Kameyama Keisuke

J-GLOBAL         Last updated: Dec 5, 2019 at 02:42
 
Avatar
Name
Kameyama Keisuke
E-mail
Keisuke.Kameyamacs.tsukuba.ac.jp
Affiliation
University of Tsukuba
Section
Faculty of Engineering, Information and Systems
Job title
Professor
Degree
PhD(Engineering)(Tokyo Institute of Technology)

Research Areas

 
 

Education

 
 
 - 
1989
Department of Electric and Electronic Engineering, Faculty of Engineering, Tokyo Institute of Technology
 
 
 - 
Mar 1991
Precision Machinery Systems, Graduate School, Division of Integrated Science and Engineering, Tokyo Institute of Technology
 

Committee Memberships

 
Apr 2018
 - 
Sep 2018
International Conference on Neural Information Processing (ICONIP 2018)  Program Commitee Member
 
Apr 2017
 - 
Sep 2017
International Conference on Neural Information Processing (ICONIP 2017)  Program Commitee Member
 

Published Papers

 
Parallel Cooperative Ensemble Learning by Adaptive Data Weighting and Error-Correcting Output Codes
Shota, Utsumi;Keisuke, Kameyama
Lecture Notes in Computer Science (Proc. ICONIP 2018)   11303 673-683   Dec 2018   [Refereed]
Revising the Algorithm of Ensenble Learning by an Index of Complementarity among Weak Learners
内海, 翔太;亀山, 啓輔
Technical Report of IEICE   118(284, IBISML2018-102) 429-434   Nov 2018
Parameter Density Inheritance Using Kernel Density Estimation for Efficient CNN Learning
堀内, 圭佑;亀山, 啓輔
Technical Report of IEICE   118(284, IBISML2018-45) 9-15   Nov 2018
Interpretable active sampling
田口, 優介;亀山, 啓輔;日野, 英逸
Technical Report of IEICE   118(220, IBISML2018-27) 97-104   Sep 2018
Arrangement of Complementary Weak Learners using Weights Assigned to Data in Parallel Ensemble Learning
内海, 翔太;亀山, 啓輔
Technical Report of IEICE   118(220) 9-15   Sep 2018
Parameter Density Inheritance Using Kernel Density Estimation for Efficient CNN Learning
Horiuchi, Keisuke;Kameyama, Keisuke
Proceedings of 2018 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT)   308-313   Dec 2018   [Refereed]
Chatbri, Houssem;McGuinness, Kevin;Little, Suzanne;Zhou, Jiang;Kameyama, Keisuke;Kwan, Paul;O’Connor, Noel
ACM Multimedia 2017 - MultiEdTech Workshop   21-26   Oct 2017   [Refereed]
Lapped cuboid-based perceptual encryption for Motion JPEG standard
Shimizu, Kosuke;Suzuki, Taizo;Kameyama, Keisuke
Proc. of APSIPA ASC 2018   2022-2026   Nov 2018   [Refereed]
Shimizu, Kosuke;Suzuki, Taizo;Kameyama, Keisuke
IEICE Transactions on Fundamentals of Electronics, Communictions and Computer Sciences   E101-A(11) 1815-1822   Nov 2018   [Refereed]
<p>We propose the cube-based perceptual encryption (C-PE), which consists of cube scrambling, cube rotation, cube negative/positive transformation, and cube color component shuffling, and describe its application to the encryption-then-compression...
Log analysis for hijacked user account's login detection method based on an autonomous system number of access source
Sato, Akira;Sannomiya, Shuji;Oyama, Yoshihiro;Yoshida, Kenichi;Kameyama, Keisuke
信学技報IA   117(299) 95-98   Nov 2017
誤り訂正符号を用いた並列調整に基づくAdaBoostによる分類性能の安定性
内海, 翔太;亀山啓輔
信学技報PRMU   117(238) 205-210   Oct 2017
多クラス分類問題における誤り訂正符号を用いた並列調整に基づくAdaBoostによる分類性能の安定化
内海, 翔太;亀山啓輔
信学技報IBISML   117(211) 43-50   Sep 2017
Chatbri, Houssem;Kameyama, Keisuke;Kwan, Paul;Little, Suzanne;O’Connor, Noel
Multimedia Tools and Applications   77(21) 28925-28948   May 2018   [Refereed]
We introduce a shape descriptor that extracts keypoints from binary images and automatically detects the salient ones among them. The proposed descriptor operates as follows: First, the contours of the image are detected and an image transformatio...
Keypoint Detection based on Learning to Rank for Robust Image Matching under Resolution Variation
Yoshikawa, Satoshi;Kameyama, Keisuke
Proceedings of International Workshop on Advanced Image Technology 2017 (IWAIT 2017)   (Paper No. 153)    Jan 2017   [Refereed]
Iris Authentication using Local Spectral Features and their Relational Operations
Aizawa, Miharu;Kameyama, Keisuke
Proceedings of International Workshop on Advanced Image Technology 2017 (IWAIT 2017)   (Paper No. 138)    Jan 2017   [Refereed]
局所高次スペクトル特徴量の関係演算による虹彩コード生成
相澤美晴;亀山啓輔
