Loading...
Projects / Programmes source: ARIS

Xml-based data-format for image analysis results

Research activity

Code Science Field Subfield
2.07.00  Engineering sciences and technologies  Computer science and informatics   

Code Science Field
P170  Natural sciences and mathematics  Computer science, numerical analysis, systems, control 
Keywords
computer vision, image analysis, integration and comparison of results, data structures, standard, XML, MPEG-7, theory of graphs, shape grammars
Evaluation (rules)
source: COBISS
Researchers (2)
no. Code Name and surname Research area Role Period No. of publicationsNo. of publications
1.  19226  PhD Peter Peer  Computer science and informatics  Researcher  2004 - 2006  394 
2.  09581  PhD Franc Solina  Computer science and informatics  Head  2004 - 2006  638 
Organisations (1)
no. Code Research organisation City Registration number No. of publicationsNo. of publications
1.  1539  University of Ljubljana, Faculty of Computer and Information Science  Ljubljana  1627023  16,011 
Abstract
Computer vision systems are penetrating into a number of areas, since we all wish to have systems that automatically and effectively grasp needed information from images. Proportionately to that there is a lot of different methods and results. But there is a lack of a suitable denominator for presentation of results. Namely, there is a lot of systems, which solve similar problems (e.g. face detection), even on different levels (e.g. on the level of the whole face or on the level of face features). Unfortunately, integration or comparison of results of different systems is difficult, also because of ununified data-format for presenting results. We wish that we would be able to integrate results of different systems and levels of computer vision in a standard but flexible way. In this way we could besides the images themselves give the actual contents of the image (the groundtruth) and gradually add analyses results of different systems. This would bring easier comparison of results and easier integration of different levels of image processing. Therefore, we intend to suggest and implement a scheme for uniform data-format for image analysis results, which will be based on XML language. This scheme will assure appropriately structured data-format for presenting the contents of images in a similar way that is given by standard MPEG-7 for describing multimedia contents. Furthermore, it will enable for instance additional analysis of structure with the theory of graphs or shape grammars.
Views history
Favourite