8%). Validation using in-flight data indicated that the instability of the dark output has not changed, but the level of dark output has slightly changed in the NIR bands (less than 6 DN). The pixel-to-pixel sensitivity variation in the orbit has been changed from that in the pre-flight experiment. The difference between the in-flight data and the pre-flight data ranges within +/− 2%. There is also a small (less than +/− 1%) but nonnegligible difference between in-flight data of different cycles in both the VIS and NIR bands, suggesting that the coefficient for spatial ununiformity correction needs to be calculated for each cycle.
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 solidliquid 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.
N. Asada, N. Hirata, H. Demura, N. Harada, Y. Shibata, S. Kikuchi, T. Hodokuma, J. Haruyama, M. Ohtake, Y. Yokota, T. Morota, C. Honda, T. Matsunaga, Y. Ogawa, M. Torii, T. Nimura, H. Araki, and S. Tazawa. Computational Geology for Lunar Data Analysis from LISM on KAGUYA. Advances in Geosciences, Volume 19: Planetary Science (SE), 19:77, 2010.
Not Available
S. Yamamoto, R. Nakamura, T. Matsunaga, Y. Ogawa, Y. Ishihara, T. Morota, N. Hirata, M. Ohtake, T. Hiroi, Y. Yokota, and J. Haruyama. Possible mantle origin of olivine around lunar impact basins detected by SELENE. Nature Geoscience, 3:533-536, 2010.
The composition, structure and evolution of the Moon's mantle is poorly constrained. The mineral olivine, one of the main constituents of Earth's mantle, has been identified by Earth-based telescopic observations at two craters on the near side of the Moon, Aristarchus and Copernicus. Global reflectance spectra in five discrete spectral bands produced by the spacecraft Clementine suggested several possible olivine-bearing sites, but one of the candidate occurrences of olivine was later re-classified, on the basis of continuous reflectance spectra over the entire 1um band, as a mixture of plagioclase and pyroxene. Here we present a global survey of the lunar surface using the Spectral Profiler onboard the lunar explorer SELENE/Kaguya. We found many exposures of olivine on the Moon, located in concentric regions around the South Pole-Aitken, Imbrium and Moscoviense impact basins where the crust is relatively thin. We propose that these exposures of olivine can be attributed either to an excavation of the lunar mantle at the time of the impacts that formed the basins, or to magnesium-rich pluton in the Moon's lower crust. On the basis of radiative transfer modelling, we suggest that at least some of the olivine detected near impact basins originates from upper mantle of the Moon.
Yu Tang and Jungpil Shin. De-ghosting for Image Stitching with Automatic. In Aytul Ercil, editor, IEEE 20th International Conference on Pattern Recognition (ICPR2010), pages 2210-2213, Istanbul, Turkey, August 2010. IEEE, IEEE.
Ghosting artifact in the field of image stitching is a common problem and the elimination of it is not an easy task. In this paper, we propose an intuitive technique according to a stitching line based on a novel energy map which is essentially a combination of gradient map which indicates the presence of structures and prominence map which determines the attractiveness of a region. We consider a region is of significance only if it is both structural and attractive. Using this improved energy map, the stitching line can easily skirt around the moving objects or salient parts based on the philosophy that human eyes mostly notice only the salient features of an image. We compare results of our method to those of 4 state-of-the-art image stitching methods and it turns out that our method outperforms the 4 methods in removing ghosting artifacts.
Yasuhiro Koyama and Jungpil Shin. On-line signature verification using subband decomposition by discrete wavelet transform. In The 3rd International Conference on the Frontiers of Information Technology, Application and Tools (FITAT2010), pages 95-104, Yanji, China, June 2010. KIPS, KIPS.
A on-line signature verification method is proposed for producing a subband decomposed signal from signature data. The method uses signal which subband decomposed a time change of five types of pen-tablet data (i.e., x-coordinate, y-coordinate, pressure, direction, altitude) by DiscreteWavelet Transform (DWT). The high frequency subband decomposed signal is used here since individual features stand out, and the differences etween the registered authentic signature and the forged signature become clear. Adaptive signal processing is used as a verification algorithm. It is repeated in order to reduce the error margin between the registered signature and the input signature. If the input signature is similar to the registered signature, the convergence coefficient value approaches one. Otherwise, it is a number other than one. Verification is carried out by using this procedure. The change of the verification rate between past verification method uses x-coordinate and y-coordinate and present research uses five types of data listed above was measured. In the comparison experiment, the verification rate improved from 89.2% to 96.4%.