第6回バイオメトリクスと認識・認証シンポジウム(SBRA2016)抄録集   (S4-21)    Nov 2016
解像度変化に頑健な画像マッチングのためのランキング学習に基づいた特徴点検出法
吉川慧;亀山啓輔
信学技報IE   116(335) 45-50   Nov 2016
局所スペクトル特徴量とその関係演算を用いた虹彩認証
相澤美晴;亀山啓輔
信学技報BioX   116(265) 83-88   Oct 2016
層状ニューラルネットワーク2クラス分類器の組み合わせによる多クラス分類器に関する考察
内海翔太;亀山啓輔
信学技報NC   116(265) 7-12   Oct 2016
A Comparative Study Using Contours and Skeletons as Shape Representations for Binary Image Matching
Kameyama Keisuke
Pattern Recognition Letters   76(1) 59-66   Jun 2015   [Refereed]
Shape Matching using Keypoints Extracted From Both the Foreground and the Background of Binary Images
Houssem,Chatbri;Kenny,Davila;Keisuke,Kameyama;Richard,Zanibbi
IEEE International Conference on Image Processing Theory, Tools and Applications (IPTA15)   205-210   Nov 2015   [Refereed]
We introduce a descriptor for shape feature extraction and matching using keypoints that are extracted from both the foreground and the background of binary images. First, distance transform (DT) is applied on the image after contour detection. Th...
Noise-robust Iris Authentication using Local Higher-Order Moment Kernels
Keisuke,Kameyama;Trung,Nguyen Bao Phan;Miharu,Aizawa
Lecture Notes in Computer Science (Proc. ICONIP 2015)   9492 419-427   Nov 2015   [Refereed]
Towards a Segmentation and Recognition-Free Approach for Content-Based Document Image Retrieval of Handwritten Queries
Keisuke,Kameyama;Houssem,Chatbri;Paul,Kwan
Asian Conference on Pattern Recognition (ACPR15 Kuala Lumpur)   146-150   Nov 2015   [Refereed]
Estimation of Secondary Cell Performances by Analysis of Electrode Images
黒木,涼;亀山,啓輔
Technical Report of IEICE (IE)   115(459) 23-28   Feb 2016
Higher-Order Moment Orders and Performance in Texture Classification using Support Vector Machines
ファン,チュン グエン バオ;亀山,啓輔
Technical report of IEICE. PRMU   112(357) 31-36   Dec 2012
Comparison of Hue Feature and Illumination Invariant Color Feature H' in Partial Image Retrieval
松本,亘;亀山,啓輔
IEICE technical report. Image engineering   112(335) 41-46   Dec 2012
A Modular Approach for Query Spotting in Document Images and Its Optimization Using Genetic Algorithms
Chatbri, Houssem; Kwan, Paul; Kameyama, Keisuke
2014 IEEE CONGRESS ON EVOLUTIONARY COMPUTATION (CEC)   2085-2092   2014   [Refereed]
Higher-Order Moment Orders and Performance in Texture Classification using Support Vector Machines
PHAN,Trung Nguyen Bao;Kameyama,Keisuke
Technical report of IEICE. PRMU   112(357) 31-36   Dec 2012
Conventionally, local moment functions (local autocorrelation functions) of orders up to 3 have been widely used as features for image texture classification. This is mainly due to the high dimensionality of higher order moment function feature sp...
Document Image Dataset Indexing and Compression Using Connected Components Clustering
Houssem,Chatbri;Keisuke,Kameyama
Proceedings of IAPR International Conference on Machine Vision and Applications (MVA 2015)   267-270   May 2015   [Refereed]
We present a method for document image dataset indexing and compression by clustering of connected components. Our method extracts connected components from each dataset image and performs component clustering to make a hash table that is a compre...
Houssem,Chatbri;Keisuke,Kameyama;Paul,Kwan
Pattern Recognition Letters   76 59-66   Jun 2016   [Refereed]
Contours and skeletons are well-known shape representations that embody visual information by using a limited set of object points. Both representations have been applied in various pattern recognition applications, while studies in cognitive scie...
Chatbri,Houssem;Kwan,Paul;Kameyama,Keisuke
Proceedings of International Conference on Pattern Recognition (ICPR 2014)   2891-2896   Jul 2014   [Refereed]
We report our ongoing research on an application-independent and segmentation-free approach for spotting queries in document images. Built on our earlier work reported in [1][2], this paper introduces an image processing approach that finds occurr...
Houssem,Chatbri;Keisuke,Kameyama
Pattern Recognition Letters   42(1) 1-10   Jun 2014   [Refereed]
We apply scale space filtering to thinning of binary sketch images by introducing a framework for making thinning algorithms robust against noise. Our framework derives multiple representations of an input image within multiple scales of filtering...
