The Experts below are selected from a list of 225 Experts worldwide ranked by ideXlab platform
Ryoji Fukuda - One of the best experts on this subject based on the ideXlab platform.
-
ICCHP - Graphic editor for visually impaired users
Lecture Notes in Computer Science, 2006Co-Authors: Atsushi Nishi, Ryoji FukudaAbstract:Additional adequate Graphical contents are very effective in various communications. The same is clearly true of information given by a visually impaired person. The main purpose of our system is to create Graphical contents without any visual information. The targets are fundamental mathematical graphic Objects. Making use of a tactile pin display and ultrasonic pen, users input Graphical Object hearing several audio assists
-
graphic editor for visually impaired users
Lecture Notes in Computer Science, 2006Co-Authors: Atsushi Nishi, Ryoji FukudaAbstract:Additional adequate Graphical contents are very effective in various communications. The same is clearly true of information given by a visually impaired person. The main purpose of our system is to create Graphical contents without any visual information. The targets are fundamental mathematical graphic Objects. Making use of a tactile pin display and ultrasonic pen, users input Graphical Object hearing several audio assists.
Adrian G. Bors - One of the best experts on this subject based on the ideXlab platform.
-
Steganalysis of 3D Objects Using Statistics of Local Feature Sets
Information Sciences, 2017Co-Authors: Adrian G. BorsAbstract:Abstract 3D steganalysis aims to identify subtle invisible changes produced in Graphical Objects through digital watermarking or steganography. Sets of statistical representations of 3D features, extracted from both cover and stego 3D mesh Objects, are used as inputs into machine learning classifiers in order to decide whether any information was hidden in the given Graphical Object. The features proposed in this paper include those representing the local Object curvature, vertex normals, the local geometry representation in the spherical coordinate system. The effectiveness of these features is tested in various combinations with other features used for 3D steganalysis. The relevance of each feature for 3D steganalysis is assessed using the Pearson correlation coefficient. Six different 3D watermarking and steganographic methods are used for creating the stego-Objects used in the evaluation study.
-
Watermarking mesh-based representations of 3-D Objects using local moments
IEEE transactions on image processing : a publication of the IEEE Signal Processing Society, 2006Co-Authors: Adrian G. BorsAbstract:A new methodology for fingerprinting and watermarking three-dimensional (3-D) Graphical Objects is proposed in this paper. The 3-D Graphical Objects are described by means of polygonal meshes. The information to be embedded is provided as a binary code. A watermarking methodology has two stages: embedding and detecting the information that has been embedded in the given media. The information is embedded by means of local geometrical perturbations while maintaining the local connectivity. A neighborhood localized measure is used for selecting appropriate vertices for watermarking. A study is undertaken in order to verify the suitability of this measure for selecting vertices from regions where geometrical perturbations are less perceptible. Two different watermarking algorithms, that do not require the original 3-D Graphical Object in the detection stage, are proposed. The two algorithms differ with respect to the type of constraint to be embedded in the local structure: by using parallel planes and bounding ellipsoids, respectively. The information capacity of various 3-D meshes is analyzed when using the proposed 3-D watermarking algorithms. The robustness of the 3-D watermarking algorithms is tested to noise perturbation and to Object cropping.
-
DSP - Watermarking Graphical Objects
2002 14th International Conference on Digital Signal Processing Proceedings. DSP 2002 (Cat. No.02TH8628), 1Co-Authors: T. Harte, Adrian G. BorsAbstract:Watermarking has been used for protecting the copyright information in various data such as audio signals, images and video. Copyright protection of Graphical Objects and models is important for protecting author rights in animation, multimedia, computer-aided design (CAD), virtual reality, medical imaging, etc. Watermarking techniques in 3D Graphical Objects are facing new challenges because of the specific nature of the information available in 3D graphics. In this paper we suggest a blind watermarking algorithm for 3D models and Objects. A string of bits is embedded in the geometrical structure of the Graphical Object by changing the locations of certain vertices. The criterion employed for selecting the vertices ensures a minimal visibility of the distortion in the watermarked Object. The proposed 3D Graphical Object algorithm is applied in various 3D Graphical models including characters and industrial Objects.
-
ICIP (3) - Watermarking 3D models
Proceedings. International Conference on Image Processing, 1Co-Authors: T. Harte, Adrian G. BorsAbstract:Copyright protection of Graphical Objects and models is important for protecting author rights in animation, multimedia, computer-aided design (CAD), virtual reality, medical imaging, etc. We suggest a blind watermarking algorithm for 3D models and Objects. A string of bits, generated according to a key, is embedded in the geometrical structure of the Graphical Object by changing the locations of certain vertices. The criterion to choose these vertices ensures a minimal visibility of the distortions in the watermarked Object. A bit encoding 1 is associated with positioning a vertex inside a volume modelled by the geometry of its neighbourhood, while a bit encoding 0 positions the vertex outside such a volume. The proposed watermarking algorithm is applied on various 3D models.
