Abstract
The paper describes our research concerning image classification of types of graphics like plots, flow charts, illustrations and photos. Illustrations and photos are also classified into one of the following semantic classes: buildings, people, nature landscape, and interior. On this basis each image is annotated by its type and class. The key elements of the system – feature extraction and classification methods – are described in detail. A new classifier based on fuzzy logic was proposed. Moreover, we developed the Multi-Classifier, a hierarchical architecture encouraging the creation of hybrid classifiers tailored to the problem being solved. Experimental results of classification efficiency show that our approach is definitely worth further development.
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
Duda, R.O., Hart, P.E.: Use of Hough transform to detect lines and curves in pictures. Commun. ACM 15, 11–15 (1972)
Canny, J.: A computational approach to edge detection. IEEE Trans. Pattern Anal. Match. Intell. 8(6), 679–698 (1986)
MIT Indoor Scene Recognition Database, http://web.mit.edu
ETH Zurich Computer Vision Laboratory, http://www.vision.ee.ethz.ch
Haralick, R.M., Dinstein, I., Shanmugam, K.: Textural features for image classification. IEEE Trans. Syst. Man Cybernet. 3, 610–621 (1973)
Lu, X., Kataria, S., Brouwer, W.J., Wang, J.Z., Prasenjit, C., Giles, L.: Automated analysis of images in documents for intelligent document search. IJDAR 12(2) (2009)
OpenCV library Wiki, http://opencv.willowgarage.com/wiki/Welcome
ALIPR - Automatic Photo Tagging and Visual Image Search, http://alipr.com
Malathi, G., Shanthi, V.: Histogram Based Classification of Ultrasound Images of Placenta. IJCA 1(16), 0975-8887 (2010)
LIBSVM - A Library for SVM, http://www.csie.ntu.edu.tw/~cjlin/libsvm/
Burges, C.J.C.: A Tutorial on Support Vector Machines for Pattern Recognition. Data Mining and Knowledge Discovery 2(2), 121–167 (1998)
Cover, T.M., Hart, P.E.: Nearest neighbor pattern classification. IEEE Transactions on Information Theory 13(1), 21–27 (1967)
Chen, L., Yap, K.-H.: A fuzzy K-nearest-neighbor algorithm to blind image deconvolution. IEEE Trans. Syst. Man Cybernet 3, 2049–2054 (2003)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Markowska-Kaczmar, U., Minda, P., Ociepa, K., Olszowy, D., Pawlikowski, R. (2011). Towards Automatic Image Annotation Supporting Document Understanding. In: Corchado, E., Kurzyński, M., Woźniak, M. (eds) Hybrid Artificial Intelligent Systems. HAIS 2011. Lecture Notes in Computer Science(), vol 6678. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-21219-2_53
Download citation
DOI: https://doi.org/10.1007/978-3-642-21219-2_53
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-21218-5
Online ISBN: 978-3-642-21219-2
eBook Packages: Computer ScienceComputer Science (R0)