Image Feature Extraction and Similarity Evaluation using Kernels for Higher-Order Local Autocorrelation
Kameyama,Keisuke;Phan,Trung Nguyen Bao
Lecture Notes in Computer Science (Proc. ICONIP 2013)   8228 442-449   Nov 2013   [Refereed]
The Higher-Order Moment (HOM) kernel is known to enable
efficient utilization of higher-order autocorrelation (HOA) features
in signals and images. Several authors report that kernel-based classification
methods employing this kernel can classify ...
Sketch-Based Image Retrieval by Size-Adaptive and Noise-Robust Feature Description
Chatbri,Houssem;Kameyama,Keisuke;Kwan,Paul
Proceedings of International Conference on Digital Image Computing: Techniques and Applications (DICTA)   469-476   Nov 2013   [Refereed]
We review available methods for Sketch-Based
Image Retrieval (SBIR) and we discuss their limitations. Then, we
present two SBIR algorithms: The first algorithm extracts shape
features by using support regions calculated for each sketch point,
and ...
Joint Use of Luminance and Color Invariants In Partial Image Retrieval
Matsumoto,Wataru;Kameyama,Keisuke
Proceedings of 2013 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS)   602-607   Nov 2013   [Refereed]
Object color plays an important role in object
image matching. Color invariants are robust features under
varying illumination conditions. In this work, we analyze the
estimation process of the color invariants by Geusebroek et al.
from RGB images...
Composite Color Invariant Feature H' Applied to Image Matching
Kameyama,Keisuke;Wataru,Matsumoto
Lecture Notes in Computer Science (Proc. ICONIP 2013)   8228 401-408   Nov 2013   [Refereed]
Object color is one of the most important feature in camerabased
object matching. Color invariants are features based on the models
of color observation that tends to be constant under varying conditions of
illumination and surface. In this work, ...
Towards Making Thinning Algorithms Robust against Noise in Sketch Images
Houssem, Chatbri;Keisuke, Kameyama
Proceedings of International Conference on Pattern Recognition (ICPR 2012)   3030-3033   Nov 2012   [Refereed]
Real-Time Lecture Delivery Connecting Distant Classrooms by Redundant Network Combining a High-Speed Satellite (WINDS) and a Terrestrial Line (JGN2plus)
Mitsuteru, Nakamura;Keisuke, Kameyama;Shin, Takahashi;Yukio, Fukui;Nobuhiko, Kitawaki;Su, Wei Tan;Yoshikazu, Kamiya
Proc. 2012 8th IEEE Colloquium on Signal Processing & Its Applications (CSPA 2012)   367-372   Mar 2012   [Refereed]
Image Feature Extraction and Similarity Evaluation using Higher-Order Moment Kernels
KAMEYAMA, Keisuke
Technical Report of IEICE (Neurocomputing)   111(483) 393-398   Mar 2012
An Adaptive Thinning Algorithm for Sketch Images based on Gaussian Scale Space
CHATBRI,Houssem;KAMEYAMA,Keisuke
IEICE technical report. Image engineering   111(442) 33-38   Feb 2012
We introduce an adaptation framework based on scale space filtering for making thinning algorithms robust against noise in an input sketch. The framework takes a sketch image as input, produces a set of Gaussian blurred images of the input sketch ...
A Composite Illumination Invariant Color Feature and Its Application to Partial Image Matching
KOBAYASHI,Masaki;KAMEYAMA,Keisuke
IEICE Transactions on Information and Systems   95(10) 2522-2532   Jan 2012   [Refereed]
In camera-based object recognition and classification, surface color is one of the most important characteristics. However, apparent object color may differ significantly according to the illumination and surface conditions. Such a variation can b...
Kwan, Paul W.;Kameyama, Keisuke;Gao, Junbin;Toraichi, Kazuo
INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE   25(5) 643-673   Aug 2011   [Refereed]
Speaker Verification using Weighted Local MFCC Features Extracted by Minimum Verification Error Learning
Shunsuke, Sakai;Toru, Nozaki;Keisuke, Kameyama
Australian Journal of Intelligent Information Processing Systems (Proceedings of ICONIP 2010)   7-12   Nov 2010   [Refereed]
Feature Selection for User-adaptive Content-Based Music Retrieval using Particle Swarm Optimization
