Scientific Program

Conference Series Ltd invites all the participants across the globe to attend 4th International Conference and Expo on Computer Graphics & Animation Berlin, Germany.

Day 2 :

Keynote Forum

Michela Spagnuolo

Research Director, CNR-IMATI-Genova, Italy

Keynote: The role of similarity in the study of fractured artefacts in Cultural Heritage
Conference Series Computer Graphics 2017 International Conference Keynote Speaker Michela Spagnuolo photo
Biography:

Michela Spagnuolo is Research Director at CNR-IMATI-GE, where she has been working since 11/07/2001. Her research interest include geometric and semantic modelling of 3D objects, approaches based on computational topology for the analysis of shapes, method for the evaluation of similarity at the structural and semantic level. On these research topics, she has co-supervised 6 PhD thesis (plus two ongoing) and several Laurea/Master degree thesis.
She authored more than 130 reviewed papers in scientific journals and international conferences, is associate editor of international journals in Computer Graphics (currently, The Visual Computer and Computers & Graphics). She actively works as chair of conferences and workshops, and she is member of the steering committee of Shape Modeling International and of the EG Workshops on 3D Object Retrieval. In 2014, she was nominated Fellow of the Eurographics Association.

Since 2005, she is responsible of the research unit of the CNR-IMATI identified as ICT.P10.009 Advanced techniques for the analysis and synthesis of 3D shapes; since 2007, she is also responsible of the research unit identified as INT.P02.008 / Modelling and analysis, tools of high-performance computing and grid computing for data and applications in bioinformatics, Interdept. Project on Bioinformatics (now within the CNR Flagship Project Interomics).
She has been working as scientific responsible fof several international and national projects.

Abstract:

Digital manipulation and analysis of tangible cultural objects has the potential to bring about a revolution in the way classification, stylistic analysis, or refitting of fragments is handled in the cultural heritage area. Similarity evaluation is underlying most of these challenges, as the ability to reason on the several and diverse artifact properties, which may relate to geometric attributes (e.g., spatial extent, aspect), to colorimetric properties (e.g., colour, texture), to specific traits that fragments exhibit (e.g., decorations), or to metadata documenting the artefacts. 3D modelling, processing and analysis are now mature enough to allow handling 3D digitized objects as if they were physical, and semantic models allow for a rich documentation of many different aspects of artefacts or assets of any complexity, as well as of contextual information about them. In this context, the talk will give an overview of issues and trends related to the analysis, presentation and documentation of digital cultural assets, with focus on the research challenges tackled within the EC project GRAVITATE: Re-unification, as the process of discovering parts of the same object held in different collections and evaluate if and how they could fit together; Re-assembly, which consists in digitally recreating an historical artefact by the set of its fragments; Re-association of objects, which allows researchers to look for new understanding and insights into the movement and links between different communities on the basis of similar artefacts found in different locations.

Keynote Forum

Yonghuai Liu

Senior Lecturer, Aberystwyth University, UK

Keynote: 3D shape matching for object modelling

Time : 10:00-10:35

Conference Series Computer Graphics 2017 International Conference Keynote Speaker Yonghuai Liu photo
Biography:

Yonghuai Liu is Senior Lecturer in Aberystwyth University. He completed his PhD (1993-1997) and PhD (1997-2000) respectively from Northwestern Polytechnical University, P. R. China and The University of Hull, UK.  In 1997, during his PhD, he received an Overseas Research Students (ORS) award.  He also Editorial board member of American Journal of Educational Research published by Science and Education: an open access and academic publisher from 2015 and associate editor in several journals. His research interests computer graphics, pattern recognition, visualization, robotics & automation, 3D imaging, analysis and its applications.

Abstract:

3D data can be easily captured nowadays using the latest laser scanners such as Microsoft Kinect. Since the scanners have limited field of view and one part of an object may occlude another, the captured data can only cover part of the object of interest and is usually described in the local scanner centred coordinate system. This means that multiple datasets have to be captured from different viewpoints. In order to fuse information in these datasets, they have to be registered into the same coordinate system for such applications as object modelling and animation. The purpose of scan registration is to estimate an underlying transformation so that one scan can be brought into the best possible alignment with another. To this end, various techniques have been proposed, in which the feature extraction and matching (FEM) is promising due to its wide applicability to different datasets subject to different sizes of overlap,  geometry, transformation, imaging noise, and clutters.  In this case, the established point matches usually include a large proportion of false ones.

