Visualization of Multimedia Database Queries



Many current content-based image retrieval systems suffer from poor result presentation. A sophisticated visualization can be used to identify differences between human perception of similarity and system-determined similarity. Analyzing such discrepancies is a prerequisite for a system trimmed towards the userís comprehension of the underlying retrieval process. The aim of the visualization techniques presented in this paper is to provide a tool to analyze a mismatch between the userís perception and the systemís calculation of similarity. We combine techniques of visual image retrieval and information visualization to acquire insight into the extracted feature data. In our project we implemented visualization techniques to present feature data on three different levels of abstraction. We discuss our experiences when working with a Data Table, a Parallel Coordinate Plot, and a Color Space Plot.


This image shows two of the representations we built. The same green image was given as a query to an image database. The visualization shows clusters of images returned. The one on the left shows, that mostly yellow and blue images were returned - clearly not what you would want. On the right, the result is a little better and also shows the actual images returned instead of the spheres.


Anke Schneidewind, Ingo Schmitt, and Petra Neumann (2004) iVi: An Enhanced Query Result Visualization for Image Databases. KI – Künstliche Intelligenz, 18(4):34–37, November 2004. Special issue on Adaptive Multimedia Retrieval.

BibTeX entry:

@ARTICLE{Schneidewind:2004:IVI, author = {Anke Schneidewind and Ingo Schmitt and Petra Neumann}, title = {iVi}: {A}n {E}nhanced {Q}uery {R}esult {V}isualization for {I}mage {D}atabases, journal = {KI -- K{\"u}nstliche Intelligenz}, year = {2004}, volume = {18}, number = {4}, month = nov, pages = {34--37}, url = {}, pdf = {../publications/papers/Schneidewind_2004_IVI.pdf}, }
Anke Schneidewind, Petra Neumann, and Ingo Schmitt (2004) An Approach to Visualize Image Retrieval Results. In Sadiye Guler, Alexander G. Hauptmann, and Andreas Henrich, eds., Proceedings of 4th International Workshop on Multimedia Data and Document Engineering (MDDE 2004, June 27–July 2, 2004, Washington D.C.). IEEE Computer Society, Los Alamitos, CA, 2004. Published on CD. Abstract in Proceedings of Computer Vision and Pattern Recognition Workshop 2004, page 148.

BibTeX entry:

@INPROCEEDINGS{Schneidewind:2004:AVI, author = {Anke Schneidewind and Petra Neumann and Ingo Schmitt}, title = {A}n {A}pproach to {V}isualize {I}mage {R}etrieval {R}esults, booktitle = {Proceedings of 4\textsuperscript{th} International Workshop on Multimedia Data and Document Engineering (MDDE 2004, June 27--July 2, 2004, Washington D.C.)}, OPTeditor = {Sadiye Guler and Alexander G. Hauptmann and Andreas Henrich}, year = {2004}, publisher = {IEEE Computer Society}, address = {Los Alamitos, CA}, doi = {10.1109/CVPR.2004.297}, doi_url = {}, url = {}, pdf = {../publications/papers/Schneidewind_2004_AVI.pdf}, }

back to the projects page