Toru,Nozaki;Keisuke,Kameyama
Proceedings of 2010 10th International Conference on Intelligent Systems Design and Applications (ISDA 10)   941-946   Nov 2010   [Refereed]
Evaluation of Audio and Video Quality in Distance Education by Ultra-High Speed Internet Satellite "Kizuna"
OKUBO,Naoko;NAKAMURA,Mitsuteru;TAKAHASHI,Shin;KAMEYAMA,Keisuke;FUKUI,Yukio;KITAWAKI,Nobuhiko;SATO,Tetsuo;OGAWA,Emiko
Technical report of IEICE. CQ   110(118) 103-108   Jul 2010
A remote lecture experiment, collaborated by three universities in Asia, via ultra-high speed interne satellite Kizuna has been held on January to March, 2009 and September to November, 2009. Participants were University of Tsukuba in Japan, Asia ...
Text-independent Speaker Verification using Optimized Linear Combination of Local MFCC Features
Shunsuke,Sakai;Keisuke,Kameyama
Proceedings of 7th IASTED International Conference on Signal Processing, Pattern Recognition and Applications (SPPRA2010) (Innsbruck)   #678-063   Mar 2010   [Refereed]
Partial Image Retrieval using SIFT based on Illumination Invariant Features
Masaki,Kobayashi;Keisuke,Kameyama
Proceedings of International Conference on Multimedia Computing and Information Technology (MCIT 2010) (Sharjah UAE)   33-36   Mar 2010   [Refereed]
Comparison of Subspace Decomposition and Grouping Methods in Independent Subspace Analysis for Source Separation
Shintaro,Noguchi;Keisuke,Kameyama
Proceedings of RISP International Workshop on Nonlinear Circuits, Communications and Signal Processing (Honolulu)   21-24   Mar 2010   [Refereed]
Kwan, Paul W.;Gao, Junbin;Guo, Yi;Kameyama, Keisuke
INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE   24(1) 15-38   Feb 2010   [Refereed]
WINDS (KIZUNA)-based Collaborative e-Learning Project in Thailand, Malaysia and Japan
HISANAGA, Makoto;TAKAHASHI, Shin;KAMEYAMA, Keisuke;FUKUI, Yukio;KITAWAKI, Nobuhiko
TRANSACTIONS OF THE JAPAN SOCIETY FOR AERONAUTICAL AND SPACE SCIENCES, AEROSPACE TECHNOLOGY JAPAN   8(27) Tj_1-Tj_9   Jan 2010   [Refereed]
The expanding digital divide deprives students in developing countries with opportunities for education. Advanced countries have the ability to enhance those opportunities. For this study, the authors set up and tested a remote lecture system usin...
Text-Independent Speaker Verification using Optimized Linear Combination of Local MFCC Features
坂井俊亮;亀山啓輔
第12回情報論的学習理論ワークショップ (IBIS 2009), Paper P044      Oct 2009
Content-Based Image Retrieval using SIFT based on Illumination Invariant Features
KOBAYASHI,Masaki;KAMEYAMA,Keisuke
Technical report of IEICE. PRMU   109(249) 1-6   Oct 2009
Recently, there has been an increasing need for Content-Based Image Retrieval (CBIR), especially the partial image retrieval system, which retrieves partial correspondences in the image database. However, the apparent color of objects are strongly...
Kameyama, Keisuke
IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS   E92D(7) 1354-1361   Jul 2009   [Refereed]
Report on the experimental collaborative remote lectures with the WINDS/ Kizuna satellite
TAKAHASHI,Shin;HISANAGA,Makoto;KAMEYAMA,Keisuke;FUKUI,Yukio;KITAWAKI,Nobuhiko
Technical report of IEICE. SAT   109(118) 39-44   Jul 2009
We reports the experiment of collaborative remote lectures with the WINDS/Kizuna satellite held last year. In the experiment, three universities: University of Tsukuba, Asia Institute of Technology in Thai, and Multimedia University in Malaysia, w...
Relevance Tuning in Content-Based Retrieval of Structurally-Modeled Images using Particle Swarm Optimization
Nozomi, Oka;Keisuke, Kameyama
Proceedings of 2009 IEEE Symposium on Computational Intelligence for Multimedia Signal and Vision Processing (CIMSVP)   Paper no. 6   Mar 2009   [Refereed]
A Function Approximation Method for Images with Grading Regions
K.,Miyamoto;T.,Kamina;T.,Sugiyama;K.,Kameyama;K.,Toraichi;Y.,Ohmiya
International Journal of Image and Graphics   9(1) 101-119   Jan 2009   [Refereed]
Content-Based Music Retrieval with Nonlinear Feature Space Transformation using Relevance Feedback
Shunsuke, Sakai;Keisuke, Kameyama
