ITE Technical Report
Online ISSN : 2424-1970
Print ISSN : 1342-6893
ISSN-L : 1342-6893
Search
Advanced search
OR
Browse
Search
22.9
Displaying 1-15 of 15 articles from this issue
Show all abstracts
    • |<
    • <
    • 1
    • >
    • >|
  • [title in Japanese]
    Article type: Cover
    Pages Cover1-
    Published: February 04, 1998
    Released on J-STAGE: June 23, 2017
    DOIhttps://doi.org/10.11485/itetr.22.9.0_Cover1
    CONFERENCE PROCEEDINGS FREE ACCESS
    Download PDF (18K)
  • [title in Japanese]
    Article type: Index
    Pages Toc1-
    Published: February 04, 1998
    Released on J-STAGE: June 23, 2017
    DOIhttps://doi.org/10.11485/itetr.22.9.0_Toc1
    CONFERENCE PROCEEDINGS FREE ACCESS
    Download PDF (81K)
  • Real Time Gesture Recognition Using Eigenspace from Multi Input Image Sequence
    Takahiro Watanabe, Masahiko Yachida
    Article type: Article
    Pages 1-8
    Published: February 04, 1998
    Released on J-STAGE: June 23, 2017
    DOIhttps://doi.org/10.11485/itetr.22.9.0_1
    CONFERENCE PROCEEDINGS FREE ACCESS
    Show abstractHide abstract
    This paper presents a real time gesture recognition method for interactive systems which can perform an interaction like a human communication. This method recognizes a user's gesture using the eigenspace constituted from multi input image sequences. This eigenspace represents an approximate 3 dimensional information of gesture, so that complicated gestures which may have a self-occlusion and confusion in a single input image can be recognized correctly. Moreover, our method is suitable for obtaining the gesture's degree information, such as speed and magnitude. Using our method, we realize a real time interactive system, the Virtual Conductor System, which can control music played by a computer using gesture recognition results and indicates the usefulness of our method.
    View full abstract
    Download PDF (1028K)
  • An Extraction Method of Road-Networks from Map Images
    Wataru ITONAGA, Noritaka YONEYAMA, Ichiro MATSUDA, Susumu ITOH
    Article type: Article
    Pages 9-14
    Published: February 04, 1998
    Released on J-STAGE: June 23, 2017
    DOIhttps://doi.org/10.11485/itetr.22.9.0_9
    CONFERENCE PROCEEDINGS FREE ACCESS
    Show abstractHide abstract
    Since car-navigation systems recently come into wide use, it becomes necessary to construct more detailed database on road-networks. This paper describes a new scheme which extracts automatically road-networks from map images. First, all of the road-regions are separated from a map image by using a probabilistic relaxation method based on geometric characteristics of road-regions and backgrounds. Then they are thinned and approximated by line segments, in order to extract road-networks composed of nodes and links. In this procedure, distortion in the neighborhood of intersections is reduced, and moreover the nodes are appropriately placed so that each link can fit well the center of the corresponding road.
    View full abstract
    Download PDF (724K)
  • Restoration from multi-frame blurred images based on stochastic image models
    Koji Fujimoto, Kazuhiro Fujita, Yasuo Yoshida
    Article type: Article
    Pages 15-22
    Published: February 04, 1998
    Released on J-STAGE: June 23, 2017
    DOIhttps://doi.org/10.11485/itetr.22.9.0_15
    CONFERENCE PROCEEDINGS FREE ACCESS
    Show abstractHide abstract
    This paper describes an image restoration method from blurred images with a common object. In order to restore a satisfactory image, we need two techniques : the one is to estimate parameters of blurring models and an original image model : the other is to restore an original image using the model parameters. In addition we need to decide the relative position of blurred images. In the case of out-of-focus blur, we estimate the blur parameters using the discrete cosine transform and iteratively restore the image based on Bayes principle. We show the validity of this method by experiments using blur-simulated images and really blurred ones.
