Abstract
The authors put forward a new method of comparative analysis and recognition of 2D contours shape, based on an automatic search of regularities by co-occurrence matrices of contours pixels. The shape of contours of the 1st (cecum and the ascending colon) segment and the 5th (the rectum) segment of large intestine (colon) in 83 patients were analyzed. The regularities obtained were used as diagnostic signs. The results of computerized diagnosis coincided with verified clinical conclusions.
Preview
Unable to display preview. Download preview PDF.
References
S. Frydrychowicz. The local form — a new method for contour segmentation. Proc. of 5th Int. Conf. on Image Analysis and Processing, Positano, Italy, Sep. 1988, pp. 322–326.
V.A.Kovalev and N.V.Mytzik. Automatic construction of structural features of objects shape for searching in video data bases. In: V.P.Gladun(eds.): Problems of design and application of knowledge bases. Kiev: Institute of Cybernetic 1992, pp. 35–49 (Russ.).
A.D.Zakrewsky. Revealing implicant conform in the boolean features space and pattern recognition. Cybernetic, No. 1, 1982, pp. 1–6 (Russ.).
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1993 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Kovalev, V.A., Mytzik, N.V. (1993). Computer analysis of the large intestine contours for the recognition of diseases. In: Chetverikov, D., Kropatsch, W.G. (eds) Computer Analysis of Images and Patterns. CAIP 1993. Lecture Notes in Computer Science, vol 719. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-57233-3_85
Download citation
DOI: https://doi.org/10.1007/3-540-57233-3_85
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-57233-6
Online ISBN: 978-3-540-47980-2
eBook Packages: Springer Book Archive