Posted in Computer Vision, dcapi, Workshop

OpenCV workshop

Saddam Bekhet, member of the DCAPI group  demonstrated  workshop about Using OpenCV  with Visual Studio 2010 Express edition on 23/01/2013 . In addition a demonstration about basic OpenCV operations (loading & manipulating images) and advanced operations (face detector & tracker from live camera stream) was demonstrated.

Face detection example link

Summary of installation settings of OpenCV :
1- Download OpenCV files
2- Download CMAKE
3- Use CMAKE to generate OpenCV library AND DLL’s  and use x64 architecture or the architecture what ever suites you  in VS2010
4-Open OpenCV build folder and search for “OpenCV.sln”  then compile it.
5- Remember to but openCV DLL’s beside The Debug \EXEDirectory of your project in Visual Studio
6- Rememeber to install intel threading block and put the DLL called  tbb.dll in  your visual studio debug\EXE

Include direcories in VS2010 Project–>Properities–>VC++ Directories

Library direcories in VS2010 Project–>Properities–>Linker–>Input
Linker–> Input
opencv_core242X.lib opencv_imgproc242X.lib opencv_highgui24X.lib opencv_ml242X.lib opencv_video242X.lib  opencv_features2d2X.lib opencv_features2d2X.lib opencv_calib3d242X.lib opencv_objdetect242X.lib opencv_contrib242X.lib
opencv_legacy242X.lib opencv_flann242X.lib opencv_nonfree242X.lib

Make sure to reblace “X” in the previous file names with correct naming of the generated OpenCV library files for example on my machine it is “opencv_nonfree242d.lib”




Posted in commonsense knowledgebases, Computer Visions, Conference, dcapi, DCAPI blog, Research, semantic gap, Semantic Video Annotation, Video Analysis, video information retrieval, Video search engine

New Journal paper Accepted to the “Multimedia Tools and Applications”

New Journal paper accepted for publishing in the Journal of “Multimedia Tools and Applications“.

The paper title is “A Framework for Automatic Semantic Video Annotation utilising Similarity and Commonsense Knowledgebases


The rapidly increasing quantity of publicly available videos has driven research into developing automatic tools for indexing, rating, searching and retrieval. Textual semantic representations, such as tagging, labelling and annotation, are often important factors in the process of indexing any video, because of their user-friendly way of representing the semantics appropriate for search and retrieval. Ideally, this annotation should be inspired by the human cognitive way of perceiving and of describing videos. The difference between the low-level visual contents and the corresponding human perception is referred to as the ‘semantic gap’. Tackling this gap is even harder in the case of unconstrained videos, mainly due to the lack of any previous information about the analyzed video on the one hand, and the huge amount of generic knowledge required on the other.

This paper introduces a framework for the Automatic Semantic Annotation of unconstrained videos. The proposed framework utilizes two non-domain-specific layers: low-level visual similarity matching, and an annotation analysis that employs commonsense knowledgebases. Commonsense ontology is created by incorporating multiple-structured semantic relationships. Experiments and black-box tests are carried out on standard video databases for
action recognition and video information retrieval. White-box tests examine the performance of the individual intermediate layers of the framework, and the evaluation of the results and the statistical analysis show that integrating visual similarity matching with commonsense semantic relationships provides an effective approach to automated video annotation.


Well done and congratulations to Amjad Altadmri .