A three-dimensional shape database from a large-scale anthropometric survey

Size: px
Start display at page:

Download "A three-dimensional shape database from a large-scale anthropometric survey"

Transcription

1 A three-dimensional shape database from a large-scale anthropometric survey Peng Li, Brian Corner, Jeremy Carson, Steven Paquette US Army Natick Soldier Research Development & Engineering Center, Natick, Massachusetts, USA Abstract: This paper presents an anthropometric database that incorporated both standard body measurements and three-dimensional (3D) scans from US Army Anthropometric Survey (2013). The database provides query abilities based on measurement and 3D shape by example. Keywords: anthropometric database, body shape query, ANSURII 1. Introduction As the use of three-dimensional (3D) scanner has expanded over the past decade, the need for a structured 3D anthropometric database has received increased attention. A number of web based 3D scan viewers [Ressler and Wang 2002] and 3D shape databases [Paquet 2000] have been developed around the Civilian America and European Anthropometry Resource (CAESAR) survey [Robinette et al. 2002]. The World Engineering Anthropometry Resource (WEAR) [ was established to address the need of a comprehensive anthropometry database incorporated 3D data [Mollard et al 2006]. The recently completed US Army Anthropometric Survey (ANSURII) collected 3D surface whole body, head and foot scans from approximately soldiers, in addition to 93 directly measured standard anthropometric measurements [Gordon et al. 2014]. To fully exploit this rich resource, we implemented a 3D shape database that enables users to query ANSURII data using standard anthropometric measurements as well as 3D shapes. The 3D shape database may be queried through a web interface in three categories: 1) query by multiple standard anthropometric measurements, 2) query by an existing shape example (for example, a new scan from a scanning device or an existing scan in the database), and 3) query using a statistically generated shape. The following sections introduce the details of our database implementation. 2. Database contents The database is implemented in MySQL [ and accessible through a web based browser. Data for each subject contains: o demographics (e.g., age, sex, race/ethnicity), o anthropometric measurements, o 3D whole body scan, o torso shape descriptor, o thumbnail image of the 3D body scan The raw 3D scans from ANSURII survey are very dense point cloud (~500k vertices) with some voids. To obtain a clean, uniform, watertight mesh, we applied a surface alignment tool [Hirshberg 2011] to register raw data into a uniform structure. The result was a whole body mesh with a lower polygon count (11k vertices and 22k faces) whose vertices are in full correspondence. Furthermore, to anonymize the scans we replaced the face with a virtual face. Figure 1 shows a raw scan and its template aligned surface. 1

2 Figure 1. A raw scan and its template aligned surface Because much of our work is on the development and evaluation of torso-borne clothing and equipment, we created a separate torso form for each subject in the database. Torsos were extracted from a whole body scan by deleting arm, leg, and head vertices at standard cut points. A Discrete Cosine Transform (DCT) was then applied to quantify torso shape [Li et al. 2012]. The DCT allows us to reconstruct the original surface shape, and partitions size information from each torso form. Values of the DCT are as a torso 3D shape descriptor. With the above stated data in the database, we provide three query mechanisms, as shown in Figure 2. The first is query based on demographic data and standard anthropometric measurements as shown in Figure 3. This query named a filter search, returns body measurements and thumbnail images of subjects who meet the demographic and body measurement criteria. Users may also specify to display those measurements not included in the query form. Since our database is geared toward 3D data, all search results include subjects 3D image as a cue for later shape query. Figure 2. Front page of the database 2

3 Figure 3. Filter search input screen (left) and results displayed (right). The second query is a search by example (Fig. 4). In our current implementation, the query will be on the torso shape descriptor. The user provides an example either from a previous filter search, where a subject was identified based on standard anthropometry and demography, or a mesh from an external source. A neighbourhood count, that is the number of most similar subjects to be returned, is also required. The database returns similar shapes based on their correlation distance to the example subject provided. For a subject that already exists in the database, this query is a simple sorting of a pre-calculated correlation matrix of the torso shape descriptors. If a new scan is submitted, the scan is processed and the shape descriptor computed. The shape descriptor values are then uploaded and the correlation distance between this new shape descriptor to the shapes in the database is calculated on-the-fly. Figure 4. Search by example input (left) and results displayed (right) 3

4 Figure 5.Distribution of variance from Torso PCA The third query form uses a statistically generated shape as an example. The collection of ANSURII torso 3D shape descriptors forms a shape space. We applied principal component analysis (PCA) to this shape space and decomposed the shape variation into a number of principal axes. We selected the first ten principal components for the shape generator. The ten components account for 77% of torso variance (as shown in fig. 5). For each principal component there is a sliding value from -1 to 1 to control its blending weight for the corresponding extreme shapes chosen from the maximum and minimum standard deviation (+/-3 standard deviations) of that principal component. For example figure 6 shows extreme shapes from the second principal component. The top ten most significant principal components provide twenty extreme shapes as constituent shapes for a shape generator. Figure 6. Extreme shapes of PC2 (front and side view) Using an interactive interface, we may blend across the constituent shapes derived from PCA. In this way a user may generate a novel shape and use it to search for similar shapes in the database population. The shape generator is shown in Figure 7 and some search results are shown in Figure 6. The search result page from the statistically produced shape query process may also be filtered through selected anthropometric measurements that are available for the matched shapes in the database. While a search displays subjects ID, thumbnail images and measurements, 3D geometry of each subject is displayed by clicking on the subject ID. Figure 9 shows a 3D whole body surface viewer from the database. The query results that include anthropometric measurements and 3D scans of relevant subjects can be downloaded to users local computer. Since these downloadable scans have uniform, fully corresponded mesh structure, users can easily use them for further shape analysis and modelling tasks. 4

5 Figure 7. PCA generated torso shape viewer. Sliders to manipulate the ten PC axis values within a range of +/- 3 standard deviations are shown on the right. Figure 8. Search results from PCA generated torso shape 5

