ITE Technical Report
Online ISSN : 2424-1970
Print ISSN : 1342-6893
ISSN-L : 1342-6893
33.44
Showing 1-17 articles out of 17 articles from the selected issue
  • Type: Cover
    Pages Cover1-
    Published: October 26, 2009
    Released: September 20, 2017
    CONFERENCE PROCEEDINGS FREE ACCESS
    Download PDF (13K)
  • Type: Index
    Pages Toc1-
    Published: October 26, 2009
    Released: September 20, 2017
    CONFERENCE PROCEEDINGS FREE ACCESS
    Download PDF (51K)
  • Yoshimi WATANABE, Tsuyoshi YAMAMOTO
    Type: Article
    Session ID: ME2009-175
    Published: October 26, 2009
    Released: September 20, 2017
    CONFERENCE PROCEEDINGS FREE ACCESS
    As digital musical making environment is getting popular, the demand of automatic score reading system is increasing. Such systems convert digital audio signal into digital score information such as MIDI and XML based musical scores, however, the accuracy of currently available systems is far from practical use. Our study is aiming to improve quality of score reading by using musical theories to intermediate score in MIDI forma produced by conventional systems. In this report, we propose the use of well known constraints in music theory and the procedures to refine machine generated music scores.
    Download PDF (336K)
  • Kazuya KOBAYASHI, Miki HASEYAMA
    Type: Article
    Session ID: ME2009-176
    Published: October 26, 2009
    Released: September 20, 2017
    CONFERENCE PROCEEDINGS FREE ACCESS
    This paper proposes a new calculation method of distance between music pieces based on personal preferences. In the proposed method, in order to utilize musical features for the distance calculation, feature vectors which represent melody, rhythm, and timbre, are firstly calculated from traning data sets. Then, by using the feature vectors, a metric having a general form of the Mahalanobis distance is defined and learned. Specifically, the metric is learned by minimizing a cost function designed so that the cost increases when the distance between dissimilar music pieces is shorter than the distance between similar music pieces. According to the distance based on the metric, the accurate retrieval of similar music can be expected.
    Download PDF (716K)
  • Makoto YAMAMOTO, Miki HASEYAMA
    Type: Article
    Session ID: ME2009-177
    Published: October 26, 2009
    Released: September 20, 2017
    CONFERENCE PROCEEDINGS FREE ACCESS
    A method for accurate scene segmentation based on statistical trend analysis of audiovisual features is proposed. In the proposed method, based on the assumption that audiovisual features in the same broadcast programs include similar trends, their trends are analyzed by using Probabilistic Latent Semantic Analysis (PLSA), the method for statistical trend analysis. Then the proposed method calculates new features representing these trends. By using these new features, degradation of scene segmentation accuracy, which results from the direct use of the features obtained from the audiovisual materials, can be avoided and thereby accurate scene segmentation becomes feasible. Experimental results performed by applying the proposed method to actual broadcast programs are shown to verify the effectiveness of the proposed method.
    Download PDF (726K)
  • Toru KANEKO
    Type: Article
    Session ID: ME2009-178
    Published: October 26, 2009
    Released: September 20, 2017
    CONFERENCE PROCEEDINGS FREE ACCESS
    The author has been engaged in research on image processing for long years since the late 1970s. In early years, works were for applications with line-drawing images, and thereafter efforts have been made with various kinds of images taken by laser-vision sensors, conventional and omni-directional cameras. This report briefly introduces application examples.
    Download PDF (1489K)
  • Fumio KISHINO
    Type: Article
    Session ID: ME2009-179
    Published: October 26, 2009
    Released: September 20, 2017
    CONFERENCE PROCEEDINGS FREE ACCESS
    Ultra realistic communications are expected to realize a new communication method which will connect among different sites. In this situation, it will become more important to communicate with one another via a virtual environment which is generated by virtual reality technique on the computer network. In order to help an operator work various things in virtual space smoothly, we hope to realize much more convenient human interface in virtual space rather than real space. Therefore, we are studying on various methods by which computer can understand human's intention and realize a higher support to various works.
    Download PDF (1000K)
  • Masayuki Nakajima
    Type: Article
    Session ID: ME2009-180
    Published: October 26, 2009
    Released: September 20, 2017
    CONFERENCE PROCEEDINGS FREE ACCESS
    CG, Human Interface, Multimedia, Virtual Reality Technology are improved rapidly these days for many kindls of fields in entertainment like movie, TV and game and Visualization in Engineering, Science and Art etc.. I report current topics in 36^<th> SIGGRAPH2009 conference during 3rd, August through 7th, August held in New Orleans Convention Center, Louisiana, USA.
    Download PDF (1632K)
  • Hiroki Takahashi
    Type: Article
    Session ID: ME2009-181
    Published: October 26, 2009
    Released: September 20, 2017
    CONFERENCE PROCEEDINGS FREE ACCESS
    SIGGRAPH is an international conference related to CG (Computer Graphics) and interactive technology. This annual conference was held from 3rd in August to 7th in August at New Orleans, Louisiana, USA. This article gives brief review of papers presented at SIGGRAPH2008.
