Abstract
For the medical image annotation task of ImageCLEF2006, we developed a refined SVM method. This method includes two stages, in which accordingly the coarse and fine classifications are performed. At the coarse stage, the common Support Vector Machines (SVM) method is used with the corresponding image feature, down-scaled low resolution pixel map (32x32). At the refined stage, the results from the first stage are refined following the steps: 1) select those images near to the borders of SVM classifiers, which are to be re-classified and selected by a predefined threshold of SVM similarity value; 2) form a new training dataset, to eliminate the influence of the great volume unbalance among classes; 3) use three classification methods and image features: 20x50 low resolution pixel maps feed into SVMs; SIFT features feed into Euclidean distance classifiers; 16x16 low resolution pixel maps feed into PCA classifiers. 4) combine the results from 3). At last the results from the two stages are combined to form the final classification result. Our experimental results showed that with the two-stage method a significant improvement of the classification rate has been achieved.
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
Lehmann, T., et al.: Automatic categorization of medical images for content-based retrieval and data mining. Computerized Medical Imaging and Graphics 29, 143–155 (2005)
Qiu, B., Xu, C.S., Tian, Q.: An automatic classification system applied in medical images. In: IEEE Intl. Conf. Multimedia & Expo (ICME) 2006, Toronto, Canada, July 9-12, 2006 (2006)
Itti, L., Koch, C.: A saliency-based search mechanism for overt and covert shifts of visual attention. Vision Research 40(10-12), 1489–1506 (2000)
Sebe, N., Tian, Q., Loupias, E., et al.: Evaluation of salient point techniques. Image and Vision Computing 21(13-14), 1087–1095 (2003)
Lowe, D.G.: Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision 60(2), 91–110 (2004)
Qiu, B., Racoceanu, D., Xu, C.S., Tian, Q.: Stripe: image feature based on a new grid method and its application in ImageCLEF. In: Ng, H.T., Leong, M.-K., Kan, M.-Y., Ji, D. (eds.) AIRS 2006. LNCS, vol. 4182, Springer, Heidelberg (2006)
Ranawana, R., Palade, V.: Multi classifier systems – a review and roadmap for developers. Journal of Hybrid Intelligent Systems (2006)
Müller, H., et al.: Overview of the ImageCLEFmed 2006 medical retrieval and annotation tasks. In: Working Notes for the CLEF 2006 Workshop, September 20-22, 2006. Alicante, Spain (2006)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Qiu, B. (2007). A Refined SVM Applied in Medical Image Annotation. In: Peters, C., et al. Evaluation of Multilingual and Multi-modal Information Retrieval. CLEF 2006. Lecture Notes in Computer Science, vol 4730. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-74999-8_85
Download citation
DOI: https://doi.org/10.1007/978-3-540-74999-8_85
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-74998-1
Online ISBN: 978-3-540-74999-8
eBook Packages: Computer ScienceComputer Science (R0)