6 Figure 9. 3D surface viewer 3. Torso shape descriptor detail and shape search method We selected torso 3D shape as our first query candidate because the torso is where most gear is carried, it is a dominant part of a whole body shape the nuance of torso geometry (front and back curves, chest shape, shoulder shape) is not easily captured with linear anthropometric measurements, and the torso is less prone to pose variation during a 3D scanning session. As noted above, for shape-based queries the torso was segmented from whole body scans and parametrised using DCT. The DCT matrix was used in shape matching. The similarity of two shapes is based on cosine distance between two shape descriptors [Li et al. 2012]. Although the shape descriptor has much smaller file size (a 35x35 matrix) than a raw scan, it is still time consuming to do distance calculation for 6000 files. It is also not efficient to implement the distance computation in SQL. Therefore shape search functions were implemented in C language and called through the server side scripting language PHP. When we query shape by subject ID we simply search a pre-calculated correlation matrix. However, for a new uploaded torso shape, the search must conduct a full distance calculation with all stored shape descriptor files, which takes approximately 40 seconds. When a shape is generated from the PCA viewer, it sends weight values w i of ten PCs to the server. On the server side these values are used as PCA parameters to construct a shape descriptor (SD) as shown in following formula [Li et al. 2015]: where λ i is the ith eigenvalue and E i is the ith eigenvector from PCA. Then the distances between SD to stored shape descriptors in the database are calculated and sorted. This is equivalent to an uploaded shape descriptor search. 4. An example query We received a request for female whole body geometry to test the robusticity of software that morphs internal organ models to a given scan. Our goal was to provide enough scans to challenge the software but not too many so the testing could be done in a reasonable amount of time. We began with a PCA of postprocessed 3D adult female scans in the ANSURII database (N=1708). Results from PCA indicated the bulk of the variation, 95%, was accounted for by 10 components. In addition to the mean form, for each of the 10 6

7 components we selected scans at +/- 1 standard deviation and +/- 3 standard deviations. We then submitted each to a search by example query with a neighbourhood of 5 scans. The query resulted in an overall average scan and 24 scans per component (the original example and 5 neighbors for +/- 1 and +/- 3 standard deviations). The total sample for software testing was 241 scans, which represented a very wide range of adult female whole body variation. 5. Conclusion and future work We have developed a 3D shape centred anthropometric database and made 3D whole body scan data searchable in both the standard anthropometric measurement domain and 3D shape domain, based on a 3D torso shape descriptor. We provided an example how the database may be used to select 3D geometry to test body morphing software. The potential of 3D data for product design and evaluation is still at an early stage. Questions about how to use 3D data will continue for a while until an end user has proper tools to deal with 3D data. For example, for a particular product a designer may be more interested in body surface variation other than the torso. We are working on body segmentation, e.g., head, hands, feet, lower and upper limb. Also, we are adding more common-language anatomical descriptors to help non-specialists.. Acknowledgements The database is implemented through a U.S. Army contract with TSE Inc. (contract # W911QY12C0085) References Gordon, C., Blackwell, C., Bradtmiller, B, Parham, J., Barrientos, P, Paquette, S., Corner, B., Carson, J., Venezia, J., Rockwell, B., Mucher, M. and Kristensen, S, Anthropometric Survey of U.S. Army Personnel: Methods and Summary Statistics. Technical Report NATICK/TR-15/007, US Army Soldier Systems Command, Natick Research, Development and Engineering Center Hirshberg, D. A., Loper, M., Rachlin, E., Tsoli, A., Weiss, A., Corner, B., Black, M. J., 2011 Evaluating the automated alignment of 3D human body scans 2nd Int. Conf. on 3D Body Scanning Technologies, Lugano, Switzerland, pp , Oct , Li, P., Corner, B., Paquette, S., Shape description of the human body based on discrete cosine transform, in Advances in Applied Human Modeling and Simulation, CRC Press, Pages Li, P., Corner, B., Paquette, S., Shape analysis of female torso based on discrete cosine transform, (to be published in) International Journal of Clothing Science and Technology, Vol. 27 Iss: 5, Emerald Group Publishing Limited. Mollard, R., Ressler, S., Robinette, K., Database contents, structure, and ontology for WEAR, Proceedings of the 16th Triennial World Conference of the International Ergonomics Association, 2006 Paquet, E., Robinette, K., Rioux, M., Management of three-dimensional and anthropometric databases: Alexandria and Cleopatra, J. Electronic Imaging 01/2000; 9: Ressler,S., Wang, Q., A Web3D Based CAESAR Viewer, CARS 2002 H.U. Lemke, M.W. Vannier; K. Inamura, A.G. Farman, K. Doi & J.H.C. Reiber (Editors), CARS/Springer. Robinette, K., Blackwell, S., Daanen, H., Boehmer, M., Fleming, S., Brill, T., Hoeferlin, D., Burnsides, D., 2002, Civilian American and European Surface Anthropometry Resource (CAESAR) Final Report, Volume I: Summary, Technical Report AFRL-HE-WP-TR , United States Air Force Research Laboratory 7

From 3-D Scans to Design Tools

From 3-D Scans to Design Tools From 3-D Scans to Design Tools Chang SHU* a, Pengcheng XI a, Stefanie WUHRER b a National Research Council, Ottawa, Canada; b Saarland University, Saarbrücken, Germany http://dx.doi.org/10.15221/13.151

More information

Modeling People Wearing Body Armor and Protective Equipment: Applications to Vehicle Design

Modeling People Wearing Body Armor and Protective Equipment: Applications to Vehicle Design Modeling People Wearing Body Armor and Protective Equipment: Applications to Vehicle Design Matthew P. Reed 1, Monica L.H. Jones 1 and Byoung-keon Daniel Park 1 1 University of Michigan, Ann Arbor, MI

More information

A Validation Study of a Kinect Based Body Imaging (KBI) Device System Based on ISO 20685:2010

A Validation Study of a Kinect Based Body Imaging (KBI) Device System Based on ISO 20685:2010 A Validation Study of a Kinect Based Body Imaging (KBI) Device System Based on ISO 20685:2010 Sara BRAGANÇA* 1, Miguel CARVALHO 1, Bugao XU 2, Pedro AREZES 1, Susan ASHDOWN 3 1 University of Minho, Portugal;

More information

3D Shape Representation and Analysis of the Human Body and Ontology for Anthropometric Landmarks

3D Shape Representation and Analysis of the Human Body and Ontology for Anthropometric Landmarks 3D Shape Representation and Analysis of the Human Body and Ontology for Anthropometric Landmarks Afzal Godil National Institute of Standards and Technology, USA WEAR conference, Banff, Canada 2007 Introduction

