Abstract
Evaluation of visual information retrieval systems is usually performed by executing test queries and computing recall- and precision-like measures based on predefined media collections and ground truth information. This process is complex and time consuming. For the evaluation of feature transformations (transformation of visual media objects to feature vectors) it would be desirable to have simpler methods available as well. In this paper we introduce a supplementary evaluation procedure for features that is founded on statistical data analysis. A second novelty is that we make use of the existing visual MPEG-7 descriptors to judge the characteristics of feature transformations. The proposed procedure is divided into four steps: (1) feature extraction, (2) merging with MPEG-7 data and normalisation, (3) statistical data analysis and (4) visualisation and interpretation. Three types of statistical methods are used for evaluation: (1) univariate description (moments, etc.), (2) identification of similarities between feature elements (e.g. cluster analysis) and (3) identification of dependencies between variables (e.g. factor analysis). Statistical analysis provides beneficial insights into the structure of features that can be exploited for feature redesign. Application and advantages of the proposed approach are shown in a number of toy examples.
Similar content being viewed by others
References
Bober M (2001) MPEG-7 visual shape descriptors. Special issue on MPEG-7. IEEE Trans Circuits Syst Video Technol 11(6):716–719
Breiteneder C, Eidenberger H (1999) Content-based image retrieval of coats of arms. In: Proc. IEEE International Workshop on Multimedia Signal Processing, Helsingör, pp 91–96
Chang SF, Sikora T, Puri A (2001) Overview of the MPEG-7 standard. Special issue on MPEG-7. IEEE Trans Circuits Syst Video Technol 11(6):688–695
Computer Vision Image Library, http://www-2.cs.cmu.edu/~cil/v-images.html (last visited 2005–03–29)
Cowan G (1998) Statistical data analysis. Oxford University Press, Oxford, UK
Del Bimbo A (1999) Visual information retrieval. Morgan Kaufmann, San Francisco
Edwards JD, Riley KJ, Eakins JP (2003) A technique for mapping irregular sized vectors applied to image collections. In: Proc. SPIE visual communications and image processing conference, vol 5150. Lugano, pp 467–475
Eidenberger H (2003) How good are the visual MPEG-7 Features? In: Proc. SPIE visual communications and image processing conference, vol 5150. Lugano, pp 476–488
Eidenberger H (2004) A new method for visual descriptor evaluation. In: Proc. SPIE storage and retrieval methods and applications for multimedia, vol 5307. San Jose, pp 145–157
Eidenberger H (2004) Statistical analysis of the MPEG-7 image descriptors. In: ACM Multimedia Systems Journal, vol 10, no 2. Springer, Berlin Heidelberg New York, pp 84–97
Eidenberger H, Breiteneder C (2003) VizIR—a framework for visual information retrieval. J Vis Lang Comput, Elsevier 14(5):443–469
Fuhr N (2001) Information retrieval methods for multimedia objects. In: Veltkamp RC, Burkhardt H, Kriegel, HP (eds) State-of-the-art in content-based image and video retrieval. Kluwer, Boston, pp 191–212
Izquierdo E, Casas JR, Leonardi R, Migliorati P, O’Connor NE, Kompatsiaris I, Strintzis MG (2003) Advanced content-based semantic scene analysis and information retrieval: the SCHEMA project. In: Proc. workshop on image analysis for multimedia interactive services, London, pp 519–528
Jain AK, Murty MN, Flynn PJ (1999) Data clustering: a review. ACM Comput Surv 31(3):264–323
Kohonen T (1990) The self-organizing map. Proc IEEE 78(9):1464–1480
Kohonen T, Oja E, Simula O, Visa A, Kangas J (1996) Engineering applications of the self-organizing map. Proc IEEE 84(10):1358–1384
Koikkalainen P, Oja E (1990) Self-organising hierarchical feature maps. In: Proc. neural networks conference. San Diego, pp 279–284
Lew MS (ed) (2003) Principles of visual information retrieval. Springer, Berlin Heidelberg New York
Loehlin JC (2001) Latent variable models: an introduction to factor. Path and structural analysis, 3rd edn. Erlbaum, Mahwah, NJ
Manjunath BS, Ohm JR, Vasudevan VV, Yamada A (2001) Color and texture descriptors. Special issue on MPEG-7. IEEE Trans Circuits Syst Video Technol 11(6):703–715
Manjunath BS, Salembier P, Sikora T (2002) Introduction to MPEG-7. Wiley, San Francisco
Marques O, Furht B (2002) Content-based image and video retrieval. Kluwer, Boston
Müller H, Müller W, Squire DMcG, Marchand-Maillet S, Pun T (2001) Performance evaluation in content-based image retrieval: overview and proposals. Special issue on image and video indexing. Pattern Recogn Lett 22(5):593–601
Smeaton AF, Over P, Kraaij W (2004) TRECVID: evaluating the effectiveness of information retrieval tasks on digital video. In: Proceedings ACM Multimedia Conference, New York, pp 652–655
Smeulders AWM, Worring M, Santini S, Gupta A, Jain R (2000) Content-based image retrieval at the end of the early years. IEEE Trans Pattern Anal Mach Intell 22(12):1349–1380
University of California Berkeley Corel Dataset Website, http://elib.cs.berkeley.edu/photos/corel/ (last visited 2005–03–29)
Vesanto J, Himberg J, Alhoniemi E, Parhankangas J (1999) Self-organizing map in Matlab: the SOM toolbox. In: Proc. Matlab DSP Conference, Espoo, pp 35–40
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Eidenberger, H. Evaluation of content-based image descriptors by statistical methods. Multimed Tools Appl 35, 241–258 (2007). https://doi.org/10.1007/s11042-007-0106-y
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-007-0106-y