Proceedings of 2008 IEEE International Conference on Systems, Man, and Cybernetics (SMC 2008)   1379 - 1384   Oct 2008   [Refereed]
4X-3 Feature Set Selection with User Relevance Feedback on Content-based Retrieval of Music
Sakai,Shunsuke;Kameyama,Keisuke
全国大会講演論文集   70(2) -463   Mar 2008
6C-2 Local Higher-Order Moment Kernel and Conventional Kernels in Texture Classification by SVM
Kameyama Keisuke
全国大会講演論文集   70(2) -43   Mar 2008
1R-3 Adaptive Coarse Classification using Relevance Feedback in Content-Based Image Retrieval
Kobayashi,Masaki;Kameyama,Keisuke
全国大会講演論文集   70(1) -473   Mar 2008
Locally Adaptive Selection of Parameters in Regularization-Based Denoising Algorithms
Katsuhiko, Someya;Keisuke, Kameyama
Proceedings of the 5th IASTED International Conference on Signal Processing, Pattern Recognition and Applications (SPPRA2008)   Paper no. 599-155   Feb 2008   [Refereed]
Comparison of local higher-order moment kernel and conventional kernels in SVM for texture classification
Kameyama,Keisuke
Lecutre Notes in Computer Science (Proc. 14th International Conference on Neural Information Processing (ICONIP’07))   4984(Part I) 851-860   Jan 2008
Use of local higher-order moment kernel (LHOM kernel) in SVMs for texture classification was investigated by comparing it with SVMs using other conventional kernels. In the experiments, it became clear that SVMs with LHOM kernels achieve better tr...
Relevance Optimization in Image Database using Feature Space Preference Mapping and Particle Swarm Optimization
Mayuko,Okayama;Nozomi,Oka;亀山,啓輔
Proceedings of 14th International Conference on Neural Information Processing (ICONIP’07), LNCS   4985 608-617   Jan 2008   [Refereed]
Two methods for retrieval relevance optimization using the user's feedback is proposed for a content-based image retrieval (CBIR) system. First, the feature space used in database image clustering for coarse classification is transferred to a pref...
Comparison of Local Higher-Order Moment Kernel and Conventional Kernels in SVM for Texture Classification
Keisuke, Kameyama
Proceedings of 14th International Conference on Neural Information Processing (ICONIP’07), LNCS   4984 852-860   Nov 2007   [Refereed]
Optimization of Similarity Evaluation Algorithm Using Relevance Feedback in Content-Based Image Retrieval
OKA,Nozomi;KAMEYAMA,Keisuke;TORAICHI,Kazuo
Journal of Japan Society for Fuzzy Theory and Intelligent Informatics   19(5) 524-536   Oct 2007   [Refereed]
Recently, Content-based Image Retrieval (CBIR) which evaluates the relevance of images derived by image features is being widely investigated, aiming at retrieval from large database of unlabeled images. Most commonly in CBIR, "similarity", which ...
高次モーメントスペクトルカーネルを用いたサポートベクトルマシンによる信号分類
亀山, 啓輔
Risk engineering   3(0) 29-34   Mar 2007
Image resolution conversion based on an edge-adaptive interpolation kernel
Mori,Takashi;Kameyama,Keisuke;Ohmiya,Yasuhiro;Lee,Jia;Toraichi,Kazuo
IEEE PACIFIC RIM CONFERENCE ON COMMUNICATIONS, COMPUTERS AND SIGNAL PROCESSING   497-500   Jan 2007   [Refereed]
-In this paper we propose a novel edge-adaptive interpolation method which is easy to implement and computationally efficient. Although various edge-adaptive image interpolation methods have been proposed in the past, none of them are comparable t...
Content-Based Image Retrieval of Kaou Images by Relaxation Matching of Region Features
K.,Kameyama;S.-N.,Kim;M.,Suzuki;K.,Toraichi;+山本,隆志
International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems   14(4) 509-523   Aug 2006   [Refereed]
Hardware Implementation Method of TV Picture Quality Enhancement by Fluency Interpolation(<Special Section>Image Processing and Coding)
Ohmiya,Yasuhiro;Toraichi,Kazuo;Miura,Yasuyuki;Kitamura,Mamoru;Okamoto,Akira;Wada,Koichi;Kameyama,Keisuke;Morooka,Yasuo
The journal of the Institute of Image Information and Television Engineers   60(7) 1042-1050   Jul 2006   [Refereed]
New large displays are replacing the traditional Cathode Ray Tube. An important goal is to improve the quality of TV images to suit these displays. To achieve this goal, we use an interpolation process that convolutes the TV signal. In particular,...
