The Experts below are selected from a list of 207 Experts worldwide ranked by ideXlab platform

Jean-philippe Domenger - One of the best experts on this subject based on the ideXlab platform.

  • Semi-synthetic Document Image Generation Using Texture Mapping on Scanned 3D Document Shapes
    2013
    Co-Authors: Van Cuong Kieu, Nicholas Journet, Muriel Visani, Rémy Mullot, Jean-philippe Domenger
    Abstract:

    This article presents a method for generating semi-synthetic images of old documents where the pages might be torn (not flat). By using only 2D deformation models, most existing methods give non-realistic synthetic document images. Thus, we propose to use 3D approach for reproducing geometric distortions in real documents. First, a new proposed Texture Coordinate generation technique extracts Texture Coordinates of each vertex in the document shape (mesh) resulting from 3D scanning of a real degraded document. Then, any 2D document image can be overlayed on the mesh by using an existing Texture image mapping method. As a result, many complex real geometric distortions can be integrated in generated synthetic images. These images then can be used for enriching training sets or for performance evaluation. The degradation method here is jointly used with the character degradation model we proposed in [1] to generate the 6000 semi-synthetic degraded images of the music score removal staff line competition of ICDAR 20131.

  • Semi-synthetic Document Image Generation Using Texture Mapping on Scanned 3D Document Shapes
    2013
    Co-Authors: Van Cuong Kieu, Nicholas Journet, Muriel Visani, Jean-philippe Domenger, Rémy Mullot
    Abstract:

    This article presents a method for generating semisynthetic images of old documents where the pages might be torn (not flat). By using only 2D deformation models, most existing methods give non-realistic synthetic document images. Thus, we propose to use 3D approach for reproducing geometric distortions in real documents. First, our new Texture Coordinate generation technique extracts Texture Coordinates of each vertex in the document shape (mesh) resulting from 3D scanning of a real degraded document. Then, any 2D document image can be overlayed on the mesh by using an existing Texture image mapping method. As a result, many complex real geometric distortions can be integrated in generated synthetic images. These images then can be used for enriching training sets or for performance evaluation. Our degradation method here is jointly used with the character degradation model we proposed in [1] to generate the 6000 semi-synthetic degraded images of the music score removal staff line competition of ICDAR 2013

  • ICDAR - Semi-synthetic Document Image Generation Using Texture Mapping on Scanned 3D Document Shapes
    2013 12th International Conference on Document Analysis and Recognition, 2013
    Co-Authors: Van Cuong Kieu, Nicholas Journet, Muriel Visani, Rémy Mullot, Jean-philippe Domenger
    Abstract:

    This article presents a method for generating semi-synthetic images of old documents where the pages might be torn (not flat). By using only 2D deformation models, most existing methods give non-realistic synthetic document images. Thus, we propose to use 3D approach for reproducing geometric distortions in real documents. First, a new proposed Texture Coordinate generation technique extracts Texture Coordinates of each vertex in the document shape (mesh) resulting from 3D scanning of a real degraded document. Then, any 2D document image can be overlayed on the mesh by using an existing Texture image mapping method. As a result, many complex real geometric distortions can be integrated in generated synthetic images. These images then can be used for enriching training sets or for performance evaluation. The degradation method here is jointly used with the character degradation model we proposed in [1] to generate the 6000 semi-synthetic degraded images of the music score removal staff line competition of ICDAR 2013.

Van Cuong Kieu - One of the best experts on this subject based on the ideXlab platform.

  • Semi-synthetic Document Image Generation Using Texture Mapping on Scanned 3D Document Shapes
    2013
    Co-Authors: Van Cuong Kieu, Nicholas Journet, Muriel Visani, Rémy Mullot, Jean-philippe Domenger
    Abstract:

    This article presents a method for generating semi-synthetic images of old documents where the pages might be torn (not flat). By using only 2D deformation models, most existing methods give non-realistic synthetic document images. Thus, we propose to use 3D approach for reproducing geometric distortions in real documents. First, a new proposed Texture Coordinate generation technique extracts Texture Coordinates of each vertex in the document shape (mesh) resulting from 3D scanning of a real degraded document. Then, any 2D document image can be overlayed on the mesh by using an existing Texture image mapping method. As a result, many complex real geometric distortions can be integrated in generated synthetic images. These images then can be used for enriching training sets or for performance evaluation. The degradation method here is jointly used with the character degradation model we proposed in [1] to generate the 6000 semi-synthetic degraded images of the music score removal staff line competition of ICDAR 20131.