More information

Database system. Régis Mollard

Database system. Régis Mollard Database system The use of an on-line anthropometric database system for morphotype analysis and sizing system adaptation for different world market apparel sportwear Régis Mollard Paris Descartes University

More information

Accommodation Assessments for Vehicle Occupants using Augmented Reality

Accommodation Assessments for Vehicle Occupants using Augmented Reality Accommodation Assessments for Vehicle Occupants using Augmented Reality Byoung-keon Daniel Park 1 and Matthew P. Reed 1 1 University of Michigan, Ann Arbor, MI 48109, USA keonpark@umich.edu Abstract. This

More information

Dynamic Human Shape Description and Characterization

Dynamic Human Shape Description and Characterization Dynamic Human Shape Description and Characterization Z. Cheng*, S. Mosher, Jeanne Smith H. Cheng, and K. Robinette Infoscitex Corporation, Dayton, Ohio, USA 711 th Human Performance Wing, Air Force Research

More information

Evaluating the Automated Alignment of 3D Human Body Scans

Evaluating the Automated Alignment of 3D Human Body Scans Evaluating the Automated Alignment of 3D Human Body Scans David A. Hirshberg c, Matthew Loper c, Eric Rachlin c, Aggeliki Tsoli a,c, Alexander Weiss a, Brian Corner b, Michael J. Black a,c {david.hirshberg,

More information

Quantitative Evaluation of Human Body Surface Modeling Methodology

Quantitative Evaluation of Human Body Surface Modeling Methodology Quantitative Evaluation of Human Body Surface Modeling Methodology Matthew P. Reed Byoung-Keon Park Biosciences Group University of Michigan Transportation Research Institute February 2017 UMTRI-2017-5

More information

3-D or Not 3D? That Is The Question December 2005

3-D or Not 3D? That Is The Question December 2005 3-D or Not 3D? That Is The Question December 2005 Kathleen M. Robinette, Ph.D. Principal Research Anthropologist Human Effectiveness Directorate Air Force Research Laboratory 3-D or Not 3-D? Did you know?

More information

PCA Based 3D Shape Reconstruction of Human Foot Using Multiple Viewpoint Cameras

PCA Based 3D Shape Reconstruction of Human Foot Using Multiple Viewpoint Cameras PCA Based 3D Shape Reconstruction of Human Foot Using Multiple Viewpoint Cameras Edmée Amstutz 1, Tomoaki Teshima 1, Makoto Kimura 2, Masaaki Mochimaru 2, and Hideo Saito 1 1 Graduate School of Science

More information

Precise and Automatic Anthropometric Measurement Extraction Using Template Registration

Precise and Automatic Anthropometric Measurement Extraction Using Template Registration Precise and Automatic Anthropometric Measurement Extraction Using Template Registration Oliver WASENMÜLLER, Jan C. PETERS, Vladislav GOLYANIK, Didier STRICKER German Research Center for Artificial Intelligence

More information

Applied Ergonomics 44 (2013) 775e784. Contents lists available at SciVerse ScienceDirect. Applied Ergonomics

Applied Ergonomics 44 (2013) 775e784. Contents lists available at SciVerse ScienceDirect. Applied Ergonomics Applied Ergonomics 44 (2013) 775e784 Contents lists available at SciVerse ScienceDirect Applied Ergonomics journal homepage: www.elsevier.com/locate/apergo Head-and-face shape variations of U.S. civilian

More information

Developing and Implementing Parametric Human Body Shape Models in Ergonomics Software

Developing and Implementing Parametric Human Body Shape Models in Ergonomics Software Developing and Implementing Parametric Human Body Shape Models in Ergonomics Software Matthew P. Reed, Ulrich Raschke, Rishi Tirumali, and Matthew B. Parkinson* University of Michigan Transportation Research

More information

Predicting Seated Body Shape from Standing Body Shape

Predicting Seated Body Shape from Standing Body Shape Predicting Seated Body Shape from Standing Body Shape M. P. REED*, B-K. D. PARK, B.D. CORNER University of Michigan Transportation Research Institute US Marine Corps, Marine Expeditionary Rifle Squad -

More information

EXPANDED ACCOMMODATION ANALYSIS AND RAPID PROTOTYPING TECHNIQUE FOR THE DESIGN OF A CREW STATION COCKPIT

EXPANDED ACCOMMODATION ANALYSIS AND RAPID PROTOTYPING TECHNIQUE FOR THE DESIGN OF A CREW STATION COCKPIT ICAS 2002 CONGRESS EXPANDED ACCOMMODATION ANALYSIS AND RAPID PROTOTYPING TECHNIQUE FOR THE DESIGN OF A CREW STATION COCKPIT Edward Winkler 1, Landon Onyebueke 2, and Olusesan Ameye 2. 1 The Boeing Company

More information

Statistical Learning of Human Body through Feature Wireframe

Statistical Learning of Human Body through Feature Wireframe Statistical Learning of Human Body through Feature Wireframe Jida HUANG 1, Tsz-Ho KWOK 2*, Chi ZHOU 1 1 Industrial and Systems Engineering, University at Buffalo, SUNY, Buffalo NY, USA; 2 Mechanical, Industrial

More information

Evaluating Measurement Error of a 3D Movable Body Scanner for Calibration

Evaluating Measurement Error of a 3D Movable Body Scanner for Calibration Evaluating Measurement Error of a 3D Movable Body Scanner for Calibration YU-CHENG LIN Department of Industrial Engingeering and Management Overseas Chinese University No. 100 Chiaokwang Road, 408, Taichung

More information

Body Trunk Shape Estimation from Silhouettes by Using Homologous Human Body Model

Body Trunk Shape Estimation from Silhouettes by Using Homologous Human Body Model Body Trunk Shape Estimation from Silhouettes by Using Homologous Human Body Model Shunta Saito* a, Makiko Kochi b, Masaaki Mochimaru b, Yoshimitsu Aoki a a Keio University, Yokohama, Kanagawa, Japan; b

More information

Three-Dimensional Child Anthropometry for Vehicle Safety Analysis. Matthew P. Reed Sheila M. Ebert-Hamilton Biosciences Group October 2012