Hyeongsoo Kim, Li Xun, Jungpil Shin, and Keun Ho Ryu. A Selective Level of Detail Technique for Feature-based Digital Map. In The 3rd International Conference on the Frontiers of Information Technology, Application and Tools (FITAT2010), pages 105-109, Yanji, China, June 2010. KIPS, KIPS.
Recently, due to the use of 3D spatial data in various fields, interestingness of 3D spatial data model has increased. Nevertheless, existing digital maps can not efficiently manage data, and it's hard to offer users various and detailed spatial information. Hence, in order to solve the problems of existing digital map, we proposed selective LOD (Level of Detail) model which can be applied to feature-based digital map. We designed LOD model for cubic effect and detailed representation of 3D feature using the LOD concept that the shape of feature is changed by viewpoint. In this paper, we confirmed that LOD model applying presented model can offer more detailed spatial information to use. Especially, presented LOD model has efficiency because it considers data transmission aspect as well as visualization aspect. Thus, the presented model is possible to support more detailed spatial information and efficient management by feature unit.
Kazuomi Oota and Jungpil Shin. Adding variability to improve generation of handwriting-style fonts. In The 3rd International Conference on the Frontiers of Information Technology, Application and Tools (FITAT2010), pages 86-94, Yanji, China, June 2010. KIPS, KIPS.
In this research, a handwriting-style font generation method considering stroke changes of own character is proposed. Then a variability is added to generated characters by incorporating it into a handwriting-style font generation system reflecting indivisuality with local and global features. As a preparation before generation, similar strokes are grouped with vector quantization, and the proposed method is applied to each group. The strokes created from there are combined, and fonts are generated. The next three main stages are carried out in this method to generate new strokes; (1) Feature extraction on every stroke is performed until it reaches an arbitrary threshold in decreasing order of amount of change. (2) Splitting is performed in order to get the feature point number of all strokes in the same group to be matched, at that time, the correspondence is taken between two strokes and the position of feature points is made similar. (3) Variation is added to generated strokes by expressing change of a stroke by addition of selection probability and random selection within the limits. These steps are added in a generation process, and evaluation experiments for generated characters are performed by 14 subjects. The rate which the generated character from own inputs is chosen in a top-fives was 80% at subjective evaluation experiment, and the rate which the character is included in a top-three was 86% at objective evaluation experiment. From these two results, the reflection of individuality to the generated characters which the variation was added was accepted.
Jungpil Shin, Dai Hanata, and Suyun Ju. A Selective Level of Detail Technique for Feature-based Digital Map. In The 2nd International Symposium on Aware Computing (ISAC 2010), pages 80-85, Tainan, Taiwan, June 2010. IEEE Signal Processing Society, IEEE.
This paper present a map search system using Shape context and Bipartite graph matching. Shape context is using for measuring shape similarity and the recovering of point correspondences. After generated from the shape context, Bipartite Graph Matching leads the optimal correspondence between two shapes. For raising the recognition rate, Hierarchical description is used. Shape context is the method that treats shapes as a set of points and makes the histogram of the distribution of points. In Hierarchical description, Wavelet analysis is used. To reduce the amount of calculation, Piecewise linear approximation is implemented as the feature extraction method. The system shows six similar shapes to hand-written input shapes from reference shapes that are Japan's 47 prefectures. Comparison result of Linear matching, DP matching and Shape context with Bipartite graph matching describes that the 1st place recognition rates of each algorithms are 82.00%, 84.52% and 92.45%, which describes the robustness of Shape context. Experiment of several level of hierarchical description describes that hierarchical approximation can raise the recognition rate from 92.45 to 94.97% using the deepest-4 depth, which means that the hierarchical approximation is effective to remove the noise from the handwritten inputs.
Junichi Sato and Jungpil Shin. Font generation with automatic HANE addition. In The 3rd International Conference on the Frontiers of Information Technology, Application and Tools (FITAT2010), pages 6-12, Yanji, China, June 2010. KIPS, KIPS.