Atsushi Nishi - One of the best experts on this subject based on the ideXlab platform.
-
ICCHP - Graphic editor for visually impaired users
Lecture Notes in Computer Science, 2006Co-Authors: Atsushi Nishi, Ryoji FukudaAbstract:Additional adequate Graphical contents are very effective in various communications. The same is clearly true of information given by a visually impaired person. The main purpose of our system is to create Graphical contents without any visual information. The targets are fundamental mathematical graphic Objects. Making use of a tactile pin display and ultrasonic pen, users input Graphical Object hearing several audio assists
-
graphic editor for visually impaired users
Lecture Notes in Computer Science, 2006Co-Authors: Atsushi Nishi, Ryoji FukudaAbstract:Additional adequate Graphical contents are very effective in various communications. The same is clearly true of information given by a visually impaired person. The main purpose of our system is to create Graphical contents without any visual information. The targets are fundamental mathematical graphic Objects. Making use of a tactile pin display and ultrasonic pen, users input Graphical Object hearing several audio assists.
Tae Support Office - One of the best experts on this subject based on the ideXlab platform.
-
TAE+ 5.2 - TRANSPORTABLE APPLICATIONS ENVIRONMENT PLUS, VERSION 5.2 (SILICON GRAPHICS VERSION)
1994Co-Authors: Tae Support OfficeAbstract:TAE (Transportable Applications Environment) Plus is an integrated, portable environment for developing and running interactive window, text, and Graphical Object-based application systems. The program allows both programmers and non-programmers to easily construct their own custom application interface and to move that interface and application to different machine environments. TAE Plus makes both the application and the machine environment transparent, with noticeable improvements in the learning curve. The main components of TAE Plus are as follows: (1) the WorkBench, a What You See Is What You Get (WYSIWYG) tool for the design and layout of a user interface; (2) the Window Programming Tools Package (WPT), a set of callable subroutines that control an application's user interface; and (3) TAE Command Language (TCL), an easy-to-learn command language that provides an easy way to develop an executable application prototype with a run-time interpreted language. The WorkBench tool allows the application developer to interactively construct the layout of an application's display screen by manipulating a set of interaction Objects including input items such as buttons, icons, and scrolling text lists. User interface interactive Objects include data-driven Graphical Objects such as dials, thermometers, and strip charts as well as menubars, option menus, file selection items, message items, push buttons, and color loggers. The WorkBench user specifies the windows and interaction Objects that will make up the user interface, then specifies the sequence of the user interface dialogue. The description of the designed user interface is then saved into resource files. For those who desire to develop the designed user interface into an operational application, the WorkBench tool also generates source code (C, C++, Ada, and TCL) which fully controls the application's user interface through function calls to the WPTs. The WPTs are the runtime services used by application programs to display and control the user interfaces. Since the WPTs access the workbench-generated resource files during each execution, details such as color, font, location, and Object type remain independent from the application code, allowing changes to the user interface without recompiling and relinking. In addition to WPTs, TAE Plus can control interaction of Objects from the interpreted TAE Command Language. TCL provides a means for the more experienced developer to quickly prototype an application's use of TAE Plus interaction Objects and add programming logic without the overhead of compiling or linking. TAE Plus requires MIT's X Window System and the Open Software Foundation's Motif. The HP 9000 Series 700/800 version of TAE 5.2 requires Version 11 Release 5 of the X Window System. All other machine versions of TAE 5.2 require Version 11, Release 4 of the X Window System. The Workbench and WPTs are written in C++ and the remaining code is written in C. TAE Plus is available by license for an unlimited time period. The licensed program product includes the TAE Plus source code and one set of supporting documentation. Additional documentation may be purchased separately at the price indicated below. The amount of disk space required to load the TAE Plus tar format tape is between 35Mb and 67Mb depending on the machine version. The recommended minimum memory is 12Mb. Each TAE Plus platform delivery tape includes pre-built libraries and executable binary code for that particular machine, as well as source code, so users do not have to do an installation. Users wishing to recompile the source will need both a C compiler and either GNU's C++ Version 1.39 or later, or a C++ compiler based on AT&T 2.0 cfront. TAE Plus was developed in 1989 and version 5.2 was released in 1993. TAE Plus 5.2 is available on media suitable for five different machine platforms: (1) IBM RS/6000 series workstations running AIX (.25 inch tape cartridge in UNIX tar format), (2) DEC RISC workstations running ULTRIX (TK50 cartridge in UNIX tar format), (3) HP9000 Series 700/800 computers running HP-UX 9.x and X11/R5 (HP 4mm DDS DAT tape cartridge in UNIX tar format), (4) Sun4 (SPARC) series computers running SunOS (.25 inch tape cartridge in UNIX tar format), and (5) SGI Indigo computers running IRIX (.25 inch IRIS tape cartridge in UNIX tar format). Please contact COSMIC to obtain detailed information about the supported operating system and OSF/Motif releases required for each of these machine versions. An optional Motif Object Code License is available for the Sun4 version of TAE Plus 5.2. Version 5.1 of TAE Plus remains available for DEC VAX computers running VMS, HP9000 Series 300/400 computers running HP-UX, and HP 9000 Series 700/800 computers running HP-UX 8.x and X11/R4. Please contact COSMIC for details on these versions of TAE Plus.