Three-Dimensional Child Anthropometry for Vehicle Safety Analysis. Matthew P. Reed Sheila M. Ebert-Hamilton Biosciences Group October 2012 Three-Dimensional Child Anthropometry for Vehicle Safety Analysis Matthew P. Reed Sheila M. Ebert-Hamilton Biosciences Group October 2012 Children in Cars Data on the size, shape, and posture of children

More information

A Model-based Approach to Rapid Estimation of Body Shape and Postures Using Low-Cost Depth Cameras

A Model-based Approach to Rapid Estimation of Body Shape and Postures Using Low-Cost Depth Cameras A Model-based Approach to Rapid Estimation of Body Shape and Postures Using Low-Cost Depth Cameras Abstract Byoung-Keon D. PARK*, Matthew P. REED University of Michigan, Transportation Research Institute,

More information

Creating Custom Human Avatars for Ergonomic Analysis using Depth Cameras

Creating Custom Human Avatars for Ergonomic Analysis using Depth Cameras Creating Custom Human Avatars for Ergonomic Analysis using Depth Cameras Matthew P. Reed, Byoung-Keon Park, K. Han Kim University of Michigan Transportation Research Institute Ulrich Raschke Siemens PLM

More information

Anthropometric Investigation of Head Measurements for Indian Adults

Anthropometric Investigation of Head Measurements for Indian Adults Anthropometric Investigation of Measurements for Indian Adults Parth SHAH 1, Yan LUXIMON* 1, Fang FU 1, Vividh MAKWANA 2 1 School of Design, The Hong Kong Polytechnic University, Hong Kong; 2 Navneet Hi-Tech

More information

Human Body Shape Deformation from. Front and Side Images

Human Body Shape Deformation from. Front and Side Images Human Body Shape Deformation from Front and Side Images Yueh-Ling Lin 1 and Mao-Jiun J. Wang 2 Department of Industrial Engineering and Engineering Management, National Tsing Hua University, Hsinchu, Taiwan

More information

Estimating 3D Human Shapes from Measurements

Estimating 3D Human Shapes from Measurements Estimating 3D Human Shapes from Measurements Stefanie Wuhrer Chang Shu March 19, 2012 arxiv:1109.1175v2 [cs.cv] 16 Mar 2012 Abstract The recent advances in 3-D imaging technologies give rise to databases

More information

Aalborg Universitet. Published in: Procedia Engineering. DOI (link to publication from Publisher): /j.proeng

Aalborg Universitet. Published in: Procedia Engineering. DOI (link to publication from Publisher): /j.proeng Aalborg Universitet 3D anthropometric investigation of head and face characteristics of Australian cyclists Perret-Ellena, Thierry; Skals, Sebastian Laigaard; Subic, Aleksandar; Mustafa, Helmy; Pang, Toh

More information

Shape Map Method for 3D Body Scanning Information Storage

Shape Map Method for 3D Body Scanning Information Storage Shape Map Method for 3D Body Scanning Information Storage Peng SIXIANG* a, Chan CHEE-KOOI a, Ameersing LUXIMON a, W.H. IP b a Institute of Textiles & Clothing, Hong Kong Polytechnic University, Hong Kong,

More information

Face detection and recognition. Many slides adapted from K. Grauman and D. Lowe

Face detection and recognition. Many slides adapted from K. Grauman and D. Lowe Face detection and recognition Many slides adapted from K. Grauman and D. Lowe Face detection and recognition Detection Recognition Sally History Early face recognition systems: based on features and distances

More information

Automatically Creating Design Models from 3D Anthropometry Data

Automatically Creating Design Models from 3D Anthropometry Data Automatically Creating Design Models from 3D Anthropometry Data Stefanie Wuhrer Saarland University Saarbrücken, Germany swuhrer@mmci.uni-saarland.de Chang Shu National Research Council of Canada Ottawa,

More information

Supplemental Material: Detailed, accurate, human shape estimation from clothed 3D scan sequences

Supplemental Material: Detailed, accurate, human shape estimation from clothed 3D scan sequences Supplemental Material: Detailed, accurate, human shape estimation from clothed 3D scan sequences Chao Zhang 1,2, Sergi Pujades 1, Michael Black 1, and Gerard Pons-Moll 1 1 MPI for Intelligent Systems,

More information

Human Shape from Silhouettes using Generative HKS Descriptors and Cross-Modal Neural Networks

Human Shape from Silhouettes using Generative HKS Descriptors and Cross-Modal Neural Networks Human Shape from Silhouettes using Generative HKS Descriptors and Cross-Modal Neural Networks Endri Dibra 1, Himanshu Jain 1, Cengiz Öztireli 1, Remo Ziegler 2, Markus Gross 1 1 Department of Computer

More information

Object Classification Using Tripod Operators

Object Classification Using Tripod Operators Object Classification Using Tripod Operators David Bonanno, Frank Pipitone, G. Charmaine Gilbreath, Kristen Nock, Carlos A. Font, and Chadwick T. Hawley US Naval Research Laboratory, 4555 Overlook Ave.

More information

Measurement of 3D Foot Shape Deformation in Motion

Measurement of 3D Foot Shape Deformation in Motion Measurement of 3D Foot Shape Deformation in Motion Makoto Kimura Masaaki Mochimaru Takeo Kanade Digital Human Research Center National Institute of Advanced Industrial Science and Technology, Japan The

More information

Statistics and Information Technology

Statistics and Information Technology Statistics and Information Technology Werner Stuetzle Professor and Chair, Statistics Adjunct Professor, Computer Science and Engineering University of Washington Prepared for NSF Workshop on Statistics:

More information

Human pose estimation using Active Shape Models

Human pose estimation using Active Shape Models Human pose estimation using Active Shape Models Changhyuk Jang and Keechul Jung Abstract Human pose estimation can be executed using Active Shape Models. The existing techniques for applying to human-body

More information

Simulating Seat Back Interaction Using Realistic Body Contours

Simulating Seat Back Interaction Using Realistic Body Contours Simulating Seat Back Interaction Using Realistic Body Contours Matthew P. Reed Jingwen Hu Biosciences Group Introduction Dimensional mismatch between a seat and sitter can cause discomfort. Traditional

