Change detection in segmented images based on reference filters
M.A. Lebedev, A.Yu. Rubis, V.S. Gorbatsevich, Yu.V. Vizilter, O.V. Vygolov

 

FGUP “GosNIIAS”

Full text of article: Russian language.

Abstract:
In this paper we substantiate and develop a new comparative diffusion morphology technique based on filters that allow geometrical changes in the images under comparison. Two alternative interpretations of the morphological projector using “absolute” and “relative” definitions of a morphological image shape are proposed. Diffusion morphology based on superposition of two Pytiev’s projectors on mosaic shapes is considered. Diffusion morphology based on 'reference' filters is proposed as a generalization of the approach. The advantage of using diffusion morphology compared to classical Pytiev’s projective morphology in change detection applications is demonstrated.

Keywords:
mathematical morphology, image matching, diffusion maps.

Citation:
Lebedev MA, Rubis AYu, Gorbatsevich VS, Vizilter YuV, Vygolov OV. Change detection in segmented images based on reference filters. Computer Optics 2016; 40(1): 80-6. DOI: 10.18287/2412-6179-2016-40-1-80-86..

References:

  1. Pytiev YuP, Chulichkov AI. Methods of morphological image analysis [in Russian]. Moscow: “Fizmatlit” Publisher; 2010.
  2. Vizilter YuV, Gorbatsevich VS, Rubis AYu, Zheltov SYu. Shape-Based Image Matching Using Heat Kernels and Diffusion Maps. ISPRS Archives 2014; XL-3: 357-364.
  3. Vizilter YuV, Zheltov SuY, Bondarenko AV, Ososkov MV, Morzhin AV. Image processing and analysis in technical vision applications [in Russian]. Moscow: “Fizmatlit” Publisher; 2010.
  4. Pytiev YuP. Skew projectors and relative shapes in image morphological analysis [in Russian]. Computational Mathematics and Mathematical Physics 2013; 53(12): 2100-2122.
    © 2009, IPSI RAS
    Institution of Russian Academy of Sciences, Image Processing Systems Institute of RAS, Russia, 443001, Samara, Molodogvardeyskaya Street 151; e-mail: ko@smr.ru; Phones: +7 (846 2) 332-56-22, Fax: +7 (846 2) 332-56-20