| IEICE Technical Committee Submission System Conference Schedule |
Online Proceedings [Sign in] Tech. Rep. Archives |
All Technical Committee Conferences (Searched in: All Years)
| Committee | Date Time | Place | Paper Title / Authors | Abstract | Paper # | |
| NC, IBISML, IPSJ-BIO, IPSJ-MPS [detail] | 2022-06-28 13:30 |
Okinawa | (Okinawa, Online) (Primary: On-site, Secondary: Online) |
Joint-Conditional Mutual Information Based Feature Subset Selection for Remotely Sensed Hyperspectral Image Classification U A Md Ehsan Ali, Keisuke Kameyama (Univ. Tsukuba)  NC2022-16 IBISML2022-16 |
Hundreds of contiguous bands of remotely sensed hyperspectral image (HSI) capture the spectral signatures of observed ob... [more] | NC2022-16 IBISML2022-16 pp.115-122 |
| MI, MICT [detail] | 2021-11-05 12:45 |
Online | Online (Online) | [Invited Talk]
Iris Authentication using Higher-Order Spectral Features Keisuke Kameyama (Univ. Tsukuba) MICT2021-35 MI2021-33 |
This report summarizes the works on the use of higher-order spectral (HOS) features for iris authentication. Initially, ... [more] | MICT2021-35 MI2021-33 pp.31-36 |
| PRMU, IPSJ-CVIM | 2020-03-16 15:10 |
Kyoto | (Kyoto) (Cancelled but technical report was issued) |
Metal Material Analysis using SEM Images of Multiple Magnifications Ryunosuke Ito, Keisuke Kameyama (Univ. Tsukuba), Hideitsu Hino (ISM) PRMU2019-78 |
In recent years, in order to quickly develop metal materials having special properties, it is urgently necessary to make... [more] | PRMU2019-78 pp.71-76 |
| IBISML | 2020-01-10 14:05 |
Tokyo | ISM (Tokyo) | Active learning for multiple data selection using reinforcement learning Yuusuke Taguchi (Univ. of Tsukuba), Hideitsu Hino (ISM), Keisuke Kameyama (Univ. of Tsukuba) IBISML2019-32 |
(To be available after the conference date) [more] | IBISML2019-32 pp.99-106 |
| BioX | 2019-10-03 13:55 |
Okinawa | (Okinawa) | Recognition feature prediction from low-resolution iris images using CNN Ryo Watanabe, Keisuke Kameyama (Univ. of Tsukuba) BioX2019-55 |
In iris authentication, Daugman's method employing Gabor features is widely supported. However, the method's performance... [more] | BioX2019-55 pp.5-10 |
| IBISML | 2018-11-05 15:10 |
Hokkaido | Hokkaido Citizens Activites Center (Kaderu 2.7) (Hokkaido) | [Poster Presentation]
Parameter Density Inheritance Using Kernel Density Estimation for Efficient CNN Learning Keisuke Horiuchi, Keisuke Kameyama (Tsukuba Univ.) IBISML2018-45 |
CNNs have shown state-of-the-art performances on a large variety of classification tasks. However, because of its comple... [more] | IBISML2018-45 pp.9-15 |
| IBISML | 2018-11-05 15:10 |
Hokkaido | Hokkaido Citizens Activites Center (Kaderu 2.7) (Hokkaido) | [Poster Presentation]
Revising the Algorithm of Ensenble Learning by an Index of Complementarity among Weak Learners Shota Utsumi, Keisuke Kameyama (Univ. of Tsukuba) IBISML2018-102 |
In ensemble learning, the performance of each weak learner and their acquisition of complementary functions affects the ... [more] | IBISML2018-102 pp.429-434 |
| PRMU, IBISML, IPSJ-CVIM [detail] | 2018-09-20 09:40 |
Fukuoka | (Fukuoka) | Arrangement of Complementary Weak Learners using Weights Assigned to Data in Parallel Ensemble Learning Shota Utsumi, Keisuke Kameyama (Univ. of Tsukuba) PRMU2018-37 IBISML2018-14 |
The accuracy of each weak learner and acquisition of complementary functions among weak learners are important for impro... [more] | PRMU2018-37 IBISML2018-14 pp.9-15 |
| PRMU, IBISML, IPSJ-CVIM [detail] | 2018-09-21 09:50 |
Fukuoka | (Fukuoka) | Interpretable active sampling Yuusuke Taguchi, Keisuke Kameyama (Univ. of Tsukuba), Hideitsu Hino (ism) PRMU2018-50 IBISML2018-27 |
(To be available after the conference date) [more] | PRMU2018-50 IBISML2018-27 pp.97-104 |
| IA | 2017-11-16 14:50 |
Overseas | KMITL, Bangkok, Thailand (Overseas) | Log analysis for hijacked user account's login detection method based on an autonomous system number of access source Akira Sato, Shuji Sannomiya, Yoshihiro Oyama, Hisashi Nakai, Kenichi Yoshida, Keisuke Kameyama (Univ. of Tsukuba) IA2017-50 |