    View full abstract
    Download PDF (1201K)
  • Image Analysis Through Iterated Function Systems
    Hiroyuki Honda, Miki Haseyama, Hideo Kitajima
    Article type: Article
    Pages 23-28
    Published: February 04, 1998
    Released on J-STAGE: June 23, 2017
    DOIhttps://doi.org/10.11485/itetr.22.9.0_23
    CONFERENCE PROCEEDINGS FREE ACCESS
    Show abstractHide abstract
    This paper proposes an image analysis through iterated function systems (IFSs). On the IFSs, an image can be represented by few parameters. Therefore, the parameters contain some characteristics of the image. First, we examine some statistical characteristics of the IFS parameters which represent the location of Domain Block. Next, an edge detection using IFSs is shown. And a statistical characteristic of the image obtained by the above IFSs is examined. These results show the availability of this method.
    View full abstract
    Download PDF (803K)
  • A Note of Cut Detection Using Audio Signals : Its Improvement and Results
    Takahiro Usuda, Miki Haseyama, Hideo Kitajima
    Article type: Article
    Pages 29-34
    Published: February 04, 1998
    Released on J-STAGE: June 23, 2017
    DOIhttps://doi.org/10.11485/itetr.22.9.0_29
    CONFERENCE PROCEEDINGS FREE ACCESS
    Show abstractHide abstract
    This paper presents a study of improvement for cut detection of video signals using audio ones. The existent method assists the cut detection effectively by fuzzy c-means clustering of PARCOR coefficients computed from audio signals corresponding to the video ones. However, this method has a problem which is how to select the number of clusters. To solve this problem, this paper proposes the improved clustering method for the PARCOR coefficients computed from audio signals.
    View full abstract
    Download PDF (553K)
  • An Arbitrary Order Implementation of a CORDIC ARMA Lattice Synthesis Filter
    Shin'ichi Shiraishi, Miki Haseyama, Hideo Kitajima
    Article type: Article
    Pages 35-42
    Published: February 04, 1998
    Released on J-STAGE: June 23, 2017
    DOIhttps://doi.org/10.11485/itetr.22.9.0_35
    CONFERENCE PROCEEDINGS FREE ACCESS
    Show abstractHide abstract
    This paper proposes a method which transforms CORDIC ARMA lattice filters for signal analysis into signal synthesis filters in case where their AR orders are larger than the MA orders. By using CORDIC processors, the proposed signal synthesis filter can be effectively implemented without any multipliers. Since the obtained signal synthesis filter consists of dedicated CORDIC processors, it keeps the advantage of the CORDIC ARMA lattice filter, that is a simple structure.
    View full abstract
    Download PDF (870K)
  • Image Morphing by using Thin Plate Spline Transformation and Snake Model
    Aboul Ella Hassanien, Masayuki NAKAJIMA
    Article type: Article
    Pages 43-48
    Published: February 04, 1998
    Released on J-STAGE: June 23, 2017
    DOIhttps://doi.org/10.11485/itetr.22.9.0_43
    CONFERENCE PROCEEDINGS FREE ACCESS
    Show abstractHide abstract
    The interpolation of scattered data is a problem that is appearing in science and engineering. In this paper, we presents a warping algorithm using thin plate spline, a well known scattered data method which has several advantages. It is efficient in time complexity and smoothed interpolated morphed images with only a remarkably small number of feature points specified. It allows each feature point to be mapped to the corresponding feature point in the warped image. Once the image warped to align the positions of feature and their shapes. The in-between images from given two images could be defined by cross dissolving the positions of correspondence features and their shapes and colors. We adopt a semiautomatic algorithm based on ziplock snake model for the establishment of these correspondence points. We also, describe an efficient cross dissolve algorithm to generate the in-between images. Comparison with other two acattered data methods ; radial basis function and elastic body spline are explained.
    View full abstract
    Download PDF (958K)
  • Euclidean Structure from Two Uncalibrated Images : Synthesis of Facial Expressions on Arbitrary Viewpoints
    Katsunori ISONO, Zhengyou Zhang, Shigeru AKAMATSU
    Article type: Article
    Pages 49-54
    Published: February 04, 1998
    Released on J-STAGE: June 23, 2017
    DOIhttps://doi.org/10.11485/itetr.22.9.0_49
    CONFERENCE PROCEEDINGS FREE ACCESS
    Show abstractHide abstract
    The methods for synthesizing facial images with arbitrary expressions on arbitrary viewpoints are applied to a lot of applications such as low bandwidth video conferencing. In this paper, our goal is to reconstruct Euclidean structure of a face with expressions from 2 uncalibrated real images using a knowledge for expression. What we have is the knowledge about the object category (faces in our case). Therefore, the recovered Euclidean structure is not necessarily a precise Euclidean description of that object, but is useful for many applications such as new image synthesis. By using this technique, Euclidean structure with expression was reconstructed and synthesizing new images achieved a fairly good performance.
