ITE Technical Report
Online ISSN : 2424-1970
Print ISSN : 1342-6893
ISSN-L : 1342-6893
Search
Advanced search
OR
Browse
Search
24.39
Displaying 1-11 of 11 articles from this issue
Show all abstracts
    • |<
    • <
    • 1
    • >
    • >|
  • [title in Japanese]
    Article type: Cover
    Pages Cover1-
    Published: June 23, 2000
    Released on J-STAGE: June 23, 2017
    DOIhttps://doi.org/10.11485/itetr.24.39.0_Cover1
    CONFERENCE PROCEEDINGS FREE ACCESS
    Download PDF (13K)
  • [title in Japanese]
    Article type: Index
    Pages Toc1-
    Published: June 23, 2000
    Released on J-STAGE: June 23, 2017
    DOIhttps://doi.org/10.11485/itetr.24.39.0_Toc1
    CONFERENCE PROCEEDINGS FREE ACCESS
    Download PDF (44K)
  • A Detection Method of Face Images by Using the Lip Detection Neural Network and the Skin Distinction Neural Network
    Yasue Mitsukura, Minoru Fukumi, Norio Akamatsu
    Article type: Article
    Session ID: HIR2000-125
    Published: June 23, 2000
    Released on J-STAGE: June 23, 2017
    DOIhttps://doi.org/10.11485/itetr.24.39.0_1
    CONFERENCE PROCEEDINGS FREE ACCESS
    Show abstractHide abstract
    It this paper, we propose a new method to examine whether or not human faces are included in color images by using a lip detection neural network(LDNN) and a skin distinction neural network(SDNN). In conventional methods, if there are the same color as scenes, the domain which is accepted as not only the skin color but any other color can be searched. Howver, first, the lip are detected by the LDNN in the proposed method. Next, SDNN is utilized to distinguish the skin color from the other. The proposed method can obtain relatively high recognition accuracy, since it have the double recognition structure of LDNN and SDNN. Finally, in order to demonstrate the effectiveness of the proposed scheme, computer simulations were performed. First, 100 lip color, 100 skin color and 100 background pictures, which are picture changed into 10×10 pixels, are prepared for training. The validity was verified by testing images containing several faces.
    View full abstract
    Download PDF (1328K)
  • Person Authentication Based on Writing Pressure
    Toshihiro NONAKA, Mami KIKUCHI, Norio AKAMATSU
    Article type: Article
    Session ID: HIR2000-126
    Published: June 23, 2000
    Released on J-STAGE: June 23, 2017
    DOIhttps://doi.org/10.11485/itetr.24.39.0_7
    CONFERENCE PROCEEDINGS FREE ACCESS
    Show abstractHide abstract
    This paper describes an on-line signature verification based on writing pressure which is obtained by an electronic pen with high sensitivity. The supposed system can acquisit pen pressure data without using a tublet under approximately the same conditions as writing letters with an ordinary pen. It result in acquisition of considerably stable informtion. The proposed verification method consists of two processes. In the first process, correspondding strokes of two signatutes are matched by a parameter-based approach and an apparently forged signature is rejected. In the second process, the verification is performed by using a function-based approach at each corresponding region. As a result of the experiments with thirty-one subjects, we have obtained a false rejection rate is equal to a false acceptance rate of 11.1%.
    View full abstract
    Download PDF (682K)
  • A Neural Network Model of Working Memory : Retention of "What" and "Where" Information
    Tetsuto Minami, Toshio Inui
    Article type: Article
    Session ID: HIR2000-127
    Published: June 23, 2000
    Released on J-STAGE: June 23, 2017
    DOIhttps://doi.org/10.11485/itetr.24.39.0_13
    CONFERENCE PROCEEDINGS FREE ACCESS
    Show abstractHide abstract
    Pysiological studies have revealed that prefrontal cortex(PF) plays an important role in working memory. However its mechanism is still unknown. Particularly it is very important whether there are separate regions in PF working memory. Rao et al.(1997) found neurons contributing to both object and spatial working memory in prefrontal cortex. In this study, we could simulate some results of Rao et al.(1997). This suggests a possibility that there is no separate region in PF working memory.