User accounts may be hijacked carelessly, and system administrators should detect such hijacked user accounts as soon a... [more] |
IA2017-50 pp.95-98 |
| PRMU | 2017-10-13 15:20 |
Kumamoto | (Kumamoto) | Stability of Classification Performance by AdaBoost with Parallell Adjustment using Error-Correcting Output Codes Shota Utsumi, Keisuke Kameyama (Univ. of Tsukuba) PRMU2017-99 |
[more] | PRMU2017-99 pp.205-210 |
| PRMU, IBISML, IPSJ-CVIM [detail] | 2017-09-15 10:00 |
Tokyo | (Tokyo) | Stabilization of Classification Performance by AdaBoost with Parallel-Adjustment using Error-Correcting Output Codes Shota Utsumi, Keisuke Kameyama (Univ. of Tsukuba) PRMU2017-44 IBISML2017-16 |
[more] | PRMU2017-44 IBISML2017-16 pp.43-50 |
| VLD, DC, CPSY, RECONF, CPM, ICD, IE (Joint) [detail] |
2016-11-30 11:45 |
Osaka | Ritsumeikan University, Osaka Ibaraki Campus (Osaka) | Keypoint Detection based on Learning to Rank for Robust Image Matching under Resolution Variation Satoshi Yoshikawa, Keisuke Kameyama (Univ. of Tsukuba) CPM2016-85 ICD2016-46 IE2016-80 |
The image matching by keypoint selection from images is used in various situations in computer vision. Among them, Sca... [more] |
CPM2016-85 ICD2016-46 IE2016-80 pp.45-50 |
| MBE, BioX, NC | 2016-10-22 09:25 |
Osaka | Osaka Electro-Communication University (Osaka) | Constructing Multi-Class Classifiers by Combination of 2-Class Layered Neural Networks Shota Utsumi, Keisuke Kameyama (Univ. of Tsukuba) BioX2016-18 MBE2016-32 NC2016-17 |
Exhaustive code is one of the error correcting codes usable in improving the accuracy of multi-class classifier by mani... [more] |
BioX2016-18 MBE2016-32 NC2016-17 pp.7-12 |
| MBE, BioX, NC | 2016-10-22 17:45 |
Osaka | Osaka Electro-Communication University (Osaka) | Iris Authentication using Local Spectral Features and their Relational Operations Miharu Aizawa, Keisuke Kameyama (Univ. Tsukuba) BioX2016-32 MBE2016-46 NC2016-31 |
Recently, methods of personal authentication using biometric features have been attracting attention. Daugman's pioneer... [more] | BioX2016-32 MBE2016-46 NC2016-31 pp.83-88 |
| ITS, IE, ITE-AIT, ITE-HI, ITE-ME, ITE-MMS, ITE-CE [detail] | 2016-02-22 10:15 |
Hokkaido | Hokkaido Univ. (Hokkaido) | Estimation of Secondary Cell Performances by Analysis of Electrode Images Ryo Kuroki, Keisuke Kameyama (Univ. Tsukuba) ITS2015-60 IE2015-102 |
The performance of secondary cells used by electric cars depends on the performances of their electrodes. However, the r... [more] | ITS2015-60 IE2015-102 pp.23-28 |
| PRMU, HIP | 2012-12-13 15:15 |
Yamagata | (Yamagata) | Higher-Order Moment Orders and Performance in Texture Classification using Support Vector Machines Trung Nguyen Bao Phan, Keisuke Kameyama (Univ. of Tsukuba) PRMU2012-75 HIP2012-64 |
Conventionally, local moment functions (local autocorrelation functions) of orders up to 3 have been widely used as feat... [more] | PRMU2012-75 HIP2012-64 pp.31-36 |
| ITE-BCT, IPSJ-AVM, CS, IE [detail] | 2012-12-06 13:55 |
Fukui | Fukuisi-chiiki-kouryu-plaza (Fukui) | Comparison of Hue Feature and Illumination Invariant Color Feature H' in Partial Image Retrieval Wataru Matsumoto, Keisuke Kameyama (U.Tsukuba) CS2012-78 IE2012-92 |
Object color plays an important role in image matching. Kobayashi et al., proposed the color invariant feature H' by com... [more] | CS2012-78 IE2012-92 pp.41-46 |
| MBE, NC (Joint) |
2012-03-16 13:45 |
Tokyo | Tamagawa University (Tokyo) | Image Feature Extraction and Similarity Evaluation using Higher-Order Moment Kernels Keisuke Kameyama (Univ. of Tsukuba) NC2011-188 |
The Higher-Order Moment (HOM) kernel has been known to enable efficient utilization of higher-order moment (statistical)... [more] | NC2011-188 pp.393-398 |
| ITS, IE, ITE-AIT, ITE-HI, ITE-ME [detail] | 2012-02-20 11:40 |
Hokkaido | Hokkaido Univ. (Hokkaido) | An Adaptive Thinning Algorithm for Sketch Images based on Gaussian Scale Space Houssem Chatbri, Keisuke Kameyama (Univ. of Tsukuba) ITS2011-31 IE2011-107 |
We introduce an adaptation framework based on scale space filtering for making thinning algorithms robust against noise ... [more] | ITS2011-31 IE2011-107 pp.33-38 |
[Return to Top Page]