-
TAE+ 5.2 - TRANSPORTABLE APPLICATIONS ENVIRONMENT PLUS, VERSION 5.2 (SUN4 VERSION WITH MOTIF)
1994Co-Authors: Tae Support OfficeAbstract:TAE (Transportable Applications Environment) Plus is an integrated, portable environment for developing and running interactive window, text, and Graphical Object-based application systems. The program allows both programmers and non-programmers to easily construct their own custom application interface and to move that interface and application to different machine environments. TAE Plus makes both the application and the machine environment transparent, with noticeable improvements in the learning curve. The main components of TAE Plus are as follows: (1) the WorkBench, a What You See Is What You Get (WYSIWYG) tool for the design and layout of a user interface; (2) the Window Programming Tools Package (WPT), a set of callable subroutines that control an application's user interface; and (3) TAE Command Language (TCL), an easy-to-learn command language that provides an easy way to develop an executable application prototype with a run-time interpreted language. The WorkBench tool allows the application developer to interactively construct the layout of an application's display screen by manipulating a set of interaction Objects including input items such as buttons, icons, and scrolling text lists. User interface interactive Objects include data-driven Graphical Objects such as dials, thermometers, and strip charts as well as menubars, option menus, file selection items, message items, push buttons, and color loggers. The WorkBench user specifies the windows and interaction Objects that will make up the user interface, then specifies the sequence of the user interface dialogue. The description of the designed user interface is then saved into resource files. For those who desire to develop the designed user interface into an operational application, the WorkBench tool also generates source code (C, C++, Ada, and TCL) which fully controls the application's user interface through function calls to the WPTs. The WPTs are the runtime services used by application programs to display and control the user interfaces. Since the WPTs access the workbench-generated resource files during each execution, details such as color, font, location, and Object type remain independent from the application code, allowing changes to the user interface without recompiling and relinking. In addition to WPTs, TAE Plus can control interaction of Objects from the interpreted TAE Command Language. TCL provides a means for the more experienced developer to quickly prototype an application's use of TAE Plus interaction Objects and add programming logic without the overhead of compiling or linking. TAE Plus requires MIT's X Window System and the Open Software Foundation's Motif. The HP 9000 Series 700/800 version of TAE 5.2 requires Version 11 Release 5 of the X Window System. All other machine versions of TAE 5.2 require Version 11, Release 4 of the X Window System. The Workbench and WPTs are written in C++ and the remaining code is written in C. TAE Plus is available by license for an unlimited time period. The licensed program product includes the TAE Plus source code and one set of supporting documentation. Additional documentation may be purchased separately at the price indicated below. The amount of disk space required to load the TAE Plus tar format tape is between 35Mb and 67Mb depending on the machine version. The recommended minimum memory is 12Mb. Each TAE Plus platform delivery tape includes pre-built libraries and executable binary code for that particular machine, as well as source code, so users do not have to do an installation. Users wishing to recompile the source will need both a C compiler and either GNU's C++ Version 1.39 or later, or a C++ compiler based on AT&T 2.0 cfront. TAE Plus was developed in 1989 and version 5.2 was released in 1993. TAE Plus 5.2 is available on media suitable for five different machine platforms: (1) IBM RS/6000 series workstations running AIX (.25 inch tape cartridge in UNIX tar format), (2) DEC RISC workstations running ULTRIX (TK50 cartridge in UNIX tar format), (3) HP9000 Series 700/800 computers running HP-UX 9.x and X11/R5 (HP 4mm DDS DAT tape cartridge in UNIX tar format), (4) Sun4 (SPARC) series computers running SunOS (.25 inch tape cartridge in UNIX tar format), and (5) SGI Indigo computers running IRIX (.25 inch IRIS tape cartridge in UNIX tar format). Please contact COSMIC to obtain detailed information about the supported operating system and OSF/Motif releases required for each of these machine versions. An optional Motif Object Code License is available for the Sun4 version of TAE Plus 5.2. Version 5.1 of TAE Plus remains available for DEC VAX computers running VMS, HP9000 Series 300/400 computers running HP-UX, and HP 9000 Series 700/800 computers running HP-UX 8.x and X11/R4. Please contact COSMIC for details on these versions of TAE Plus.
