期刊文章

#
THE SOLUTION OF PROBLEMS OF AMPELOGRAPHY BY USING ASC-ANALYSIS OF IMAGES OF LEAVES IN THEIR EXTERNAL CONTOURS (GENERALIZATION, ABSTRACTION, CLASSIFICATION AND IDENTIFICATION)
[2015]

####
Lutsenko Y. V.;
Bandyk D. K.;
Troshin L. P.;
Kuban State Agrarian University [Corporate Author]

THE SOLUTION OF PROBLEMS OF AMPELOGRAPHY BY USING ASC-ANALYSIS OF IMAGES OF LEAVES IN THEIR EXTERNAL CONTOURS (GENERALIZATION, ABSTRACTION, CLASSIFICATION AND IDENTIFICATION)

2015

Lutsenko Y. V.; Bandyk D. K.; Troshin L. P.

http://ej.kubagro.ru/2015/08/pdf/03.pdf

The article discusses the use of automatic systemic-cognitive analysis (ASC-analysis), its mathematical model is a system of information theory and software tools – an intellectual system called "Eidos" for the solution of some problems of ampelography: 1) digitization of scanned images of the leaves and creation of their mathematical models; 2) the formation of mathematical models of specific leaves using the spreading of information theory; 3) the formation of models of generalized images of leaves of various sorts; 4) comparing an image of a specific leaf with a generalized image of the leaf of different varieties and finding a quantitative degree of similarity and differences between them, i.e. the identification of the varieties on the leaf; 5) quantification of the similarities and differences of the varieties, i.e. cluster-constructive analysis of generalized images of the leaves of different varieties. We propose a new approach to digitizing images of leaves, based on using the polar coordinate system, the center of gravity of the image and its external contour. Before scanning images we may use transformation to standardize the position of the still images, their sizes and rotation angle. Therefore, the results of digitization and ASC-analysis of the images might be invariant (independent) relatively to their position, size and rotation. The specific shape of the contour of the leaf is regarded as noise information on the variety, including information about the true shape of the leaf of the class (clean signal) and noise, which distort this true form, originating in a random environment. Software tools of ASC-analysis – intellectual "Eidos" system ensures noise reduction and the selection of the signal about the true shape of the leaf of each variety on the basis of a number of noisy concrete examples of the leaves of this variety. This creates a one way form of a leaf of each class, free from their concrete implementations, i.e., the "Eidos" of these images (in the sense of Plato) is a prototype or archetype (in the Jungian sense) of the images

[Polythematic Online Scientific Journal of Kuban State Agrarian University]

2016/RU/RU2016_0.rdf

The article discusses the use of automatic systemic-cognitive analysis (ASC-analysis), its mathematical model is a system of information theory and software tools – an intellectual system called "Eidos" for the solution of some problems of ampelography: 1) digitization of scanned images of the leaves and creation of their mathematical models; 2) the formation of mathematical models of specific leaves using the spreading of information theory; 3) the formation of models of generalized images of leaves of various sorts; 4) comparing an image of a specific leaf with a generalized image of the leaf of different varieties and finding a quantitative degree of similarity and differences between them, i.e. the identification of the varieties on the leaf; 5) quantification of the similarities and differences of the varieties, i.e. cluster-constructive analysis of generalized images of the leaves of different varieties. We propose a new approach to digitizing images of leaves, based on using the polar coordinate system, the center of gravity of the image and its external contour. Before scanning images we may use transformation to standardize the position of the still images, their sizes and rotation angle. Therefore, the results of digitization and ASC-analysis of the images might be invariant (independent) relatively to their position, size and rotation. The specific shape of the contour of the leaf is regarded as noise information on the variety, including inform

ation about the true shape of the leaf of the class (clean signal) and noise, which distort this true form, originating in a random environment. Software tools of ASC-analysis – intellectual "Eidos" system ensures noise reduction and the selection of the signal about the true shape of the leaf of each variety on the basis of a number of noisy concrete examples of the leaves of this variety. This creates a one way form of a leaf of each class, free from their concrete implementations, i.e., the "Eidos" of these images (in the sense of Plato) is a prototype or archetype (in the Jungian sense) of the images