Our Automated Face Beautification Engine is publically accessible. This is a project that I have been working with Dr. Yu Wang and Dr. Zuoguan Wang.

  • The address:

  • The version 2.3 of the AGSM toolkit has been released! Great new features include: (1) line fitting and circle fitting demos; (2) C++/MEX implementation of GVF and force/torque computation; (3) smart initialization; (4) the AGSM Canvas app! This new version is significantly FASTER and MORE ROBUST than version 1.0.

  • Checkout AGSM toolkit v2.3:

  • About Me

    I am Quan Wang, a fifth-year Ph.D. student majoring in Computer & Systems Engineering at RPI. My advisor is Professor Kim L. Boyer.

    My research interests focus on:

  • Biomedical image analysis (mainly 2D and 3D segmentation)
  • Occupancy sensing for smart lighting
  • Deep learning and manifold learning
  • Object tracking
  • And other topics in Computer Vision and Pattern Recognition
  • My Curriculum Vitae: click here


    Lab address:
    JEC 6304
    Signal Analysis and Machine Perception Laboratory (SAMPL)
    Department of Electrical, Computer, and Systems Engineering
    Rensselaer Polytechnic Institute

    View Larger Map


    Active Geometric Shape Models and CSF Detection

    I have been working with Prof. Kim L. Boyer to develop a novel approach, the Active Geometric Shape Models, to fit parametric shapes to data and images. Our paper is published on CVIU.

  • Project Wiki
  • Link
  • Paper in PDF
  • Slides
  • Download software

  • COSBOS: COlor-Sensor-Based Occupancy Sensing

    With multiple color-controllable LED fixtures and color sensors, our COSBOS technique enables low-cost and privacy-preserving occupancy distribution estimation. The direct application of this technique is occupancy-sensitive smart lighting, in which the system automatically delivers the light that best suits the occupancy scenario in an indoor space.

  • Project Wiki
  • JSSL 2014 Paper in PDF
  • ICPR 2014 Paper in PDF
  • PBVS 2014 Paper in PDF
  • SPIE 2014 Paper in PDF

  • Learning-Based Knee Cartilage Segmentation in 3D MR

    The automatic segmentation of human knee cartilage from 3D MR images is challenging due to the thin sheet structure of the cartilage with diffuse boundaries and inhomogeneous intensities. We present an iterative multi-class learning method to segment the femoral, tibial and patellar cartilage simultaneously, which effectively exploits the spatial contextual constraints between bone and cartilage, and also between different cartilages. High accuracy and robustness is achieved on 176 volumes from the OAI dataset.

  • Paper in PDF
  • Poster
  • Slides
  • Code

  • Tracking Tetrahymena Pyriformis Cells using Decision Trees

    We approach the cell tracking problem by interpreting it as a classification problem. Our paper is published on ICPR 2012.

  • Paper in PDF
  • Poster
  • Shotgun
  • Code

  • Segmentation and Disease Detection in Echocardiogram Images

    This is my work as an Research Intern at IBM. It is part of the Medical Sieve project.

  • Poster

  • Manifold Learning for Image Classification

    We apply manifold learning techniques including multidimensional scaling (MDS) and Isomap on high-level semantics-sensitive pairwise image distances, such as IMED, SPM, IRM and their variants to learn fixed-length vector representations of images. We are looking at applications including style categorization, scene classification and object recognition.

  • Project Wiki
  • SIBGRAPI paper
  • Slides
  • Download MDS encoder source code

  • GPU Implementation for GVF Force Field

    This is a project I have been working on when I was in Prof. Badrinath Roysam's lab. My work is part of the FARSIGHT project . Here is the

  • Project Report
  • Documentation
  • Full Package including Code

  • Implementation and Study of Light-field-based 3D Object Retrieval System

    This is my research for undergraduate thesis at Tsinghua University, under the guidance of Prof. Qionghai Dai and Prof. Guihua Er.