More information

Accurate 3D Face and Body Modeling from a Single Fixed Kinect

Accurate 3D Face and Body Modeling from a Single Fixed Kinect Accurate 3D Face and Body Modeling from a Single Fixed Kinect Ruizhe Wang*, Matthias Hernandez*, Jongmoo Choi, Gérard Medioni Computer Vision Lab, IRIS University of Southern California Abstract In this

More information

CLASSIFICATION FOR ROADSIDE OBJECTS BASED ON SIMULATED LASER SCANNING

CLASSIFICATION FOR ROADSIDE OBJECTS BASED ON SIMULATED LASER SCANNING CLASSIFICATION FOR ROADSIDE OBJECTS BASED ON SIMULATED LASER SCANNING Kenta Fukano 1, and Hiroshi Masuda 2 1) Graduate student, Department of Intelligence Mechanical Engineering, The University of Electro-Communications,

More information

A Survey on Feature Extraction Techniques for Palmprint Identification

A Survey on Feature Extraction Techniques for Palmprint Identification International Journal Of Computational Engineering Research (ijceronline.com) Vol. 03 Issue. 12 A Survey on Feature Extraction Techniques for Palmprint Identification Sincy John 1, Kumudha Raimond 2 1

More information

Training-Free, Generic Object Detection Using Locally Adaptive Regression Kernels

Training-Free, Generic Object Detection Using Locally Adaptive Regression Kernels Training-Free, Generic Object Detection Using Locally Adaptive Regression Kernels IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIENCE, VOL.32, NO.9, SEPTEMBER 2010 Hae Jong Seo, Student Member,

More information

Human Activity Recognition Using Multidimensional Indexing

Human Activity Recognition Using Multidimensional Indexing Human Activity Recognition Using Multidimensional Indexing By J. Ben-Arie, Z. Wang, P. Pandit, S. Rajaram, IEEE PAMI August 2002 H. Ertan Cetingul, 07/20/2006 Abstract Human activity recognition from a

More information

Landmark Detection on 3D Face Scans by Facial Model Registration

Landmark Detection on 3D Face Scans by Facial Model Registration Landmark Detection on 3D Face Scans by Facial Model Registration Tristan Whitmarsh 1, Remco C. Veltkamp 2, Michela Spagnuolo 1 Simone Marini 1, Frank ter Haar 2 1 IMATI-CNR, Genoa, Italy 2 Dept. Computer

More information

Visual Learning and Recognition of 3D Objects from Appearance

Visual Learning and Recognition of 3D Objects from Appearance Visual Learning and Recognition of 3D Objects from Appearance (H. Murase and S. Nayar, "Visual Learning and Recognition of 3D Objects from Appearance", International Journal of Computer Vision, vol. 14,

More information

Motion Texture. Harriet Pashley Advisor: Yanxi Liu Ph.D. Student: James Hays. 1. Introduction

Motion Texture. Harriet Pashley Advisor: Yanxi Liu Ph.D. Student: James Hays. 1. Introduction Motion Texture Harriet Pashley Advisor: Yanxi Liu Ph.D. Student: James Hays 1. Introduction Motion capture data is often used in movies and video games because it is able to realistically depict human

More information

Development of a Methodology for Simulating Seat Back Interaction Using Realistic Body Contours

Development of a Methodology for Simulating Seat Back Interaction Using Realistic Body Contours Development of a Methodology for Simulating Seat Back Interaction Using Realistic Body Contours Jingwen Hu Matthew P. Reed Biosciences Group April 16, 2013 Introduction Dimensional mismatch between a seat

More information

Surface Reconstruction. Gianpaolo Palma

Surface Reconstruction. Gianpaolo Palma Surface Reconstruction Gianpaolo Palma Surface reconstruction Input Point cloud With or without normals Examples: multi-view stereo, union of range scan vertices Range scans Each scan is a triangular mesh

More information

Object and Action Detection from a Single Example

Object and Action Detection from a Single Example Object and Action Detection from a Single Example Peyman Milanfar* EE Department University of California, Santa Cruz *Joint work with Hae Jong Seo AFOSR Program Review, June 4-5, 29 Take a look at this:

More information

Matching and Recognition in 3D. Based on slides by Tom Funkhouser and Misha Kazhdan

Matching and Recognition in 3D. Based on slides by Tom Funkhouser and Misha Kazhdan Matching and Recognition in 3D Based on slides by Tom Funkhouser and Misha Kazhdan From 2D to 3D: Some Things Easier No occlusion (but sometimes missing data instead) Segmenting objects often simpler From

More information

A Tool Kit to Generate 3D Animated CAESAR Bodies

A Tool Kit to Generate 3D Animated CAESAR Bodies 05DHM-10 A Tool Kit to Generate 3D Animated CAESAR Bodies Qiming Wang, Sandy Ressler National Institute of Standards and Technology ABSTRACT The Civilian American and European Surface Anthropometry Resource

More information

A GENERIC FACE REPRESENTATION APPROACH FOR LOCAL APPEARANCE BASED FACE VERIFICATION

A GENERIC FACE REPRESENTATION APPROACH FOR LOCAL APPEARANCE BASED FACE VERIFICATION A GENERIC FACE REPRESENTATION APPROACH FOR LOCAL APPEARANCE BASED FACE VERIFICATION Hazim Kemal Ekenel, Rainer Stiefelhagen Interactive Systems Labs, Universität Karlsruhe (TH) 76131 Karlsruhe, Germany

More information

Int. J. Human Factors Modelling and Simulation, Vol. 3, No. 2,

Int. J. Human Factors Modelling and Simulation, Vol. 3, No. 2, Int. J. Human Factors Modelling and Simulation, Vol. 3, No. 2, 2012 133 3D anthropometric data processing Chang Shu* National Research Council of Canada, 1200 Montreal Road, Ottawa, Ontario, Canada E-mail:

More information

Linear Discriminant Analysis in Ottoman Alphabet Character Recognition

Linear Discriminant Analysis in Ottoman Alphabet Character Recognition Linear Discriminant Analysis in Ottoman Alphabet Character Recognition ZEYNEB KURT, H. IREM TURKMEN, M. ELIF KARSLIGIL Department of Computer Engineering, Yildiz Technical University, 34349 Besiktas /