3D data can be easily captured nowadays using the latest laser scanners such as Microsoft Kinect. Since the scanners have limited field of view and one part of an object may occlude another, the captured data can only cover part of the object of interest and is usually described in the local scanner centred coordinate system. This means that multiple datasets have to be captured from different viewpoints. In order to fuse information in these datasets, they have to be registered into the same coordinate system for such applications as object modelling and animation. The purpose of scan registration is to estimate an underlying transformation so that one scan can be brought into the best possible alignment with another. To this end, various techniques have been proposed, in which the feature extraction and matching (FEM) is promising due to its wide applicability to different datasets subject to different sizes of overlap,  geometry, transformation, imaging noise, and clutters.  In this case, the established point matches usually include a large proportion of false ones.

This talk will focus on how to estimate the reliability of such point matches from which the best possible underlying transformation will be estimated. To this end, I will first show some example 3D data captured by different scanners, from which some issues can be identified that the registration of multiple scans is challenging. Then I will review the main techniques in the literature. Inspired by the AdaBoost learning techniques, various novel algorithms will be proposed,  discussed and reviewed. These techniques are mainly based on the real and gentle AdaBoost respectively and include several steps: weight initialization, underlying transformation estimation in the weighted least squares sense, estimation of the average and variance of the errors of all the point matches, error normalization, and weight update and learning. Such steps are iterated until either the average error is small enough or the maximum number of iterations has been reached. Finally, the underlying transformation is re-estimated in the weighted least squares sense using the weights estimated.

I will thirdly validate the proposed algorithms using various datasets captured using Minolta Vivid 700, Technical Arts 100X, and Microsoft Kinect and show the experimental results. To show the robustness of the proposed techniques different FEM methods will also be considered for the establishment of the potential point matches: signature of histograms of orientations (SHOT) and unique shape context (USC), for example. Finally, I will conclude the talk and indicate some future work.I will thirdly validate the proposed algorithms using various datasets captured using Minolta Vivid 700, Technical Arts 100X, and Microsoft Kinect and show the experimental results. To show the robustness of the proposed techniques different FEM methods will also be considered for the establishment of the potential point matches: signature of histograms of orientations (SHOT) and unique shape context (USC), for example. Finally, I will conclude the talk and indicate some future work.

Keynote Forum

J. Joshua Thomas

Senior Lecturer, KDU Penang University College, Malaysia

Keynote: Visual analytics solution for scheduling processing phases
Conference Series Computer Graphics 2017 International Conference Keynote Speaker J. Joshua Thomas photo
Biography:

J. Joshua Thomas is a senior lecturer at KDU Penang University College, Malaysia since 2008. He started in April 2002 as a lecturer at the same university college. He obtained his PhD (Intelligent Systems) in 2015 from University Sains Malaysia, Penang, and Master’s degree in 1999 from Madurai Kamaraj University, India. From July to September 2005, he worked as a research assistant at the Artificial Intelligence Lab in University Sains Malaysia. From March 2008 to March 2010, he worked as a research associate at the same University.  He is currently associate editor for the international journal: Intelligent Information Processing, an editorial board member for the Journal of Energy Optimization and Engineering (IJEOE), and invited guest editor for Journal of Visual Languages Communication (JVLC-Elsevier), Journal of Healthcare Engineering (JHE), and Information Visualization (SAGE). He is serving as a Special Session Chair (Optimization in Smart Data and Visualization) at the International Conference COMPSE2017 Thailand, and Workshop presenter at IVIC2017, Bangi Malaysia. He has invited as guest speaker for the public lecturers at SQL Saturday Malaysia 2015 and 2016 a training event for Microsoft Data Platform professionals and those wanting to learn about SQL Server, Business Intelligence and Analytics. He has been serving as programme committee member, external examiner, and referee for more than five international conferences. He has published more than 30 papers in leading international conference proceedings and peer reviewed journals.

Abstract:

Introducing Examviz, a novel tool designed for visualizing examination schedules and clashes at the initial level. Examviz uses a metaphor to visual analytics process (VAP) typically processed computationally with local search algorithm then visualized and interpreted by the user in order to perform problem solving with direct interactions between the primary data, processing and visualization. An integrated problem solving environment (PSE) that analyses the combined effect of user-driven steering with automatic tuning of algorithmic parameters based on constraintsand the criticality of the application for the simulations is proposed. It is important to allow the human timetabler to steer the ongoing simulation, especially in the case of critical clashes between conflicting courses to exams and to time slots. An integrated visual design Examvizwhich is based on the parallel coordinate’s style of visualization that uses a novel mapping of courses to exams and to time slots has been developed. Examviz has three processing phases which combines human factors and the algorithm to explore conflicting data through visualization particularly to provide incremental improvements over the solution.