B-19-14 Consideration concerned with construction of theoretical model for description ubiquitous cloud (Ver.1)
Niwa,Miyuki;Kamina,Tetsuo;Wu,De-An;Kameyama,Keisuke;Katagishi,Kazuki;Toraichi,Kazuo;Murakami,Hitomi;Ohashi,Masayoshi
Proceedings of the IEICE General Conference   2006(2) 555   Mar 2006
Matched Filter Design by Fluency Analysis for a More Accurate Fundus Image Blood-Vessel Extraction
K., Sheng;K., Kameyama;K., Katagishi;and, K. Toraichi
The 4th IASTED International Conference on Biomedical Engineering   Paper no. 519-088   Feb 2006   [Refereed]
Image Resolution Conversion by Optimized Adaptation of Interpolation Kernels
A., Fujii;K., Kameyama;T., Kamina;Y., Ohmiya;and, K. Toraichi
The 3rd IASTED International Conference on Signal Processing, Pattern Recognition, and Applications   Paper no. 520-051   Feb 2006   [Refereed]
An Image Segmentation Method for Function Approximation of Gradation Images
K., Miyamoto;T., Kamina;T., Sugiyama;K., Kameyama;and, K. Toraichi
The 3rd IASTED International Conference on Signal Processing, Pattern Recognition, and Applications   Paper no. 520-057   Feb 2006   [Refereed]
Optimal parameter selection in image similarity evaluation algorithms using Particle Swarm Optimization
Kameyama,Keisuke;Oka,Nozomi;Toraichi,Kazuo
Proceedings of 2006 IEEE Congress on Evolutionary Computation   3824-3831   Jan 2006   [Refereed]
Image relevance evaluation in conventional Content-Based Image Retrieval (CBIR) researches typically relied on a given criterion. However, it is important that this criterion can be changed according to the use of the image database. This work pro...
Image Enhancement Using Multiple Video Frames and Non-uniform Fluency Interpolation
K., Hirano;K., Kameyama;Y., Ohmiya;K., Toraichi
Proc. 4th IASTED International Conference on Communications, Internet and Information Technology 2005   Paper no. 496-073   Oct 2005   [Refereed]
Content-Based Image Retrieval of Kaou Images by Region Characterization and Probabilistic Relaxation
K., Kameyama; S-N., Kim; K., Toraichi; T., Yamamoto
Proc. Modeling Decisions in Artificial Intelligence (MDAI 2005)   Paper no.109   Jul 2005   [Refereed]
Feature Extraction of Hyperspectral Data for under Spilled Blood Visualization Using Particle Swarm Optimization
S., T. Monteiro;K., Uto;Y., Kosugi;N., Kobayashi;E., Watanabe;K., Kameyama
International Journal of Bioelectromagnetism   17(1) 1-4   Jul 2005   [Refereed]
Feature Extraction of Hyperspectral Data for under Spilled Blood Visualization Using Particle Swarm Optimization
S., T. Monteiro; K., Uto; Y., Kosugi; N., Kobayashi; E., Watanabe; K., Kameyama
Joint Meeting of 5th Int'l Conf. on Bioelectromagnetism and 5th Int'l Symp. on Noninvasive Functional Source Imaging within the Human Brain and Heart (BEM&NFSI)      Feb 2005   [Refereed]
Content-Based Retrieval of Kamon Images by Image Smoothing and Relaxation
T., Tachikawa;K., Kameyama;T., Kawabe;K., Toraichi;N., Otsu;T., Kurita;P., W. H. Kwan
Proc. IASTED International Conference on Modeling, Identification and Control (MIC)   Paper no. 457-174   Feb 2005   [Refereed]
Image Interpolation Using Feedforward Neural Network
H., Aokage; K., Kameyama; K., Wada
Proc. IASTED International Conference on Artificial Intelligence and Applications (AIA) 2005   Paper no. 453-314   Feb 2005   [Refereed]
Human Perception Model for Ultrasonic Difference Tones
T., Sugimoto;T., Kawabe;K., Kameyama;K., Toraichi
Proc. IASTED International Conference on Modeling, Identification and Control (MIC) 2005   457-170   Feb 2005   [Refereed]
A Shape-Directed Scaling Method for Fundus Image with Maintenance to Blood-Vessel Shapes and Color Reality
Sheng,Kai;Kameyama,Keisuke;Toraichi,Kazuo;Mitamura,Yoshinori;Katagishi,Kazuki;Morooka,Yasuo;Ohmiya,Yasuhiro
IEEJ Transactions on Electronics, Information and Systems   125(9) 1399-1407   Jan 2005   [Refereed]
When digitized fundus images are used in medicine, important information for clinicians diagnosis should be maintained well after scaling. Conventional scaling methods select the interpolation kernel based on Shannons sampling theorem which is onl...
Texture Classification by Support Vector Machines with Kernels for Higher-Order Gabor Filtering