-
TAE+ 5.1 - TRANSPORTABLE APPLICATIONS ENVIRONMENT PLUS, VERSION 5.1 (VAX VMS VERSION)
1994Co-Authors: Tae Support OfficeAbstract:TAE (Transportable Applications Environment) Plus is an integrated, portable environment for developing and running interactive window, text, and Graphical Object-based application systems. The program allows both programmers and non-programmers to easily construct their own custom application interface and to move that interface and application to different machine environments. TAE Plus makes both the application and the machine environment transparent, with noticeable improvements in the learning curve. The main components of TAE Plus are as follows: (1) the WorkBench, a What You See Is What You Get (WYSIWYG) tool for the design and layout of a user interface; (2) the Window Programming Tools Package (WPT), a set of callable subroutines that control an application's user interface; and (3) TAE Command Language (TCL), an easy-to-learn command language that provides an easy way to develop an executable application prototype with a run-time interpreted language. The WorkBench tool allows the application developer to interactively construct the layout of an application's display screen by manipulating a set of interaction Objects including input items such as buttons, icons, and scrolling text lists. User interface interactive Objects include data-driven Graphical Objects such as dials, thermometers, and strip charts as well as menubars, option menus, file selection items, message items, push buttons, and color loggers. The WorkBench user specifies the windows and interaction Objects that will make up the user interface, then specifies the sequence of the user interface dialogue. The description of the designed user interface is then saved into resource files. For those who desire to develop the designed user interface into an operational application, the WorkBench tool also generates source code (C, C++, Ada, and TCL) which fully controls the application's user interface through function calls to the WPTs. The WPTs are the runtime services used by application programs to display and control the user interfaces. Since the WPTs access the workbench-generated resource files during each execution, details such as color, font, location, and Object type remain independent from the application code, allowing changes to the user interface without recompiling and relinking. In addition to WPTs, TAE Plus can control interaction of Objects from the interpreted TAE Command Language. TCL provides a means for the more experienced developer to quickly prototype an application's use of TAE Plus interaction Objects and add programming logic without the overhead of compiling or linking. TAE Plus requires MIT's X Window System, Version 11 Release 4, and the Open Software Foundation's Motif. The Workbench and WPTs are written in C++ and the remaining code is written in C. TAE Plus is available by license for an unlimited time period. The licensed program product includes the TAE Plus source code and one set of supporting documentation. Additional documentation may be purchased separately at the price indicated below. The amount of disk space required to load the TAE Plus tar format tape is between 35Mb and 67Mb depending on the machine version. The recommended minimum memory is 12Mb. Each TAE Plus platform delivery tape includes pre-built libraries and executable binary code for that particular machine, as well as source code, so users do not have to do an installation. Users wishing to recompile the source will need both a C compiler and either GNU's C++ Version 1.39 or later, or a C++ compiler based on AT&T 2.0 cfront. TAE Plus was developed in 1989 and version 5.2 was released in 1993. TAE Plus 5.2 is expected to be available on media suitable for seven different machine platforms: 1) DEC VAX computers running VMS (TK50 cartridge in VAX BACKUP format), 2) IBM RS/6000 series workstations running AIX (.25 inch tape cartridge in UNIX tar format), 3) DEC RISC workstations running ULTRIX (TK50 cartridge in UNIX tar format), 4) HP9000 Series 300/400 computers running HP-UX (.25 inch HP-preformatted tape cartridge in UNIX tar format), 5) HP9000 Series 700 computers running HP-UX (HP 4mm DDS DAT tape cartridge in UNIX tar format), 6) Sun4 (SPARC) series computers running SunOS (.25 inch tape cartridge in UNIX tar format), and 7) SGI Indigo computers running IRIX (.25 inch IRIS tape cartridge in UNIX tar format). Please contact COSMIC to obtain detailed information about the supported operating system and OSF/Motif releases required for each of these machine versions. An optional Motif Object Code License is available for the Sun4 version of TAE Plus 5.2.