Using characteristic font which reflects user's individuality at handwriting on word processor and so on is one of demand of users because typical fonts are simple and it will be lack in fun a little. However, huge amount of characters are used in Japanese document and the cost for user to write each characters will be enormous. This paper describes about the method to create hand-written style font which reflects user's individuality with low cost of user, using automatic "hane" (flick stroke) generation. To solve this problem following step will go through. First, make the databases which were generated by the stroke data which lacked hane. Second, extract information of hane from the user's input. Finally, add hane to the generated font's stroke which might maintains hane. At the result, automatic hane generation was success. In addition, the number of compressed character stroke data was been few than the data which was generated with original stroke data when the data was generated with hane deleted stroke data.
Mamiko Tano and Jungpil Shin. Extraction of Multiple Moving Object Using Snakes. In The 3rd International Conference on the Frontiers of Information Technology, Application and Tools (FITAT2010), pages 16-23, Yanji, China, June 2010. KIPS, KIPS.
In this paper, we present multiple moving objects extraction sysytem using Snakes. The processing of the extraction of the movement object is divided into two stages. First, the area of the movement object is extracted by using the background difference for the preprocessing. Second, The split and merge Snakes is used for the extraction that uses Snakes. When the object is extracted with Snakes in the previous frame, the same object can be extracted by expanding and reducing the same Snakes. In addition, an outline model by whom an initial outline is set to the frame of the image is reduced and new object is extracted. As a result, two or more movement objects were able to be extracted. Even if the image contains small noise and the edge of the moving object is not able to be detected, a smooth profile line of the object is able to be extracted by Snakes
Takashi Onose, Keun-Soo Yun, and Jungpil Shin. Feature analysis of characters for signature evaluation. In The 3rd International Conference on the Frontiers of Information Technology, Application and Tools (FITAT2010), pages 43-52, Yanji, China, June 2010. KIPS, KIPS.
The purpose of this thesis is feature analysis of Chinese characters for signature evaluation. Signature evaluation is to examine the quality of the signature to improve the accuracy of personal authentication that uses handwritten signatures. Although a hand-written character is different in each person, the difference vary by the character. The differences of individual writing can be calculated by a one-way analysis of variance. The Chinese characters where individuality appears frequently can be investigated by examining the relation between them. As a result of the verification, Chinese characters with large number of strokes, strokes with bending and breaking, strokes with horizontal line and strokes which are short or long make individuality appear. And, F-value which shows the appearance of individuality was obtained for all Chinese characters and strokes. The signature is expected to be evaluated by using these information.
Yuki Nakai and Jungpil Shin. A real-time robust head tracking system by using hierarchical division. In The 3rd International Conference on the Frontiers of Information Technology, Application and Tools (FITAT2010), pages 69-77, Yanji, China, June 2010. KIPS, KIPS.
In this paper, a real-time head tracking system corresponding to a diagonal viewpoints by using frame differences is presented. Hierarchical division and a circle detection method are proposed for the development of this system. The hierarchical division is a technique for extracting each moving object from a frame image. Our proposed circle detection method is a technique based on presumption of the center position of a circle. Experiments demonstrate the real-time performance and robustness of our system working in complex scenes. This system corresponds to diagonal viewpoints from 0 to about 60 degrees by using the hierarchical division and the circle detection suffices for practical use.
Kouhei Miura and Jungpil Shin. Personal identification using free text. In The 3rd International Conference on the Frontiers of Information Technology, Application and Tools (FITAT2010), pages 78-85, Yanji, China, June 2010. KIPS, KIPS.
This paper propose a personal identification using free text. In the field of personal identification based on handwriting, almost research has been focused on signature verification. However, signature verification has a serious problem that is possibility of a forged signature appearance. To solve this problem, a writer identification method which uses free text was introduced. In the previous ethod, any handwriting characters are accepted as a text in the identification process, and the text used in the identification process can be different from that in the enrollment process. The proposal method uses pen pressure and inclination for the previous method, and improves.
Michikazu Kikugawa, Won-Du Chang, Soonwook Hwang, and Jungpil Shin. A Fast Shape Retrieval using Dendrogram. In The IEEE International Joint Conference on Neural Network (IJCNN2010), pages 124-128, Barcelona, Spain, July 2010. IEEE Signal Processing Society, IEEE.
A lot of image data has been digitized and preserved in computers. In order to search for an image, an efficient and accurate retrieval method is needed. This paper is concerned with shape retrieval which is one of the searching methods for finding similar images in a database. Shape, the outer form of a picture, is considered the most promising feature to identify entities in an image. The problem of shape retrieval takes a lot of time because an exhaustive search is mainly used in literatures. This paper suggests the use of a clustering method known as dendrogram for shape retrieval. In addition, we proposed the automatic decision of a threshold to determine a number of clusters in dendrogram. Through the experimental result, the proposed method proved fast retrieval preserving almost the same level accuracy.