  • Semi-synthetic Document Image Generation Using Texture Mapping on Scanned 3D Document Shapes
    2013
    Co-Authors: Van Cuong Kieu, Nicholas Journet, Muriel Visani, Jean-philippe Domenger, Rémy Mullot
    Abstract:

    This article presents a method for generating semisynthetic images of old documents where the pages might be torn (not flat). By using only 2D deformation models, most existing methods give non-realistic synthetic document images. Thus, we propose to use 3D approach for reproducing geometric distortions in real documents. First, our new Texture Coordinate generation technique extracts Texture Coordinates of each vertex in the document shape (mesh) resulting from 3D scanning of a real degraded document. Then, any 2D document image can be overlayed on the mesh by using an existing Texture image mapping method. As a result, many complex real geometric distortions can be integrated in generated synthetic images. These images then can be used for enriching training sets or for performance evaluation. Our degradation method here is jointly used with the character degradation model we proposed in [1] to generate the 6000 semi-synthetic degraded images of the music score removal staff line competition of ICDAR 2013

  • ICDAR - Semi-synthetic Document Image Generation Using Texture Mapping on Scanned 3D Document Shapes
    2013 12th International Conference on Document Analysis and Recognition, 2013
    Co-Authors: Van Cuong Kieu, Nicholas Journet, Muriel Visani, Rémy Mullot, Jean-philippe Domenger
    Abstract:

    This article presents a method for generating semi-synthetic images of old documents where the pages might be torn (not flat). By using only 2D deformation models, most existing methods give non-realistic synthetic document images. Thus, we propose to use 3D approach for reproducing geometric distortions in real documents. First, a new proposed Texture Coordinate generation technique extracts Texture Coordinates of each vertex in the document shape (mesh) resulting from 3D scanning of a real degraded document. Then, any 2D document image can be overlayed on the mesh by using an existing Texture image mapping method. As a result, many complex real geometric distortions can be integrated in generated synthetic images. These images then can be used for enriching training sets or for performance evaluation. The degradation method here is jointly used with the character degradation model we proposed in [1] to generate the 6000 semi-synthetic degraded images of the music score removal staff line competition of ICDAR 2013.

Kwan Heng Lee - One of the best experts on this subject based on the ideXlab platform.

  • An improved mesh simplification method using additional attributes with optimal positioning
    International Journal of Advanced Manufacturing Technology, 2010
    Co-Authors: Han Kyun Choi, Hyun Soo Kim, Kwan Heng Lee
    Abstract:

    The use of highly detailed models is continuously increasing in computer-aided design (CAD) design and computer graphics field as the technology of range scanners advances. Real-time rendering and manipulating applications are also increasing to support applications in various areas such as collaborative design and scientific visualization. Although graphics hardware technology has been improved rapidly, more attributes such as color, material property, Texture Coordinate, and curvature are added to CAD models, and it becomes a challenge to handle and render such heavy models. Consequently, the models with complex mesh need to be approximated to improve the efficiency of rendering and manipulation and to reduce computation time. A considerable amount of work has been done regarding geometry preservation, but relatively little research has been performed to preserve both geometry and additional attributes. We present a feature sensitive simplification method using curvature color as an additional attribute. We also use curvature color filtering and optimal positioning methods after edge collapse to preserve feature more sensitively. Our method is applied to several models, and the performance is demonstrated by comparing it with other methods.

  • Texture Coordinate compression for 3-D mesh models using Texture image rearrangement
    Lecture Notes in Computer Science, 2005
    Co-Authors: Sung-yeol Kim, Young-suk Yoon, Seung-man Kim, Kwan Heng Lee
    Abstract:

    Previous works related to Texture Coordinate coding of the three-dimensional(3-D) mesh models employed the same predictor as the geometry coder. However, discontinuities in the Texture Coordinates cause unreasonable prediction. Especially, discontinuities become more serious for the 3-D mesh model with a non-atlas Texture image. In this paper, we propose a new coding scheme to remove discontinuities in the Texture Coordinates by reallocating Texture segments according to a coding order. Experiment results show that the proposed coding scheme outperforms the MPEG-4 3DMC standard in terms of compression efficiency. The proposed scheme not only overcome the discontinuity problem by regenerating a Texture image, but also improve coding efficiency of Texture Coordinate compression.

  • PCM (1) - Texture Coordinate compression for 3-d mesh models using Texture image rearrangement
    Advances in Multimedia Information Processing - PCM 2005, 2005
    Co-Authors: Sung-yeol Kim, Young-suk Yoon, Seung-man Kim, Kwan Heng Lee
    Abstract:

    Previous works related to Texture Coordinate coding of the three-dimensional(3-D) mesh models employed the same predictor as the geometry coder. However, discontinuities in the Texture Coordinates cause unreasonable prediction. Especially, discontinuities become more serious for the 3-D mesh model with a non-atlas Texture image. In this paper, we propose a new coding scheme to remove discontinuities in the Texture Coordinates by reallocating Texture segments according to a coding order. Experiment results show that the proposed coding scheme outperforms the MPEG-4 3DMC standard in terms of compression efficiency. The proposed scheme not only overcome the discontinuity problem by regenerating a Texture image, but also improve coding efficiency of Texture Coordinate compression.

Rémy Mullot - One of the best experts on this subject based on the ideXlab platform.

