-
Shuichi Matsumoto
2005 Volume 59 Issue 8 Pages
1134-1135
Published: August 01, 2005
Released on J-STAGE: March 14, 2011
JOURNAL
FREE ACCESS
-
Ryoichi Kawada
2005 Volume 59 Issue 8 Pages
1136-1139
Published: August 01, 2005
Released on J-STAGE: August 17, 2011
JOURNAL
FREE ACCESS
-
Full Reference Methods
Atsushi Kitamura
2005 Volume 59 Issue 8 Pages
1140-1144
Published: August 01, 2005
Released on J-STAGE: August 17, 2011
JOURNAL
FREE ACCESS
-
Osamu Sugimoto
2005 Volume 59 Issue 8 Pages
1145-1149
Published: August 01, 2005
Released on J-STAGE: August 17, 2011
JOURNAL
FREE ACCESS
-
Atsuro Ichigaya
2005 Volume 59 Issue 8 Pages
1150-1153
Published: August 01, 2005
Released on J-STAGE: March 14, 2011
JOURNAL
FREE ACCESS
-
Eisuke Nakasu
2005 Volume 59 Issue 8 Pages
1154-1155
Published: August 01, 2005
Released on J-STAGE: March 14, 2011
JOURNAL
FREE ACCESS
-
Aki Kobayashi
2005 Volume 59 Issue 8 Pages
1156-1161
Published: August 01, 2005
Released on J-STAGE: March 14, 2011
JOURNAL
FREE ACCESS
-
Satoshi Kabasawa, Kenichiro Kawasaki
2005 Volume 59 Issue 8 Pages
1162-1168
Published: August 01, 2005
Released on J-STAGE: March 14, 2011
JOURNAL
FREE ACCESS
-
Yoshihiro Konishi
2005 Volume 59 Issue 8 Pages
1169-1172
Published: August 01, 2005
Released on J-STAGE: March 14, 2011
JOURNAL
FREE ACCESS
-
Atsushi Matsui, Simon Clippingdale, Fumiki Uzawa, Takashi Matsumoto
2005 Volume 59 Issue 8 Pages
1183-1190
Published: August 01, 2005
Released on J-STAGE: August 17, 2011
JOURNAL
FREE ACCESS
We developed a new algorithm for face recognition using a Bayesian framework. In our algorithm, posterior distributions are computed using a Hamiltonian Monte Carlo method. The face features we used were those used in our previous work based on the elastic graph matching method. While our previous method attempted to optimize facial feature point positions to maximize a similarity function between each model and face region in the input sequence, our new approach evaluates posterior distributions of models conditioned on the input sequence. Experimental results show that our new algorithm out-performs the Eigenface method in terms of both identification errors and processing costs. Our new algorithm eliminates almost all identification errors on sequences showing individuals smiling, although such data was not used in training.
View full abstract
-
Purim Na Bangchang, Mehrdad Panahpour Tehrani, Toshiaki Fujii, Masayuk ...
2005 Volume 59 Issue 8 Pages
1191-1198
Published: August 01, 2005
Released on J-STAGE: March 14, 2011
JOURNAL
FREE ACCESS
In this paper, we propose a new 3D visual system, named “Free Viewpoint Television or” FTV, which can acquire, process, and display any 3D scene in realtime. With this FTV system, users can freely control their own viewpoint and direction. The idea is based on the concept of ray-space, where 3D information can be represented by a group of light rays. A collection of light rays is obtained through an array of cameras, while the missing ray informationbetween cameras is generated by interpolation. The first prototype based on this concept had both good image quality and a fast display rate.
View full abstract
-
Kunio Sakamoto, Rieko Kimura
2005 Volume 59 Issue 8 Pages
1199-1203
Published: August 01, 2005
Released on J-STAGE: August 17, 2011
JOURNAL
FREE ACCESS
A display system that does not require special glasses is desirable for 3D imaging. Conventional lenticular and parallax barrier display systems have pseudoscopic images. These images occur at the position where theleft eye can see the right eye view and vice versa, causing 3D image depth to be reversed to the observer. We developed lenticular and barrier 3D displays using a polarizer slit to eliminate pseudoscopic viewing regions. These pseudoscopic viewing regions can be eliminated by arranging the gap between neighboring viewing zones. Because the polarizer slits create stereoscopic viewing regions and gaps, multiple observers perceive stereo-pair images within a viewing region where the left eyeis in a left eye zone and the right eye is in a right eye zone.
View full abstract
-
Yasuhiro Yoshioka, Yoshiyuki Furukawa, Hiroshi Masuda
2005 Volume 59 Issue 8 Pages
1205-1210
Published: August 01, 2005
Released on J-STAGE: August 17, 2011
JOURNAL
FREE ACCESS
We propose modeling operations using a volume-based cut-and-paste method for generating rough 3D models. Cut-and-paste editing extracts a characteristic feature from a source model and copies it to a target model. To create such a cut-and-paste technique, we developed a new method that consists of mesh segmentation and volume fitting. In our method, a feature region and its surrounding area are separated from the user-specified area and are used for generating a parametric volume that involves the feature region. In feature pasting, parametric volumes are deformed and pasted to the target model, and then, features inside the volume are adaptively deformed and pasted to the target. Our experimental results show our operations can effectively generate new models by removing, pasting, and deforming partial shapes in existing models.
View full abstract
-
Yu Takigawa, Seiji Hotta, Senya Kiyasu, Sueharu Miyahara
2005 Volume 59 Issue 8 Pages
1211-1214
Published: August 01, 2005
Released on J-STAGE: August 17, 2011
JOURNAL
FREE ACCESS
We propose a weighted-categorical average pattern classifier (CAP) and a variable-CAP, which are modified CAP, as identification methods for online writer identification when few study patterns are available. Our proposed method had a writer identification rate was higher than that of CAP.
View full abstract
-
Mie Sato, Shoji Oshigiri, Hiroshi Hasegawa, Masao Kasuga, Miyoshi Ayam ...
2005 Volume 59 Issue 8 Pages
1215-1218
Published: August 01, 2005
Released on J-STAGE: August 17, 2011
JOURNAL
FREE ACCESS
Curved roads where driving is difficult can cause traffic accidents. To avoid such accidents, the cognitive properties of drivers on curved roads should be investigated more precisely. We examined the functional visual field of drivers in various types of roads, such as curved and straight roads. Our results show the functional visual field on curved roads is narrower than on straight roads. Consequently, we conclude that drivers must concentrate on driving on curved roads, although they have a margin for driving on straight roads.
View full abstract
-
Seiji Hotta, Senya Kiyasu, Sueharu Miyahara
2005 Volume 59 Issue 8 Pages
1219-1223
Published: August 01, 2005
Released on J-STAGE: March 14, 2011
JOURNAL
FREE ACCESS
We developed a browsing and similarity searching method for videos based on cluster analysis. First, videos are segmented into shots by fuzzy clustering of graph spectral methods. Second, the videos are represented as a sequence of symbols by grouping together shots. According to this representation, the directed graph of videos is formed based on the relationship between these symbols. Initial and terminal shots are extracted from the di-rected graph using fuzzy cluster extraction. The shots can be browsed from the initial shots to the terminal ones sequentially. Selected shots are used as a query video on similarity searches. The performance of the proposed method was evaluated using a video dataset from NASA.
View full abstract