    View full abstract
    Download PDF (1293K)
  • 3D Video Composition for Image Expression Room
    Jong-II Park, Kei Ohkawa, Seiki Inoue
    Article type: Article
    Pages 55-60
    Published: February 04, 1998
    Released on J-STAGE: June 23, 2017
    DOIhttps://doi.org/10.11485/itetr.22.9.0_55
    CONFERENCE PROCEEDINGS FREE ACCESS
    Show abstractHide abstract
    Aiming at supporting for free and flexible self-expression in communication systems, we are under construction of Image Expression Room (IE Roon). In the room, users can interact with produced images easily since he/she can see himself/herself on a large mirrored screen. This combined with a multimedia database provides users with an efficient way of expressing themselves. In this paper, we present video composition methods for the IE Room. Key techniques include building a 3D virtual scene with real images only, locating objects in the scene, interactive handling of camera position, and adjustment of the virtual scene according to the camera position.
    View full abstract
    Download PDF (897K)
  • Parallel Processing Algorithm of Volume Rendering
    Eiji SATO, Yuji SAKAMOTO
    Article type: Article
    Pages 61-66
    Published: February 04, 1998
    Released on J-STAGE: June 23, 2017
    DOIhttps://doi.org/10.11485/itetr.22.9.0_61
    CONFERENCE PROCEEDINGS FREE ACCESS
    Show abstractHide abstract
    Volume rendering is one method to visualize three-dimensional volume data which are imaged by MRI and X-Ray CT. But because the size of three-dimensional data is large, a lot of time is spent to load data into memory of computer and to rendering calculation. To solve problems mentioned above, a new parallel volume rendering algorithm is proposed. It is possible to distribute three-dimensional data on each parallel processing by the proposed method.
    View full abstract
    Download PDF (606K)
  • Voxel Automata
    Koichi TSUCHIYA, Yuji SAKAMOTO
    Article type: Article
    Pages 67-72
    Published: February 04, 1998
    Released on J-STAGE: June 23, 2017
    DOIhttps://doi.org/10.11485/itetr.22.9.0_67
    CONFERENCE PROCEEDINGS FREE ACCESS
    Show abstractHide abstract
    In methods which deform 3-dimensional data, limited prediction methods, a simulation method that uses the spring model, a method that cuts away objects using masking, etc. are included. We propose a method based on Voxelautomata which based on voxel & cellular automatons with the objective of deforming an object composed of density values using a small number process. The proposed method can directly deform the object by avoiding use of approximation mesh and making mask. The proposed method uses 3-dimensional data and by determining 5 mapping functions performs the deformation of the object. Only 4 mapping functions define the characteritic of deformation in the method.
    View full abstract
    Download PDF (730K)
  • Comprehensibility-based Evaluation of Real-time News Subtitling for Hearing Impaired Persons
    K. Komine, H. Hoshino, H. Isono, T. Uchida, Y. Iwahana, M. Sakakibara
    Article type: Article
    Pages 73-78
    Published: February 04, 1998
    Released on J-STAGE: June 23, 2017
    DOIhttps://doi.org/10.11485/itetr.22.9.0_73
    CONFERENCE PROCEEDINGS FREE ACCESS
    Show abstractHide abstract
    Possibility of real-time subtitling of news programs was considered for people with impaired hearing. Before we try to realize the system, we need to know the effectiveness and preferred format of subtitling. In order to evaluate the comprehensibility of real-time subtitling, subjects with impaired hearing were shown a short news program with subtitles, and their comprehension of its contents was subsequently tested. Results indicated that subjects performed about as well on average after viewing a program with subtitles as people with normal hearing did after viewing a program with sound, and better than after viewing a program with neither, suggesting that real-time subtitling was effective for people with impaired hearing.
    View full abstract
    Download PDF (928K)
  • [title in Japanese]
    Article type: Appendix
    Pages App1-
    Published: February 04, 1998
    Released on J-STAGE: June 23, 2017
    DOIhttps://doi.org/10.11485/itetr.22.9.0_App1
    CONFERENCE PROCEEDINGS FREE ACCESS
    Download PDF (72K)
    • |<
    • <
    • 1
    • >
    • >|
feedback
 Top