More information

DETC MODELING VARIABILITY IN TORSO SHAPE FOR CHAIR AND SEAT DESIGN

DETC MODELING VARIABILITY IN TORSO SHAPE FOR CHAIR AND SEAT DESIGN Proceedings of DETC08 ASME International Design Engineering Technical Conferences August 3-6, 2008, New York, NY, USA DETC2008-49483 MODELING VARIABILITY IN TORSO SHAPE FOR CHAIR AND SEAT DESIGN Matthew

More information

Digital Image Processing Chapter 11: Image Description and Representation

Digital Image Processing Chapter 11: Image Description and Representation Digital Image Processing Chapter 11: Image Description and Representation Image Representation and Description? Objective: To represent and describe information embedded in an image in other forms that

More information

Face detection and recognition. Detection Recognition Sally

Face detection and recognition. Detection Recognition Sally Face detection and recognition Detection Recognition Sally Face detection & recognition Viola & Jones detector Available in open CV Face recognition Eigenfaces for face recognition Metric learning identification

More information

3D-based resources fostering the analysis, use, and exploitation of available body anthropometric data

3D-based resources fostering the analysis, use, and exploitation of available body anthropometric data 3D-based resources fostering the analysis, use, and exploitation of available body anthropometric data Alfredo BALLESTER*, Eduardo PARRILLA, Jordi URIEL, Ana PIEROLA, Sandra ALEMANY, Beatriz NACHER, Jorge

More information

Vehicle Dimensions Estimation Scheme Using AAM on Stereoscopic Video

Vehicle Dimensions Estimation Scheme Using AAM on Stereoscopic Video Workshop on Vehicle Retrieval in Surveillance (VRS) in conjunction with 2013 10th IEEE International Conference on Advanced Video and Signal Based Surveillance Vehicle Dimensions Estimation Scheme Using

More information

Paper type Research paper. Algorithms of the Automatic Landmark Identification for Various Torso Shapes

Paper type Research paper. Algorithms of the Automatic Landmark Identification for Various Torso Shapes Algorithms of the Automatic Landmark Identification for Various Torso Shapes Paper type Research paper Hyunsook Han Clothing & Textile Department, Seoul National University, Seoul, Korea. hannhs@hanmail.net

More information

Hand Gesture Extraction by Active Shape Models

Hand Gesture Extraction by Active Shape Models Hand Gesture Extraction by Active Shape Models Nianjun Liu, Brian C. Lovell School of Information Technology and Electrical Engineering The University of Queensland, Brisbane 4072, Australia National ICT

More information

AFRL-RH-WP-TR

AFRL-RH-WP-TR AFRL-RH-WP-TR-2011-0023 Static and Dynamic Human Shape Modeling Concept Formation and Technology Development Zhiqing Cheng Infoscitex Corporation Julia Parakkat Melody Darby Kathleen Robinette Vulnerability

More information

3D Human Models from 1D, 2D & 3D Inputs: Reliability and Compatibility of Body Measurements

3D Human Models from 1D, 2D & 3D Inputs: Reliability and Compatibility of Body Measurements 3D Human Models from 1D, 2D & 3D Inputs: Reliability and Compatibility of Body Measurements Alfredo BALLESTER*, Ana PIÉROLA, Eduardo PARRILLA, Jordi URIEL, Ana V. RUESCAS, Cristina PÉREZ, Juan V. DURÁ,

More information

Defining the Coordinate System of 3D Foot Model Using Regression Analysis

Defining the Coordinate System of 3D Foot Model Using Regression Analysis Defining the Coordinate System of 3D Foot Model Using Regression Analysis Yoitsu TAKAHASHI Hiroki YAHARA Yukio FUKUI Seiichi NISHIHARA Department of Computer Science, University of Tsukuba, Japan Center

More information

DocFinity v10 Basics. Guide to Menus, Workspace and Panels

DocFinity v10 Basics. Guide to Menus, Workspace and Panels DocFinity v10 Basics Guide to Menus, Workspace and Panels Revised 5/20/2013 Table of Contents Access to Images and Application Functions... 3 Groups:... 3 Requests for Access to Additional Image Types

More information

THE BENEFIT OF ANSA TOOLS IN THE DALLARA CFD PROCESS. Simona Invernizzi, Dallara Engineering, Italy,

THE BENEFIT OF ANSA TOOLS IN THE DALLARA CFD PROCESS. Simona Invernizzi, Dallara Engineering, Italy, THE BENEFIT OF ANSA TOOLS IN THE DALLARA CFD PROCESS Simona Invernizzi, Dallara Engineering, Italy, KEYWORDS automatic tools, batch mesh, DFM, morphing, ride height maps ABSTRACT In the last few years,

More information

3-D Model Characterization and Identification from Intrinsic Landmarks

3-D Model Characterization and Identification from Intrinsic Landmarks Wright State University CORE Scholar Browse all Theses and Dissertations Theses and Dissertations 2011 3-D Model Characterization and Identification from Intrinsic Landmarks John L. Camp Wright State University

More information

Hein Daanen Frans Nennie Marc Rioux. 3D anthropometric data collection

Hein Daanen Frans Nennie Marc Rioux. 3D anthropometric data collection Hein Daanen Frans Nennie Marc Rioux 3D anthropometric data collection Contents Why 3D anthropometry 3D body scanning systems History Methods 3D data processing Clothing applications 2 3D scanning compared

More information

Semi-Supervised PCA-based Face Recognition Using Self-Training

Semi-Supervised PCA-based Face Recognition Using Self-Training Semi-Supervised PCA-based Face Recognition Using Self-Training Fabio Roli and Gian Luca Marcialis Dept. of Electrical and Electronic Engineering, University of Cagliari Piazza d Armi, 09123 Cagliari, Italy

More information

Model-Based Face Computation

Model-Based Face Computation Model-Based Face Computation 1. Research Team Project Leader: Post Doc(s): Graduate Students: Prof. Ulrich Neumann, IMSC and Computer Science John P. Lewis Hea-juen Hwang, Zhenyao Mo, Gordon Thomas 2.

