Source Code

MoCA Source Code

  • Windows source code for
    • Shot Detection
      • Rainer Lienhart. Comparison of Automatic Shot Boundary Detection Algorithms. In Image and Video Processing VII 1999, Proc. SPIE 3656-29, Jan. 1999. [PDF: 172KB]
    • Video OCR (text detection and text tracking)
      • Rainer Lienhart and Wolfgang Effelsberg. Automatic Text Segmentation and Text Recognition for Video Indexing. ACM/Springer Multimedia Systems, Vol. 8. pp.69-81, January 2000; also Technical Report TR-98-009, Praktische Informatik IV, University of Mannheim, May 1998. [PDF : 283KB]
    • Face detection
      • Rainer Lienhart, Silvia Pfeiffer, and Wolfgang Effelsberg. Video Abstracting. Communications of the ACM, Vol. 40, No. 12, pp.55-62, December 1997. [PDF : 132 KB] [PDF from ACM : 4313 KB]

      I order to compile you need MS Visual C++ 6.0 and Microsofts DirectX 8.0 SDK. In MoCA_Lib/src/image/ you find the complete MoCA Library source code. In MoCA_Lib/src/prgs/ you find the source code for the different programs described at http://www.informatik.uni-mannheim.de/informatik/pi4/projects/MoCA/downloads.html. The code is only available for non-commercial purposes.

Open Source Code

  • Cross platform face detection code based on a cascade of boosted classifiers (part of OpenCV; directories apps/HaarFaceDetect and apps/HaarTraining)
    • Rainer Lienhart and Jochen Maydt. An Extended Set of Haar-like Features for Rapid Object Detection. IEEE ICIP 2002, Vol. 1, pp. 900-903, Sep. 2002. [PDF : 117KB]
    • Rainer Lienhart, Alexander Kuranov, and Vadim Pisarevsky. Empirical Analysis of Detection Cascades of Boosted Classifiers for Rapid Object Detection. MRL Technical Report, Intel Labs, May 2002, revised Dec. 2002. [PDF: 1053KB]
    • Rainer Lienhart, Luhong Liang, and Alexander Kuranov. A Detector Tree of Boosted Classifiers for Real-time Object Detection and Tracking. IEEE ICME2003, July 2003. [PDF: 178KB]
  • Third party trained cascade classifiers
    • Three detectors for upper, lower und full human body (provided by Hannes Kruppa [hkruppa@inf.ethz.ch]): [Cascades: 187KB] [Demo video: 1MB]
    • Seven frontal face detectors (-90°,-60°, 30°, 0°, 30°, 60°, and 90°) for in-plane rotated faces. Input pattern size for all detectors is 20x20 pixels.

      •  
[Home] [Current Research] [Video Content Analysis] [Publications] [MoCA Project] [Source Code] [Contact]4