Full text of article: Russian language.

 PDF

Abstract:
A "width of a shape" concept considered in relation to variable-width objects is used as the integral shape descriptor for image recognition tasks. The approach to the definition of this concept is based on covering the figure of interest with certain-size disks. A function that defines the area of disk cover against the disk size is used as a shape descriptor. An analytical method for calculating the area of disk cover for polygonal figures is proposed. The possibility to approximate by polygonal figures binary raster images and objects with non-linear boundaries makes the approach universal. The proposed method is based on the medial representation of objects as a skeleton and a radial function. The method provides high accuracy and computational efficiency. The efficiency of the proposed shape descriptor is illustrated by the example of its application to the digital font recognition problem.

Keywords:
disk cover, polygonal figure, medial representation, skeleton, radial function, bicircle.

Citation:
Lomov NA, Mestetskiy LM. Area of the disk cover as an image shape descriptor. Computer Optics 2016; 40(4): 516-525. DOI: 10.18287/2412-6179-2016-40-4-516-525.

References:

1. Maragos P. Pattern Spectrum and Multiscale Shape Representation. IEEE Trans On Pattern Analysis and Machine Intelligence 1989; 11(7): 701-716.
2. Serra J. Image Analysis and Mathematical Morphology. London: Academic Press; 1982.
3. Ramirez-Cortes JM, Gomez-Gil P, Sanchez-Perez G, Baez-Lopez D. A Feature extraction method based on the pattern spectrum for hand shape biometry. Proc World Congress on Engineering and Computer Science 2008.
4. Vizilter YuV, Sidyakin SV. Morphological spectra [in Russian]. Computer vision in control systems 2012. Proceedings of the scientific-technical conference, Moscow: 14-16 March 2012: 234-241.
5. Vizilter YuV, Sidyakin SV. Comparison of shapes of two-dimensional figures with the use of morphological spectra and EMD metrics. Pattern Recognition and Image Analysis 2015; 25(3): 365-372.
6. Mestetskiy LM. Continuous morphology of binary images: figures, skeletons, circulars [in Russian]. Moscow: “Fizmatlit” Publisher; 2009.
7. Mestetskiy LM. Medial width of a figure – an image shape descriptor [in Russian]. Machine Learning and Data Analysis 2014; 1(9): 1291-1318.
8. Mestetskiy LM., Zak EM., Lomov NA. Recognition of flexible object shape based on width spectrum [in Russian]. The Privolzhsky Scientific Journal 2014; 4(32): 59-67.
9. Yakupov E, Petrova I, Fridman G, Korolkova A, Levin B. 2008-2014 – PARATYPE Originals – Digital Typefaces. Moscow: 2015.

---

© 2009, IPSI RAS
Institution of Russian Academy of Sciences, Image Processing Systems Institute of RAS, Russia, 443001, Samara, Molodogvardeyskaya Street 151; E-mail: journal@computeroptics.ru; Phones: +7 (846) 332-56-22, Fax: +7 (846) 332-56-20