More information

Content-based Medical Image Annotation and Retrieval using Perceptual Hashing Algorithm

Content-based Medical Image Annotation and Retrieval using Perceptual Hashing Algorithm Content-based Medical Image and Retrieval using Perceptual Hashing Algorithm Suresh Kumar Nagarajan 1, Shanmugam Saravanan 2 1 Senior Assistant Professor, School of Computing Science and Engineering, VIT

More information

An Automatic Hole Filling Method of Point Cloud for 3D Scanning

An Automatic Hole Filling Method of Point Cloud for 3D Scanning An Automatic Hole Filling Method of Point Cloud for 3D Scanning Yuta MURAKI Osaka Institute of Technology Osaka, Japan yuta.muraki@oit.ac.jp Koji NISHIO Osaka Institute of Technology Osaka, Japan koji.a.nishio@oit.ac.jp

More information

Social Behavior Prediction Through Reality Mining

Social Behavior Prediction Through Reality Mining Social Behavior Prediction Through Reality Mining Charlie Dagli, William Campbell, Clifford Weinstein Human Language Technology Group MIT Lincoln Laboratory This work was sponsored by the DDR&E / RRTO

More information

FEA and Multivariate Statistical Data Analysis of Polypropylene Tube Forming Process

FEA and Multivariate Statistical Data Analysis of Polypropylene Tube Forming Process FEA and Multivariate Statistical Data Analysis of Polypropylene ube Forming Process Galini Gavrilidou, Mukesh Jain Department of Mechanical Engineering, McMaster University, Hamilton, On, LS L7, Canada

More information

A 12-DOF Analytic Inverse Kinematics Solver for Human Motion Control

A 12-DOF Analytic Inverse Kinematics Solver for Human Motion Control Journal of Information & Computational Science 1: 1 (2004) 137 141 Available at http://www.joics.com A 12-DOF Analytic Inverse Kinematics Solver for Human Motion Control Xiaomao Wu, Lizhuang Ma, Zhihua

More information

Footprint Recognition using Modified Sequential Haar Energy Transform (MSHET)

Footprint Recognition using Modified Sequential Haar Energy Transform (MSHET) 47 Footprint Recognition using Modified Sequential Haar Energy Transform (MSHET) V. D. Ambeth Kumar 1 M. Ramakrishnan 2 1 Research scholar in sathyabamauniversity, Chennai, Tamil Nadu- 600 119, India.

More information

Multi-view 3D retrieval using silhouette intersection and multi-scale contour representation

Multi-view 3D retrieval using silhouette intersection and multi-scale contour representation Multi-view 3D retrieval using silhouette intersection and multi-scale contour representation Thibault Napoléon Telecom Paris CNRS UMR 5141 75013 Paris, France napoleon@enst.fr Tomasz Adamek CDVP Dublin

More information

Shape Reconstruction of Human Foot from Multi-camera Images Based on PCA of Human Shape Database

Shape Reconstruction of Human Foot from Multi-camera Images Based on PCA of Human Shape Database Shape Reconstruction of Human Foot from Multi-camera Images Based on PCA of Human Shape Database Jiahui Wang, Hideo Saito Department of Information and Computer Science, Keio University, Japan wjh, saito@ozawa.ics.keio.ac.jp

More information

Application of 2DPCA Based Techniques in DCT Domain for Face Recognition

Application of 2DPCA Based Techniques in DCT Domain for Face Recognition Application of 2DPCA Based Techniques in DCT Domain for Face Recognition essaoud Bengherabi, Lamia ezai, Farid Harizi, Abderraza Guessoum 2, and ohamed Cheriet 3 Centre de Développement des Technologies

More information

Virtual Interaction System Based on Optical Capture

Virtual Interaction System Based on Optical Capture Sensors & Transducers 203 by IFSA http://www.sensorsportal.com Virtual Interaction System Based on Optical Capture Peng CHEN, 2 Xiaoyang ZHOU, 3 Jianguang LI, Peijun WANG School of Mechanical Engineering,

More information

Geometric Registration for Deformable Shapes 1.1 Introduction

Geometric Registration for Deformable Shapes 1.1 Introduction Geometric Registration for Deformable Shapes 1.1 Introduction Overview Data Sources and Applications Problem Statement Overview Presenters Will Chang University of California at San Diego, USA Hao Li ETH

More information

Face Recognition Using Long Haar-like Filters

Face Recognition Using Long Haar-like Filters Face Recognition Using Long Haar-like Filters Y. Higashijima 1, S. Takano 1, and K. Niijima 1 1 Department of Informatics, Kyushu University, Japan. Email: {y-higasi, takano, niijima}@i.kyushu-u.ac.jp

More information

Design of Blue Pottery Working Table for Indian Population Using Taguchi Approach

Design of Blue Pottery Working Table for Indian Population Using Taguchi Approach Proceedings of the 2 nd World Congress on Mechanical, Chemical, and Material Engineering (MCM'16) Budapest, Hungary August 22 23, 2016 Paper No. ICMIE 111 DOI: 10.11159/icmie16.111 Design of Blue Pottery

More information

Recognition: Face Recognition. Linda Shapiro EE/CSE 576

Recognition: Face Recognition. Linda Shapiro EE/CSE 576 Recognition: Face Recognition Linda Shapiro EE/CSE 576 1 Face recognition: once you ve detected and cropped a face, try to recognize it Detection Recognition Sally 2 Face recognition: overview Typical

More information

Wavelet based Keyframe Extraction Method from Motion Capture Data

Wavelet based Keyframe Extraction Method from Motion Capture Data Wavelet based Keyframe Extraction Method from Motion Capture Data Xin Wei * Kunio Kondo ** Kei Tateno* Toshihiro Konma*** Tetsuya Shimamura * *Saitama University, Toyo University of Technology, ***Shobi

More information

Studying in the Sciences

Studying in the Sciences Organising data and creating figures (charts and graphs) in Excel What is in this guide Familiarisation with Excel (for beginners) Setting up data sheets Creating a chart (graph) Formatting the chart Creating

More information

Human Body Shape Modeling Using 3D Range Data for Healthcare Applications and Beauty Services

Human Body Shape Modeling Using 3D Range Data for Healthcare Applications and Beauty Services Human Body Shape Modeling Using 3D Range Data for Healthcare Applications and Beauty Services Igor Goncharenko 3D Incorporated Yokohama, Japan goga_3d@yahoo.com Abstract The paper describes a system to