K., Kameyama;K., Taga
Proc. International Joint Conference on Neural Networks 2004 (Budapest)   4 3009-3014   Jul 2004   [Refereed]
Approximate Query Processing for a Content-Based Image Retrieval Method
P., W. H. Kwan;K., Toraichi;H., Kitagawa;K., Kameyama
DEXA 2003, LNCS 2736   517-526   Sep 2003   [Refereed]
A system for Content-Retrieval and Browsing of Kaou Monogram Images using Contour and Color Characteristics
S-N., Kim;M., Suzuki;K., Kameyama;K., Toraichi;Takashi, Yamamoto
Proc. 2003 IEEE Pacific Rim Conference on Communications, Computers and Signal Processing   844-847   Aug 2003   [Refereed]
Regularization of Hidden Layer Unit Response for Neural Networks
K., Taga;K., Kameyama;K., Toraichi
Proc. 2003 IEEE Pacific Rim Conference on Communications, Computers and Signal Processing   348-351   Aug 2003   [Refereed]
Layered Neural Network Training with Model Switching and Hidden Layer Feature Regularization
K., Kameyama;K., Taga
Proc. International Joint Conference on Neural Networks 2003 (Portland)   3 2294-2299,   Jul 2003   [Refereed]
On a Relaxation-Labeling Algorithm for Real-time Contour-based Image Similarity Retrieval
P., W. H. Kwan;K., Kameyama;K., Toraichi
Image and Vision Computing Journal   21(3) 285-294   Mar 2003   [Refereed]
A Smooth Interpolation Method For Nonuniform Samples Based on Sampling Functions Composed of Piecewise Polynomials
T., Takahashi;K., Toraichi;K., Kameyama;and, K. Nakamura
Proc. IEEE Pacific Rim-Conference on Multimedia 2002 (PCM2002)   417-424   Dec 2002   [Refereed]
Constructive Relaxation Matching Involving Dynamical Model Switching and its Application to Shape Matching
K., Kameyama;K., Toraichi;Y., Kosugi
International Journal of Image and Graphics   2(4) 655-668   Oct 2002   [Refereed]
A Dispatcher-driven Processing Architecture for Image Retrieval using Clustered Relaxation Matching Servers
P., W. H. Kwan;K., Toraichi;K., Wada;and, K. Kameyama;+亀山, 啓輔
Proc. of the IASTED International Conference on Networks, Parallel and Distributed Processing, and Applications (NPDPA2002)   211-216   Oct 2002   [Refereed]
TAST - Trademark Application Assistant
P., W. H. Kwan;K., Toraichi;K., Kameyama;F., Kawazoe;and, K. Nakamura
Proc. IEEE International Conference on Image Processing (ICIP) 2002   1 884-887   Sep 2002   [Refereed]
Image Matching based on Relaxation and Model Switching on Contour Characterization
K., Kameyama;K., Toraichi;Y., Kosugi
Proc. Joint 1st Int'l Conf. on Soft Computing and Intell. Sys., and 3rd Int'l Symp. on Advanced Intell. Sys. (SCIS & ISIS) 2002   paper 24B4-5   May 2002   [Refereed]
Relaxation with Model Switching and its application to shape matching
K., Kameyama;K., Toraichi;Y., Kosugi
Proceedings of the 2002 International Joint Conference on Neural Networks (IJCNN 2002)   pp. 1564-1569   May 2002   [Refereed]
Connecting Image Similarity Retrieval with Consistent Labeling by Introducing a Match-All Label
P., W. H. Kwan;K., Kameyama;and, K. Toraichi
Proceedings of the 10th IEEE International Conference on Fuzzy Systems   3 334-337   Dec 2001   [Refereed]
A Note on Shape Matching using a Constructive Relaxation Method
K., Kameyama;K., Toraichi;Y., Kosugi
Proc. 2001 IEEE Pacific Rim Conference on Comm., Comp. and Sig. Pro.   267-270   Aug 2001   [Refereed]
On A Kaoh Database System using Fluency Functions based Automatic and Jaggyless Image Coding
M., Suzuki;K., Kameyama;K., Toraichi;K., Katagishi;and, T. Yamamoto
Proc. 2001 IEEE Pacific Rim Conference on Comm., Comp. and Sig. Pro.   148-151   Aug 2001   [Refereed]
Trademark Retrieval by Relaxation Matching on Fluency Function Approximated Image Contours
P., W. H. Kwan;K., Kameyama;K., Toraichi
Proc. 2001 IEEE Pacific Rim Conference on Comm., Comp. and Sig. Pro.   255-258   Aug 2001   [Refereed]
On an Image Contour Compression Method using Compactly Supported Sampling Functions
P., W. H. Kwan;K., Toraichi;K., Wada;K., Kameyama;K., Katagishi;T., Sugiyama;F., Yoshikawa
Proc. of IEEE Pacific Rim Conf. on Communications, Computers and Signal Processing   271-274   Aug 2001   [Refereed]
Fluency 解析の画像処理への応用 - 新しいデジタル画像変換技術 -
TORAICHI,Kazuo;KAMEYAMA,Keisuke
印刷雑誌   84(6) 23-28   Jun 2001   [Refereed]

