Translator Disclaimer
1 April 2008 Polygonal approximation of contours based on the turning angle function
Author Affiliations +
The turning angle function has been used as a signatureto represent the shape of a given contour with the aim of analysis ofshape and content-based image retrieval. We propose a methodthat uses the turning angle function to derive a polygonal model ofthe given contour in such a manner as to preserve the importantdetails in the contour. The preservation of diagnostically significantfeatures present in the contours of breast masses in mammogramsare important to discriminate between benign masses and malignanttumors. To evaluate the practical utility of the proposed polygonalmodeling method in terms of the efficiency in the classification ofbreast masses, we derive an index of spiculation SIPMTF and a measureof fractional concavity Fcc from the models obtained and comparethe results with those provided by two methods proposed inprevious related works. The features SIPMTF and Fcc were testedwith a set of 111 contours, of which 65 are related to benign massesand 46 are related to malignant tumors. High classification accuraciesof 0.93 with SIPMTF and 0.91 with Fcc were obtained, in terms ofthe area under the receiver operating characteristics curve, with adata compression of 0.067 on the average.
©(2008) Society of Photo-Optical Instrumentation Engineers (SPIE)
Rangaraj Mandayam Rangayyan, Denise Guliato, Juliano D. de Carvalho, and Sergio A. Santiago "Polygonal approximation of contours based on the turning angle function," Journal of Electronic Imaging 17(2), 023016 (1 April 2008).
Published: 1 April 2008

Back to Top