Abstract
Two similarity measures to compare whole and parts of images are proposed. These measures consider the color, shape and texture properties of image segments as well as their relative positions mutually.
After image segmentation MPEG-7 descriptors are computed for each segment. Now the information reduced images will be represented by labeled graphs.
To compute the first similarity measure it is necessary to solve the Maximum Weight Clique Problem in an extended compatibility graph. This problem is solved by a connectionistic method.
The second similarity measure needs to solve a special kind of Consistent Labeling Problem. This is done by a connectionistic method too.
Both measures may be used to improve the similarity measurement of images for instance in image and video retrieval, object recognition, stereo and many other Computer Vision tasks.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Fuh, C.S., Cho, S.W., Essig, K.: Hierarchical color image region segmentation for content based image retrieval system. IEEE TRANSACTIONS ON IMAGE PROCESSINGÂ 9(1) (January 2000)
Kaden, F., Sobik, F.: Beiträge zur angewandten Graphentheorie. ZKI Information (1982)
Li, Z.N., Zaiane, O.R., Tauber, Z.: Illumination invariance and object model in content-based image and video retrieval. Journal of Visual Communication and Image Representation 10(3), 219–244 (1999)
Ma, W.Y., Manjunath, B.S.: Edge flow: a framework of boundary detection and image segmentation. In: Proc. of CVPR (1997)
Meiers, T., Keller, I., Sikora, T.: Image visualization and navigation based on MPEG-7 descriptors. In: Conference on Augmented, Virtual Environments and 3D Imaging, EUROIMAGE 2001 (May 2001)
Ortega, M., Rui, Y., Chakrabarti, K., Mehrotra, S., Huang, T.S.: Supporting similarities queries in MARS. In: Proceedings of the 5th ACM International Multimedia Conference, Seattle,Washington, November 8-14, pp. 403–413 (1997)
Rosenfeld, A., Hummel, R., Zucker, S.: Scene labeling by relaxation operation. IEEE Trans. Syst. Man. and Cybern., 420–433 (1976)
Schaedler, K.: Die Ermittlung struktureller Ähnlichkeiten und struktureller Merkmale bei komplexen Objekten: Ein konnektionistischer Ansatz und seine Anwendungen. PhD thesis, Technische Universität Berlin (1999)
Schaedler, K., Wysotzki, F.: Comparing structures using a hopfield-style neural network. Applied Intelligence 11, 15–30 (1999)
Schlesinger, M.I., Flach, B.: Some solvable subclasses of structural recognition problems. In: Czech Pattern Recognition Workshop 2000 (2000)
Sikora, T.: The MPEG-7 visual standard for content description-An Overview. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGYÂ 11(6) (June 2001)
Weickert, J.: Fast segmentation methods based on partial differential equations and the watershed transform. In: Mustererkennung 1998, pp. 93–100. Springer, Heidelberg (1998)
Wersing, H.: Spatial Feature Binding and Learning in Competitive Neural Layer Architectures. PhD thesis, Technische Fakultät der Universität Bielefeld (2000)
Winter, A., Nastar, C. (eds.): Differential Feature Distribution Maps for Image Segmentation and Region Queries in Image Databases. In: IEEE CVPR 1999 workshop on Content Based Access of Images and Video Libraries, Ft Collins, Colorado (June 1999)
Zelinka, B.: On a certain distance between isomorphism classes of graphs. Casopis pro pestovani matematiky 100, 371–373 (1975)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Bischoff, S., Reuss, D., Wysotzki, F. (2003). Applied Connectionistic Methods in Computer Vision to Compare Segmented Images. In: Günter, A., Kruse, R., Neumann, B. (eds) KI 2003: Advances in Artificial Intelligence. KI 2003. Lecture Notes in Computer Science(), vol 2821. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-39451-8_23
Download citation
DOI: https://doi.org/10.1007/978-3-540-39451-8_23
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-20059-8
Online ISBN: 978-3-540-39451-8
eBook Packages: Springer Book Archive