More information

Human Action Recognition Using Independent Component Analysis

Human Action Recognition Using Independent Component Analysis Human Action Recognition Using Independent Component Analysis Masaki Yamazaki, Yen-Wei Chen and Gang Xu Department of Media echnology Ritsumeikan University 1-1-1 Nojihigashi, Kusatsu, Shiga, 525-8577,

More information

PATTERN RECOGNITION USING NEURAL NETWORKS

PATTERN RECOGNITION USING NEURAL NETWORKS PATTERN RECOGNITION USING NEURAL NETWORKS Santaji Ghorpade 1, Jayshree Ghorpade 2 and Shamla Mantri 3 1 Department of Information Technology Engineering, Pune University, India santaji_11jan@yahoo.co.in,

More information

A Generation Methodology for Numerical Phantoms with Statistically Relevant Variability of Geometric and Physical Properties

A Generation Methodology for Numerical Phantoms with Statistically Relevant Variability of Geometric and Physical Properties A Generation Methodology for Numerical Phantoms with Statistically Relevant Variability of Geometric and Physical Properties Steven Dolly 1, Eric Ehler 1, Yang Lou 2, Mark Anastasio 2, Hua Li 2 (1) University

More information

Correspondence. CS 468 Geometry Processing Algorithms. Maks Ovsjanikov

Correspondence. CS 468 Geometry Processing Algorithms. Maks Ovsjanikov Shape Matching & Correspondence CS 468 Geometry Processing Algorithms Maks Ovsjanikov Wednesday, October 27 th 2010 Overall Goal Given two shapes, find correspondences between them. Overall Goal Given

More information

The Quantification of Volumetric Asymmetry by Dynamic Surface Topography. Thomas Shannon Oxford Brookes University Oxford, U.K.

The Quantification of Volumetric Asymmetry by Dynamic Surface Topography. Thomas Shannon Oxford Brookes University Oxford, U.K. The Quantification of Volumetric Asymmetry by Dynamic Surface Topography Thomas Shannon Oxford Brookes University Oxford, U.K. The psychosocial impact of the cosmetic defect on Adolescent Idiopathic Scoliosis

More information

Colorado School of Mines. Computer Vision. Professor William Hoff Dept of Electrical Engineering &Computer Science.

Colorado School of Mines. Computer Vision. Professor William Hoff Dept of Electrical Engineering &Computer Science. Professor William Hoff Dept of Electrical Engineering &Computer Science http://inside.mines.edu/~whoff/ 1 Statistical Models for Shape and Appearance Note some material for these slides came from Algorithms

More information

Translation Symmetry Detection: A Repetitive Pattern Analysis Approach

Translation Symmetry Detection: A Repetitive Pattern Analysis Approach 2013 IEEE Conference on Computer Vision and Pattern Recognition Workshops Translation Symmetry Detection: A Repetitive Pattern Analysis Approach Yunliang Cai and George Baciu GAMA Lab, Department of Computing

More information

Feature Extraction for Illustrating 3D Stone Tools from Unorganized Point Clouds

Feature Extraction for Illustrating 3D Stone Tools from Unorganized Point Clouds Feature Extraction for Illustrating 3D Stone Tools from Unorganized Point Clouds Enkhbayar Altantsetseg 1) Yuta Muraki 2) Katsutsugu Matsuyama 2) Fumito Chiba 3) Kouichi Konno 2) 1) Graduate School of

More information

The Artifact Subspace Reconstruction method. Christian A Kothe SCCN / INC / UCSD January 2013

The Artifact Subspace Reconstruction method. Christian A Kothe SCCN / INC / UCSD January 2013 The Artifact Subspace Reconstruction method Christian A Kothe SCCN / INC / UCSD January 2013 Artifact Subspace Reconstruction New algorithm to remove non-stationary highvariance signals from EEG Reconstructs

More information

Improving Latent Fingerprint Matching Performance by Orientation Field Estimation using Localized Dictionaries

Improving Latent Fingerprint Matching Performance by Orientation Field Estimation using Localized Dictionaries Available Online at www.ijcsmc.com International Journal of Computer Science and Mobile Computing A Monthly Journal of Computer Science and Information Technology IJCSMC, Vol. 3, Issue. 11, November 2014,

More information

3D object comparison with geometric guides for Interactive Evolutionary CAD

3D object comparison with geometric guides for Interactive Evolutionary CAD Loughborough University Institutional Repository 3D object comparison with geometric guides for Interactive Evolutionary CAD This item was submitted to Loughborough University's Institutional Repository

More information

About this document. Introduction. Where does Life Forms fit? Prev Menu Next Back p. 2

About this document. Introduction. Where does Life Forms fit? Prev Menu Next Back p. 2 Prev Menu Next Back p. 2 About this document This document explains how to use Life Forms Studio with LightWave 5.5-6.5. It also contains short examples of how to use LightWave and Life Forms together.

More information

A Point in Non-Convex Polygon Location Problem Using the Polar Space Subdivision in E 2

A Point in Non-Convex Polygon Location Problem Using the Polar Space Subdivision in E 2 A Point in Non-Convex Polygon Location Problem Using the Polar Space Subdivision in E 2 Vaclav Skala 1, Michal Smolik 1 1 Faculty of Applied Sciences, University of West Bohemia, Univerzitni 8, CZ 30614

More information

Optimizing Monocular Cues for Depth Estimation from Indoor Images

Optimizing Monocular Cues for Depth Estimation from Indoor Images Optimizing Monocular Cues for Depth Estimation from Indoor Images Aditya Venkatraman 1, Sheetal Mahadik 2 1, 2 Department of Electronics and Telecommunication, ST Francis Institute of Technology, Mumbai,

More information

Modelling imprints of pharmaceutical tablets for imprint quality visual inspection

Modelling imprints of pharmaceutical tablets for imprint quality visual inspection Modelling imprints of pharmaceutical tablets for imprint quality visual inspection Miha Možina 1, Dejan Tomaževič 1,2, Franjo Pernuš 1,2 and Boštjan Likar 1,2 1 Sensum, Computer Vision Systems Tehnološki

More information