VOSM

VOSM (Vision Open Statistical Models, C++)

• Where to download?

  • vosm-0.3.3.tar.gz (Linux)
  • vosm-0.3.3.7z (Windows)
  • vosm-svn(platform independent)

• Documentation

  • doc in html
  • doc in pdf

• Implementations

  Current VOSM implements all popular ASMs/AAMs, and one new fitting methods (namely, 2D profile ASM) both for static images and dynamic image sequences, including:

  • 1D profile ASM
  • 2D profile ASM
  • Direct Local texture contrained (LTC) ASM
  • Basic AAM
  • ICIA(Inverse compositional image alignment) AAM
  • IAIA(Inverse additive image alignment) AAM

• Dependent Libraries

  • OpenCV 2.4.0 or above
  • boost-1.48 or above (boost-regex, boost-filesystem and boost-system are required) 

• Usage

  1. First of all, in order to use VOSM, you need to find and download respective ShapeInfo.txt files summarized in the table at 2D Statistical Models.
  2. In order to correctly run test_smfitting, you need to
     • Either define in preprocessor POSIX or WIN32 due to different OSs.
     • Or add #define POSIX or #define WIN32 in file smfitting.cpp .
  3. How to use VOSM to train a face model and fit an untrained face using the trained face model? Learn to use two commands test_smbuilding and test_smfitting. Two examples are given as:
     • test_smbuilding 
       -a “../Databases/face/2D/EMOUNT/annotations/training” 
       -i “../Databases/face/2D/EMOUNT/images/training” 
       -s “../Databases/face/2D/EMOUNT/annotations/training/ShapeInfo.txt” 
       -d “EMOUNT” 
       -c 1 
       -t “SMNDProfile”
     • test_smfitting 
       -o “../Databases/face/2D/JIAPEI/traineddata/33Frontal/BGR” 
       -t “ASM_PROFILEND” 
       -i “../Databases/face/2D/JIAPEI/images/testing” 
       -a “../Databases/face/2D/JIAPEI/annotations/testing” 
       -d “JIAPEI” 
       -s “true” 
       -r “true”

  More details about these two commands can be found by respective help commands.

AAM Building

• – AAMBuildingGUI-Toronto.rar

  Active Appearance Model (AAM) Building GUI binary code.
  A wxWidget based GUI tool is provided to simplify the process of building an AAM model. Since this tool was roughly finished in Toronto, Canada, I call it a Toronto version.

• – aambuilding-1.0.zip

  Active Appearance Model (AAM) Building Source Code.
  aambuilding-1.0 is a stable version of AAM Building, which has been tested with Boost 1.36 and OpenCV-cvs, both in Windows Vista and Ubuntu 8.04.