    View full abstract
    Download PDF (751K)
  • Free View Point Object Recognition by Using Neural Network
    Junya Arakaki, Noriko Fukuda, Itaru Nagayama
    Article type: Article
    Session ID: HIR2000-128
    Published: June 23, 2000
    Released on J-STAGE: June 23, 2017
    DOIhttps://doi.org/10.11485/itetr.24.39.0_19
    CONFERENCE PROCEEDINGS FREE ACCESS
    Show abstractHide abstract
    It is very important to evaluate the disaster and traffic situation immediately, for example, in earth quake at urban area and so on, for carrying on effective emergency rescue. If we can realize the cooperation between GIS and taking ground picture by airplane or artificial satellite, more effective assist for the emergeny rescue under real-time processing can be performed. However, moving the viewpoint causes difficulties for accurate object recognition because of the migration of their lookings. In this paper, we show some experimental results of free viewpoint object recognition for variety of automobiles constructed by 3-dimensional CG. Computer simulations of the experiments are also described.
    View full abstract
    Download PDF (712K)
  • Quantification of a motion characteristic and subjective impressionin Okinawan dance using CG
    Takeshi Arakaki, Kiyoshi Hoshino
    Article type: Article
    Session ID: HIR2000-129
    Published: June 23, 2000
    Released on J-STAGE: June 23, 2017
    DOIhttps://doi.org/10.11485/itetr.24.39.0_25
    CONFERENCE PROCEEDINGS FREE ACCESS
    Show abstractHide abstract
    Although a large number of previous studies have been made on discussion about subjective evaluation to dance and motion, little is known about the relation between characteristic of motion and subjective impression. This study was to examine the relation between characteristics of motions and contingency, and a subjective impression quantitatively in CG which realizes Okinawan Kachaasii dance, using principal component analysis and multi regressionanalysis. The present study clarifies the relation between the characteristics and time contingency of motion, and index or key for subjective impression in the Okinawan dance through dancing CG character's evaluaton. Through dancing CG character's evaluation, which helps CG designers to produce impression and atractive contents.
    View full abstract
    Download PDF (723K)
  • A Study on Unconstrained Measurements of Joint Angles of Fingers : Part 2
    Morihiro Onaga, Hiroki Higa, Kiyoshi Hoshino, Ikuo Nakamura
    Article type: Article
    Session ID: HIR2000-130
    Published: June 23, 2000
    Released on J-STAGE: June 23, 2017
    DOIhttps://doi.org/10.11485/itetr.24.39.0_31
    CONFERENCE PROCEEDINGS FREE ACCESS
    Show abstractHide abstract
    This paper reports on the development of a wireless portable apparatus for measuring joint angles of fingers. To measure motions of(Okinawa traditional) dance, a magnetic motion capture system and a data glove are used in our study. However, the data glove has an electric wire to output its detected signals, which causes motions of dancers to be constrained. So, we made the data transmission system for angles of fingers and considered whether it was possible to transmit multichannel data in real time by using it.
    View full abstract
    Download PDF (328K)
  • A study on Control Command Device Using Direct Proportional Control Method for FES System
    Kousuke Doi, Hiroki Higa, Ikuo Nakamura, Nozomu Hoshimiya, Yasunobu Ha ...
    Article type: Article
    Session ID: HIR2000-131
    Published: June 23, 2000
    Released on J-STAGE: June 23, 2017
    DOIhttps://doi.org/10.11485/itetr.24.39.0_35
    CONFERENCE PROCEEDINGS FREE ACCESS
    Show abstractHide abstract
    In this paper, method of control commands using head movement for functional electrical stimulation(FES) system is described. Control commands for FES system are a selection command, an execution command and a proportional control command. For FES system, the proportional control command is very important to restore upper extremities. By using direct proportional control method which is one of proportional control methods, the target tracking experiment was done as follows: the target signal was a sinusoidal wave, and the control signal, which was obtained by means of head movements, was compared with the target one. From the results, it was cleared the head movement in the flexion and extension axis is appropriate to the proportional control command.
    View full abstract
    Download PDF (583K)
  • [title in Japanese]
    Article type: Appendix
    Pages App1-
    Published: June 23, 2000
    Released on J-STAGE: June 23, 2017
    DOIhttps://doi.org/10.11485/itetr.24.39.0_App1
    CONFERENCE PROCEEDINGS FREE ACCESS
    Download PDF (83K)
  • [title in Japanese]
    Article type: Cover
    Pages Cover2-
    Published: June 23, 2000
    Released on J-STAGE: June 23, 2017
    DOIhttps://doi.org/10.11485/itetr.24.39.0_Cover2
    CONFERENCE PROCEEDINGS FREE ACCESS
    Download PDF (63K)
    • |<
    • <
    • 1
    • >
    • >|
feedback
 Top