Hyeongsoo Kim, Jungpil Shin, and Keun Ho Ryu. Object Categorization using Image Mining. In Jungpil Shin, editor, 2011 Korea-Japan International Joint Workshop on Digital MAP, Health, and Information Technology, Aizu-Wakamatsu, Jan 2011. Korean Association of Surveying and Mapping, Korean Association of Surveying and Mapping.
Dong Gyu Lee, Jungpil Shin, and Keun Ho Ryu. A Data mining S/W prototype for servicing efficiently U-GIS Contents. In Jungpil Shin, editor, 2011 Korea-Japan International Joint Workshop on Digital MAP, Health, and Information Technology, Aizu-Wakamatsu, Jan 2011. Korean Association of Surveying and Mapping, Korean Association of Surveying and Mapping.
H. Demura, Y. Ogawa, and Y. Takahashi. Competitive Research Fund for Development of Scientific Instruments FY2010, Environment Test for Liquid Crystal Tunable Filter, 2010.
Jungpil Shin. Laser based Intelligent Input Device for Interactive Screen, June 2010.
Co-project with Seoul University in Korea and the Univ. of AIZU
Jungpil Shin, June 2010.
Key Note Speaker and Member of the Program Committee, The 3rd International Conference FITAT 2010 In Conjunction with YUST 2010 International Symposium. (FITAT 2010) (held in Yanbian University of Science & Technology, Yanji, China, 28 June - 2 July, 2010.)
Jungpil Shin, Jan 2011.
Program Committee Chair, The 2011 Korea-Japan International Joint Workshop on Information Technology (held in The University of Aizu, Fukushima, Japan, January 9-12, 2011)
Jungpil Shin, Dec 2010.
Member of the Program Committee, The 5th International Conference on Ubiquitous Information TEchnologies & Applications (CUTE 2010), (held in Sanya, China, Dec. 16-18, 2010.)
Jungpil Shin, Dec 2010.
Member of the Program Committee at The 2010 International Conference on Machine Learning and Applications (ICMLA'10)
Jungpil Shin, May 2010.
Member of the Program Committee, The 6th International Conference on Networked Computing (INC2010) (held in Gyeongju, Korea, May 11-13, 2010.)
Jungpil Shin, Aug 2010.
Member of the Program Committee, The 6th International Conference on Digital Content, Multimedia Technology and its Applications (IDC2010), (held in Seoul, Korea, Aug 16-18, 2010.)
Jungpil Shin, Aug 2010.
Member of the Program Committee, The 6th International Conference on Networked Computing and Advanced Information Management (NCM2010), (held in Seoul, Korea, Aug 16-18, 2010.)
Jungpil Shin, Aug 2010.
Member of the Program Committee, The 2th International Symposium on Aware Computing (ISAC2010), (held in National Cheng Kung University (NCKU), Taiwan, Nov.1-4, 2010)
N. Hirata, 2010.
Member of Local Organizing Committee, Asteroid, Comet, Meteor meeting 2011
N. Hirata, 2010.
Member of Program Subcommittee, The 28th International Symposium on Space Technology and Science
N. Hirata, 2010.
Member, and member of the committee for general affairs, The Japanese Society for Planetary Sciences
Takeshi Moue. Graduation Thesis: Kanji character recognition using Wii remote controller, School of Computer Science and Engineering, March 2011.
Thesis Adviser: Jungpil Shin
Hiroaki Kai. Graduation Thesis: Detection of objects from video images using background subtraction, School of Computer Science and Engineering, March 2011.
Thesis Adviser: Jungpil Shin
Junichi Sato. Master Thesis: Signature Verification for Multiuser Online Kanji Learning System, Graduate School of Computer Science and Engineering, March 2011.
Thesis Adviser: Jungpil Shin
Hirofumi Shimoyama. Graduation Thesis:Grading Handwritten Characters with Font Image in Kanji Learning System, School of Computer Science and Engineering, March 2011.
Thesis Adviser: Jungpil Shin
Megumi Kohga. Graduation Thesis: Sensory Calligraphy Learning System with Evaluation of Character Shape, School of Computer Science and Engineering, March 2011.
Thesis Adviser: Jungpil Shin