Books etc

 
Model Switching Maneuvers in Pattern Recognition Systems
Kameyama,Keisuke
Sep 1999   
リスク工学の視点とアプローチ ―現代生活に潜むリスクにどう取り組むかー
Hiroshi FURUKAWA; Mika SATO; Keisuke KAMEYAMA; Ayako TANIGUCHI; Michitaka UMEMOTO; Yuko HATANO;
Corona-sha   Jan 2009   

Conference Activities & Talks

 
JPEG perceptual encryption with bit-pair permutation in quantized DCT coefficients
淸水, 恒輔;鈴木, 大三;亀山, 啓輔
IEICE 33rd Signal Processing Symposium   6 Nov 2018   電子情報通信学会
Reversible data hiding for two-layer HDR image coding using difference expansion into residual signals
楊, 凱;淸水, 恒輔;鈴木, 大三;亀山, 啓輔
IEICE 33rd Signal Processing Symposium   6 Nov 2018   電子情報通信学会
3-D human pose estimation from 2-D still image by least-square regression using convolutional neural network
長谷川, 輝;鈴木, 大三;亀山, 啓輔
IEICE General Conference   22 Mar 2017   電子情報通信学会
Human hand detection based on skin color region detection and HOG features
堀内, 圭佑;鈴木, 大三;亀山, 啓輔
IEICE General Conference   22 Mar 2017   電子情報通信学会
Palm vein authentication using shape context descriptor
杉原, 伊織;鈴木, 大三;亀山, 啓輔
IEICE General Conference   22 Mar 2017   電子情報通信学会

Research Grants & Projects

 
Statistical pattern recognition
Content-based multimedia database
Pattern recognition and signal processing using higher-order statistics
Learning in neural networks
Simultaneous search of model and parameters in pattern recognition systems.