  • Poster

  • Publications

    Journal Publications

    Quan Wang, Kim L. Boyer, "The active geometric shape model: A new robust deformable shape model and its applications", Computer Vision and Image Understanding, Volume 116, Issue 12, December 2012, Pages 1178-1194, ISSN 1077-3142, doi:10.1016/j.cviu.2012.08.004. [link] [PDF] [Slides] [software]
    Quan Wang, Xinchi Zhang, Kim L. Boyer, "Occupancy distribution estimation for smart light delivery with perturbation-modulated light sensing", Journal of Solid State Lighting, 2014, 1:17, ISSN 2196-1107, doi:10.1186/s40539-014-0017-2. [link] [PDF]

    Conference Publications

    Quan Wang, Xinchi Zhang, Kim L. Boyer, "3D Scene Estimation with Perturbation-Modulated Light and Distributed Sensors", 10th IEEE Workshop on Perception Beyond the Visible Spectrum (PBVS). (ORAL) [PDF]
    Quan Wang, Dijia Wu, Le Lu, Meizhu Liu, Kim L. Boyer, and Shaohua Kevin Zhou, "Semantic Context Forests for Learning-Based Knee Cartilage Segmentation in 3D MR Images", Medical Computer Vision. Large Data in Medical Imaging. Pages 105-115. (ORAL) [PDF] [poster] [slides] [software]
    Quan Wang, Yan Ou, A. Agung Julius, Kim L. Boyer and Min Jun Kim, "Tracking Tetrahymena Pyriformis Cells using Decision Trees", 2012 21st International Conference on Pattern Recognition (ICPR), Pages 1843-1847, 11-15 Nov. 2012. [PDF] [poster] [shotgun] [software]
    Quan Wang, Kim L. Boyer, "Feature Learning by Multidimensional Scaling and its Applications in Object Recognition", 2013 26th SIBGRAPI Conference on Graphics, Patterns and Images (Sibgrapi). IEEE, 2013. (ORAL) [PDF] [slides] [software]
    Tanveer Syeda-Mahmood, Quan Wang, Patrick McNeillie, David Beymer, Colin Compas, "Discriminating Normal and Abnormal Left Ventricular Shapes in Four-Chamber View 2D Echocardiography", accepted by International Symposium on Biomedical Imaging (ISBI) 2014.
    Quan Wang, Xinchi Zhang, Meng Wang, Kim L. Boyer, "Learning Room Occupancy Patterns from Sparsely Recovered Light Transport Models", 22nd International Conference on Pattern Recognition (ICPR), 2014. (ORAL) [PDF]
    Xinchi Zhang, Quan Wang, Kim L. Boyer, "Illumination Adaptation with Rapid-Response Color Sensors", SPIE Optical Engineering + Applications, 2014. (ORAL) [PDF]
    Quan Wang, Xin Shen, Meng Wang, Kim L. Boyer, "Label Consistent Fisher Vectors for Supervised Feature Aggregation", 22nd International Conference on Pattern Recognition (ICPR), 2014. [PDF] [software]

    Patents Pending

    Quan Wang, Dijia Wu, Meizhu Liu, Le Lu, S. Kevin Zhou, "Automatic Spatial Context Based Multi-Object Segmentation in 3D Images", United States No. 61/734280, Filed December 6, 2012
    David Beymer, Patrick McNeillie, Tanveer Syeda-Mahmood, Quan Wang, "Discriminating between normal and abnormal left ventricles in echocardiography", United States No. 14/262780, Filed April 27, 2014
    Quan Wang, Xinchi Zhang, Kim L. Boyer, "Occupancy sensing with perturbation-modulated light and distributed non-imaging color sensors", United States No. 62/014745, Filed June 20, 2014


    I am the reviewer of
  • SIBGRAPI Conference on Graphics, Patterns, and Images 2013
  • SIBGRAPI Conference on Graphics, Patterns, and Images 2014
  • VISAPP International Conference on Computer Vision Theory and Applications 2014
  • EURASIP Journal on Image and Video Processing
  • Computer Communication & Collaboration
  • Technical Reports

    Quan Wang, "GMM-Based Hidden Markov Random Field for Color Image and 3D Volume Segmentation", arXiv:1212.4527 [cs.CV]. [PDF]
    Quan Wang, "HMRF-EM-image: Implementation of the Hidden Markov Random Field Model and its Expectation-Maximization Algorithm", arXiv:1207.3510 [cs.CV]. [PDF]
    Quan Wang, "Kernel Principal Component Analysis and its Applications in Face Recognition and Active Shape Models", arXiv:1207.3538 [cs.CV]. [PDF]


    The SimpleMatrix C++ Library

    SimpleMatrix is an extremely lightweight matrix library, containing a single header file.

  • It uses the namespace smat.
  • The Matrix class is a template class.
  • It implements basic matrix representations and operations, such as multiplication, transpose, and submatrix.
  • It does not implement complicated operations such as inverse, determinant, eigenvector, or decompositions.
  • It implements the Multidimensional Scaling (MDS) algorithm.

  • Link to the project site.
    Download the library here.