C. V. Jawahar - One of the best experts on this subject based on the ideXlab platform.
-
Graphical Object Detection in Document Images
arXiv: Computer Vision and Pattern Recognition, 2020Co-Authors: Ranajit Saha, Ajoy Mondal, C. V. JawaharAbstract:Graphical elements: particularly tables and figures contain a visual summary of the most valuable information contained in a document. Therefore, localization of such Graphical Objects in the document images is the initial step to understand the content of such Graphical Objects or document images. In this paper, we present a novel end-to-end trainable deep learning based framework to localize Graphical Objects in the document images called as Graphical Object Detection (GOD). Our framework is data-driven and does not require any heuristics or meta-data to locate Graphical Objects in the document images. The GOD explores the concept of transfer learning and domain adaptation to handle scarcity of labeled training images for Graphical Object detection task in the document images. Performance analysis carried out on the various public benchmark data sets: ICDAR-2013, ICDAR-POD2017,and UNLV shows that our model yields promising results as compared to state-of-the-art techniques.
-
DAS - IIIT-AR-13K: A New Dataset for Graphical Object Detection in Documents
Document Analysis Systems, 2020Co-Authors: Ajoy Mondal, Peter Lipps, C. V. JawaharAbstract:We introduce a new dataset for Graphical Object detection in business documents, more specifically annual reports. This dataset, iiit-ar-13k, is created by manually annotating the bounding boxes of Graphical or page Objects in publicly available annual reports. This dataset contains a total of 13k annotated page images with Objects in five different popular categories—table, figure, natural image, logo, and signature. It is the largest manually annotated dataset for Graphical Object detection. Annual reports created in multiple languages for several years from various companies bring high diversity into this dataset. We benchmark iiit-ar-13k dataset with two state of the art Graphical Object detection techniques using faster r-cnn [20] and mask r-cnn [11] and establish high baselines for further research. Our dataset is highly effective as training data for developing practical solutions for Graphical Object detection in both business documents and technical articles. By training with iiit-ar-13k, we demonstrate the feasibility of a single solution that can report superior performance compared to the equivalent ones trained with a much larger amount of data, for table detection. We hope that our dataset helps in advancing the research for detecting various types of Graphical Objects in business documents (http://cvit.iiit.ac.in/usodi/iiitar13k.php).
-
IIIT-AR-13K: A New Dataset for Graphical Object Detection in Documents
arXiv: Computer Vision and Pattern Recognition, 2020Co-Authors: Ajoy Mondal, Peter Lipps, C. V. JawaharAbstract:We introduce a new dataset for Graphical Object detection in business documents, more specifically annual reports. This dataset, IIIT-AR-13k, is created by manually annotating the bounding boxes of Graphical or page Objects in publicly available annual reports. This dataset contains a total of 13k annotated page images with Objects in five different popular categories - table, figure, natural image, logo, and signature. It is the largest manually annotated dataset for Graphical Object detection. Annual reports created in multiple languages for several years from various companies bring high diversity into this dataset. We benchmark IIIT-AR-13K dataset with two state of the art Graphical Object detection techniques using Faster R-CNN [20] and Mask R-CNN [11] and establish high baselines for further research. Our dataset is highly effective as training data for developing practical solutions for Graphical Object detection in both business documents and technical articles. By training with IIIT-AR-13K, we demonstrate the feasibility of a single solution that can report superior performance compared to the equivalent ones trained with a much larger amount of data, for table detection. We hope that our dataset helps in advancing the research for detecting various types of Graphical Objects in business documents.
-
ICDAR - Graphical Object Detection in Document Images
2019 International Conference on Document Analysis and Recognition (ICDAR), 2019Co-Authors: Ranajit Saha, Ajoy Mondal, C. V. JawaharAbstract:Graphical elements: particularly tables and figures contain a visual summary of the most valuable information contained in a document. Therefore, localization of such Graphical Objects in the document images is the initial step to understand the content of such Graphical Objects or document images. In this paper, we present a novel end-to-end trainable deep learning based framework to localize Graphical Objects in the document images called as Graphical Object Detection ( GOD ). Our framework is data-driven and does not require any heuristics or meta-data to locate Graphical Objects in the document images. The GOD explores the concept of transfer learning and domain adaptation to handle scarcity of labeled training images for Graphical Object detection task in the document images. Performance analysis carried out on the various public benchmark data sets: ICDAR -2013, ICDAR - POD2017 and UNLV shows that our model yields promising results as compared to state-of-the-art techniques.
