All issues
Predecessor
26.23
Displaying 1-11 of 11 articles from this issue
- |<
- <
- 1
- >
- >|
-
Article type: Cover
Pages Cover1-
Published: March 04, 2002
Released on J-STAGE: June 23, 2017
CONFERENCE PROCEEDINGS FREE ACCESSDownload PDF (13K) -
Article type: Index
Pages Toc1-
Published: March 04, 2002
Released on J-STAGE: June 23, 2017
CONFERENCE PROCEEDINGS FREE ACCESSDownload PDF (38K) -
Akinori TAGUCI, Terumasa AOKI, Hiroshi YASUDAArticle type: Article
Session ID: MIP2002-80
Published: March 04, 2002
Released on J-STAGE: June 23, 2017
CONFERENCE PROCEEDINGS FREE ACCESSMany people would like to enjoy fashions and to buy fashionable clothes. But actually they cannot. With the variety of fashion, there are many choices. But we cannot get all information of fashion when we take it. In general, when we take clothes, we cannot try on all clothes in a shop. This is because most of us hate trying on many clothes, a service of shop assistant and wasteful time of changing other clothes. Also when we will order new clothes in order-made shop, we should image a production and ourselves who are trying it on. In this paper, we propose Digital-Mirror system. This system is a kind of mirror and it enables to create images of trying on clothes we want without trying it on actually. Using this system, people can enjoy fashions more than current shopping.View full abstractDownload PDF (864K) -
Takuya Kodama, Motoki UCHIMURA, Masaki SUZUKI, Jinhui CHAOArticle type: Article
Session ID: MIP2002-81
Published: March 04, 2002
Released on J-STAGE: June 23, 2017
CONFERENCE PROCEEDINGS FREE ACCESSThis paper first presents robust algorithms to extract invariants of the lineai Lie algebra model from 3D objects. In paticular, an extended 3D Hough transform is presented to extract accuate estimates of the normal vectors.The Least square fitting is used to find normal vectors and representation matrices.Then an algorithm of segmentation for 3D objects is shown using the invariants of the linear Lie algebra. Distributions of invariants, both in the invariant space and on the object surface ,are ued for clustering and edge detection.View full abstractDownload PDF (579K) -
Kaori HASHIMOTO, Satoshi SAKUMA, Hiroyuki ARAI, Yasuko TAKAHASHIArticle type: Article
Session ID: MIP2002-83
Published: March 04, 2002
Released on J-STAGE: June 23, 2017
CONFERENCE PROCEEDINGS FREE ACCESSWe propose a high-speed structure and texture acquisition system for creating 3D spaces for Internet services such as digital cities. These spaces should offer high resolution (such that signs can be read) and be easy to construct. This system mounts two line scan cameras linked by a rotary encoder on a moving platform, such as a car, to acquire high-resolution stereo images at relatively high speed. Subsequent computer processing yields shapes representing the structures on to which the high-resolution images are pasted. A preliminary indoor experiment using scale buildings confirms the excellent ability of this system.View full abstractDownload PDF (1004K) -
Motoki UCHIMURA, [in Japanese], Susumu SHIOTA, Masaki SUZUKI, Jinhui C ...Article type: Article
Session ID: MIP2002-84
Published: March 04, 2002
Released on J-STAGE: June 23, 2017
CONFERENCE PROCEEDINGS FREE ACCESS3D object models using linear Lie algebra are known that they can determine a shape uniquely with several invariants and have enough representation. Because these models represent surface of shape as integral curves of group using Lie algebra, it is important to inhibit integral error in order to generate high precise shapes. This paper propose the shape generation algorithm considered curvature and possible to inhibit error. Also, it try to shorten the integral process per integral curves and reduce accumulated error using integral surfaces generated by parallel operation of multiple integral curves.View full abstractDownload PDF (521K) -
Takanori YABE, Ken-ichi TANAKAArticle type: Article
Session ID: MIP2002-85
Published: March 04, 2002
Released on J-STAGE: June 23, 2017
CONFERENCE PROCEEDINGS FREE ACCESSSeveral investigations were reported as inverse halftoning. In previous inverse halftoning methods, noise reduction and emphasis of the reconstructed images are not sufficient. In this article, we propose new methods that combination of the previous inverse halftoning method and Kalman filter. Effectiveness of the proposed methods on image reconstruction is cleared. Image reconstruction of the gray scale image with proposed method is superior compared with previous methods, from binary image by halftoning methods, namely, dither methods and error diffusion in general.View full abstractDownload PDF (768K) -
Mitsuhiro Sato, Madoka Hasegawa, Shigeo KatoArticle type: Article
Session ID: MIP2002-86
Published: March 04, 2002
Released on J-STAGE: June 23, 2017
CONFERENCE PROCEEDINGS FREE ACCESSConstrained average method is one of dither methods which combines edge emphasis and grayscale rendition to provide legibility of textual region and proper quality of continuous tone region. However, image quality of continuous tone region is insufficient than other dither methods, such as ordered dither method or error diffusion method. Constrained average method uses a uniform distribution to decide number of lit pixels related to the average intensity in a picture area. However, actual distribution of continuous tone region is closer to Laplacian distribution or triangle distribution. In this paper, we introduce various probability distributions and actual luminance distribution to constrained average method in order to improve image quality of dithered image.View full abstractDownload PDF (801K) -
Yoichi SATOArticle type: Article
Session ID: MIP2002-87
Published: March 04, 2002
Released on J-STAGE: June 23, 2017
CONFERENCE PROCEEDINGS FREE ACCESSIn this talk, I present a conference report on 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition that was held for three days from December 11, 2001 at Kauai Island, Hawaii. Over 900 papers were submitted for this conference. Among those submitted papers, 78 were accepted for oral presentations, and 195 were accepted for poster presentations. I briefly introduce some of the representative papers, and talk about our paper on illumination estimation based on shadows presented at this conference.View full abstractDownload PDF (98K) -
Article type: Appendix
Pages App1-
Published: March 04, 2002
Released on J-STAGE: June 23, 2017
CONFERENCE PROCEEDINGS FREE ACCESSDownload PDF (75K) -
Article type: Appendix
Pages App2-
Published: March 04, 2002
Released on J-STAGE: June 23, 2017
CONFERENCE PROCEEDINGS FREE ACCESSDownload PDF (75K)
- |<
- <
- 1
- >
- >|