    GMM-Based Hidden Markov Random Field for Color Image and 3D Volume Segmentation

    This is the final project of Prof. Qiang Ji's course Introduction to Probabilistic Graphical Models. In this project, we first study the Gaussian-based hidden Markov random field (HMRF) model and its expectationmaximization (EM) algorithm. Then we generalize it to Gaussian mixture model-based hidden Markov random field. The algorithm is implemented in MATLAB. We also apply this algorithm to color image segmentation problems and 3D volume segmentation problems.
    Download the paper here.
    Download the Matlab code here.

    Hidden Markov Random Field Model, its Expectation-Maximization Algorithm, Implementation, and Applications in Edge-Prior-Preserving Image Segmentation

    This is the final project of Prof. Birsen Yazıcı's course Detection and Estimation Theory. In this project, we study the hidden Markov random field (HMRF) model and its expectation-maximization (EM) algorithm. We implement a MATLAB toolbox named HMRF-EM-image for 2D image segmentation using the HMRF-EM framework. This toolbox also implements edge-prior-preserving image segmentation, and can be easily reconfigured for other problems, such as 3D image segmentation.
    Download the paper here.
    Download the HMRF-EM-image Matlab toolbox here.

    Kernel Principal Component Analysis and its Applications in Face Recognition and Active Shape Models

    This is the final project of Prof. Qiang Ji's course Pattern Recognition. In this paper, we discussed the theories of PCA, kernel PCA and ASMs. Then we focused on the pre- image reconstruction for Gaussian kernel PCA, and used this technique to design kernel PCA based ASMs. We tested kernel PCA on synthetic data and human face images, and found that Gaussian kernel PCA succeeded in revealing more complicated structures of data than traditional PCA and achieving much lower classification error rate. We also implemented the Gaussian kernel PCA based ASMs and tested it on human face images. We found that Gaussian kernel PCA based ASMs is promising in providing more deformation patterns than traditional ASMs.
    Download the paper here.
    Download the PPT here.
    Download the Matlab code here.

    Tracking Based 3D Visualization from 2D Videos

    This is the final project of Prof. Qiang Ji's course Computer Vision. In this project, we established a framework to convert 2D videos to pseudo 3D videos. Our basic idea is to track the moving objects in the video and separate them from the background. Then we give different depth information to the objects and the background, and visualize them in 3D. Download the report here.

    Here is a demo of our 3D animations. Please wear blue-red 3D glasses.

    Hästens app on iPhone

    This is the final project for the course Software Design & Documentation at RPI. This is our project website.

    Here is the video presentation of the app:


    I have been working as the teaching assistant of these courses:

  • Embedded Control [ENGR 2350], 2011 Spring, Prof. Russell P. Kraft
  • Real-Time Applications in Control & Communications [ECSE 4760], 2011 Spring, Prof. Russell P. Kraft
  • Introduction to Engineering Analysis [ENGR 1100], 2011 Fall, Prof. Mark W. Olles
  • Biological Image Ananysis [ECSE 4960], 2012 Spring, Dr. Jens Rittscher
  • Electric Circuits [ECSE 2010], 2012 Spring, Prof. Jeffrey Braunstein
  • Modeling and Analysis of Uncertainty [ENGR 2600], 2012 Fall, Prof. Charles J. Malmborg

  • Here are some of the course materials I made for my students:
  • Matlab Tutorial 1
  • Matlab Tutorial 2
  • Matlab Tutorial 3
  • Accessing RCS IBM Console in Windows Using Linux Virtual Machine
  • how to build SimpleITK Python
  • Courses and Study

    MY GPA at RPI is 4.0 out of 4.0. I have been taking these courses at RPI:

  • Operating Systems by Prof. David E. Goldschmidt
  • Detection and Estimation Theory by Prof. Birsen Yazici
  • Introduction to Stochastic Signals and Systems by Prof. John Woods
  • Computational Linear Algebra by Prof. Donald Schwendeman
  • Pattern Recognition by Prof. Qiang Ji
  • Computational Optimization by Prof. Kristin P. Bennett
  • Computer Vision by Prof. Qiang Ji
  • Machine Learning by Prof. Malik Magdon-Ismail
  • Biological Image Ananysis by Dr. Jens Rittscher
  • Software Design and Documentation by John Sturman
  • Probabilistic Graphic Models by Prof. Qiang Ji
  • Graph Theory by Prof. Mark K. Goldberg
  • Database Systems by Prof. Sibel Adali
  • Data Science by Prof. Peter Fox
  • Compressed Sensing and its Applications by Prof. Meng Wang
  • comments powered by Disqus