  • Semi-synthetic Document Image Generation Using Texture Mapping on Scanned 3D Document Shapes
    2013
    Co-Authors: Van Cuong Kieu, Nicholas Journet, Muriel Visani, Rémy Mullot, Jean-philippe Domenger
    Abstract:

    This article presents a method for generating semi-synthetic images of old documents where the pages might be torn (not flat). By using only 2D deformation models, most existing methods give non-realistic synthetic document images. Thus, we propose to use 3D approach for reproducing geometric distortions in real documents. First, a new proposed Texture Coordinate generation technique extracts Texture Coordinates of each vertex in the document shape (mesh) resulting from 3D scanning of a real degraded document. Then, any 2D document image can be overlayed on the mesh by using an existing Texture image mapping method. As a result, many complex real geometric distortions can be integrated in generated synthetic images. These images then can be used for enriching training sets or for performance evaluation. The degradation method here is jointly used with the character degradation model we proposed in [1] to generate the 6000 semi-synthetic degraded images of the music score removal staff line competition of ICDAR 20131.

  • Semi-synthetic Document Image Generation Using Texture Mapping on Scanned 3D Document Shapes
    2013
    Co-Authors: Van Cuong Kieu, Nicholas Journet, Muriel Visani, Jean-philippe Domenger, Rémy Mullot
    Abstract:

    This article presents a method for generating semisynthetic images of old documents where the pages might be torn (not flat). By using only 2D deformation models, most existing methods give non-realistic synthetic document images. Thus, we propose to use 3D approach for reproducing geometric distortions in real documents. First, our new Texture Coordinate generation technique extracts Texture Coordinates of each vertex in the document shape (mesh) resulting from 3D scanning of a real degraded document. Then, any 2D document image can be overlayed on the mesh by using an existing Texture image mapping method. As a result, many complex real geometric distortions can be integrated in generated synthetic images. These images then can be used for enriching training sets or for performance evaluation. Our degradation method here is jointly used with the character degradation model we proposed in [1] to generate the 6000 semi-synthetic degraded images of the music score removal staff line competition of ICDAR 2013

  • ICDAR - Semi-synthetic Document Image Generation Using Texture Mapping on Scanned 3D Document Shapes
    2013 12th International Conference on Document Analysis and Recognition, 2013
    Co-Authors: Van Cuong Kieu, Nicholas Journet, Muriel Visani, Rémy Mullot, Jean-philippe Domenger
    Abstract:

    This article presents a method for generating semi-synthetic images of old documents where the pages might be torn (not flat). By using only 2D deformation models, most existing methods give non-realistic synthetic document images. Thus, we propose to use 3D approach for reproducing geometric distortions in real documents. First, a new proposed Texture Coordinate generation technique extracts Texture Coordinates of each vertex in the document shape (mesh) resulting from 3D scanning of a real degraded document. Then, any 2D document image can be overlayed on the mesh by using an existing Texture image mapping method. As a result, many complex real geometric distortions can be integrated in generated synthetic images. These images then can be used for enriching training sets or for performance evaluation. The degradation method here is jointly used with the character degradation model we proposed in [1] to generate the 6000 semi-synthetic degraded images of the music score removal staff line competition of ICDAR 2013.

John Hart - One of the best experts on this subject based on the ideXlab platform.

  • Meshed atlases for real-time procedural solid texturing
    ACM Transactions on Graphics, 2002
    Co-Authors: Nathan A. Carr, John Hart
    Abstract:

    We describe an implementation of procedural solid texturing that uses the Texture atlas, a one-to-one mapping from an object's surface into its Texture space. The method uses the graphics hardware to rasterize the solid Texture Coordinates as colors directly into the atlas. A texturing procedure is applied per-pixel to the Texture map, replacing each solid Texture Coordinate with its corresponding procedural solid Texture result. The procedural solid Texture is then mapped back onto the object surface using standard Texture mapping. The implementation renders procedural solid Textures in real time, and the user can design them interactively.The quality of this technique depends greatly on the layout of the Texture atlas. A broad survey of Texture atlas schemes is used to develop a set of general purpose mesh atlases and tools for measuring their effectiveness at distributing as many available Texture samples as evenly across the surface as possible. The main contribution of this paper is a new multiresolution Texture atlas. It distributes all available Texture samples in a nearly uniform distribution. This multiresolution Texture atlas also supports MIP-mapped minification antialiasing and linear magnification filtering.

  • Bit width necessary for solid texturing hardware
    1999
    Co-Authors: Masaki Kameya, John Hart
    Abstract:

    The effects of the Texture Coordinate precision to the image for procedural Texture mapping is presented. In our project, we are trying to implement procedural solid Texture mapping by hardware. By reducing the number of parameters for our Texture mapping model and precision of Texture Coordinate, we can implement procedural Texture mapping with small number of gates. We checked that how many bits were required to produce the image without degrading original by simulation and confirmed that we could have good Textured image even with small number of bit width.