    Download PDF (585K)
  • Shinichi SUMIYOSHI, Yuji SAKAMOTO
    Type: Article
    Session ID: ME2009-182
    Published: October 26, 2009
    Released: September 20, 2017
    CONFERENCE PROCEEDINGS FREE ACCESS
    This paper proposes an effective method to synthesize arbitrary viewpoint images for the object with concavo-convex shape by constructing a 3D model from multi-view images. In the proposed method, a field which should be deformed in the 3D model is calculated with Block Space Carving method based on Space Carving method. In addition, the proposed method synthesizes 2D images at the camera positions that captured photographs and acquires robust evaluation objects for the 3D model. The proposed method constructs the 3D model considering concavo-convex shape by deforming the 3D model in the field while comparing 2D images with the photographs. At the end of this paper, the results of the simulation experiments with synthesizing arbitrary viewpoint images show that the proposed method is effective.
    Download PDF (662K)
  • Hiroki IMAMURA
    Type: Article
    Session ID: ME2009-183
    Published: October 26, 2009
    Released: September 20, 2017
    CONFERENCE PROCEEDINGS FREE ACCESS
    Recently, some modeling tools for generation of 3D-GC have been proposed. In these methods, we have to generate 3D models using a 2D input device such as mouse in 2D space projected from 3D space or orthographic views. In this paper, we attempt to construct a 3D-CG modeling tool by a marker which can input position and direction in 3D space, using ARToolKit for Augmented Reality. By this modeling tool, we can generate 3D-CG modes in 3D space directly. Therefore, we expect that we can intuitively generate 3D-CG models comparing with conventional 3D-CG modeling tools.
    Download PDF (1389K)
  • Kyouhei MINATO, Rikio ONAI
    Type: Article
    Session ID: ME2009-184
    Published: October 26, 2009
    Released: September 20, 2017
    CONFERENCE PROCEEDINGS FREE ACCESS
    Haiku is a short poem, but it can be reminded of the scene. A new entertainment can be invented if a computer can represent the scene. This paper reports on prototype system of composite image generation for Haiku. The system processes it as follows. It extracts feature words from the haiku, and searches for images by those words as query on the Web. Then it elects images that suit feature words by the image analysis, and compounds these images. To achieve the system, the technologies of morphological analysis, extracting feature words, clustering, region segmentation and blending are needed.
    Download PDF (623K)
  • Ryota TOKUMOTO, Miki HASEYAMA
    Type: Article
    Session ID: ME2009-185
    Published: October 26, 2009
    Released: September 20, 2017
    CONFERENCE PROCEEDINGS FREE ACCESS
    This paper proposes a visualization method of video retrieval based on perceptual grouping. The perceptual grouping is a perceptual phenomenon which a human perceives figures as unities in eyeshot. We have previously proposed a video retrieval system for providing the videos desired by the users if users do not have specific queries. However, in traditional method, the interface is not considered a past search history. Thus, users cannot distinguish precisely between a similar video and a video provided newly from past search results. And, it becomes difficult to confirm the change of the video search results in a series of flows along the search history. Therefore, the proposed method arranges the videos in the three-dimensional space. Furthermore, we visualize the video retrieval results based on the perceptual grouping. Consequently, the effective visualization of the video retrieval results is discussed.
    Download PDF (623K)
  • Shigeki TAKAHASHI, Takahiro OGAWA, Miki HASEYAMA
    Type: Article
    Session ID: ME2009-186
    Published: October 26, 2009
    Released: September 20, 2017
    CONFERENCE PROCEEDINGS FREE ACCESS
    This paper proposes a new method which improves coding efficiency of distributed video coding (DVC). Before the encoding process of key frames, the proposed method adds missing areas to the key frames and reduces the bit rate of the target video sequence. In the decoder, the proposed method interpolates the missing areas and reconstructs Wyner-Ziv (WZ) frames and successive key frames based on error correction results of the WZ frames. Then, since decoded WZ frames are accurately reconstructed, and interpolation errors of the missing ares are effectively reduced, the proposed method can achieve higher rate-distortion (RD) performance than the traditional DVC. Experimental results show the improvement of the proposed method over the traditional DVC.
    Download PDF (858K)
  • Type: Appendix
    Pages App1-
    Published: October 26, 2009
    Released: September 20, 2017
    CONFERENCE PROCEEDINGS FREE ACCESS
    Download PDF (83K)
  • Type: Appendix
    Pages App2-
    Published: October 26, 2009
    Released: September 20, 2017
    CONFERENCE PROCEEDINGS FREE ACCESS
    Download PDF (83K)
  • Type: Appendix
    Pages App3-
    Published: October 26, 2009
    Released: September 20, 2017
    CONFERENCE PROCEEDINGS FREE ACCESS
    Download PDF (83K)
feedback
Top