Brigita Sziová

57190882650

Publications - 19

The effect of different consequent setting on the effectiveness of Kóczy-Hirota fuzzy rule interpolation in colonoscopy image classification

Brigita Sziová Raneem Ismail Hussein Taha Szilvia Nagy

Publication Name: 2022 57th International Scientific Conference on Information Communication and Energy Systems and Technologies Icest 2022

Publication Date: 2022-01-01

Volume: Unknown

Issue: Unknown

Page Range: Unknown

Description:

The effect of the refinement of the consequent categories in Kï¿czy-Hirota fuzzy rule interpolation is studied in the model system of colonoscopy image classification. The colonoscopy image segments are classified based on 99 antecedents, which are statistical parameters of the image segments. The number of consequents is increased from 2 - contains polyp, or does not contain polyp - to a more refined set distribution based on the polyp content of the image segment.

Open Access: Yes

DOI: 10.1109/ICEST55168.2022.9828693

On the Selection the Rule Membership Functions and Fuzzy Rule Interpolation

Ferenc Lilik Brigita Sziová Szonja Krisztina Szujo L. T. Koczy Szilvia Nagy

Publication Name: Studies in Computational Intelligence

Publication Date: 2022-01-01

Volume: 959

Issue: Unknown

Page Range: 111-118

Description:

In many real physical systems based fuzzy inference systems the rulebase is sparse thus interpolation or the change of the shape of the rules become necessary if the rulebase parameters are selected according to physical parameters of the systems. Often measurements contain noise and outlines which can draw the statistics of the measured data. In the present article based on two independent examples, namely telecommunication line evaluation and colonoscopy image processing, we study the effect of the selection of the rulebase parameters on the effectiveness of stabilized fuzzy KH interpolation.

Open Access: Yes

DOI: 10.1007/978-3-030-74970-5_13

On classical and fuzzy Hough transform in colonoscopy image processing

Brigita Sziová Raneem Ismail L. T. Koczy Szilvia Nagy

Publication Name: IEEE AFRICON Conference

Publication Date: 2021-09-13

Volume: 2021-September

Issue: Unknown

Page Range: Unknown

Description:

Hough transform is used to find lines on edge-filtered images that are given in parametric form. As the fuzzy extension of the Hough transform has been proven to be more robust in environments where the lines to be found by them are not strictly following the formula given by the parametric equation of the Hough transform due to noise and weak and blurred contours, in the following considerations, we study the applicability of the circular fuzzy Hough transform for analyzing colonoscopy pictures and detecting colorectal polyps.

Open Access: Yes

DOI: 10.1109/AFRICON51333.2021.9570897

Application of structural entropy and spatial filling factor in colonoscopy image classification

Brigita Sziová Zoltán Fazekas Szilvia Nagy

Publication Name: Entropy

Publication Date: 2021-08-01

Volume: 23

Issue: 8

Page Range: Unknown

Description:

For finding colorectal polyps the standard method relies on the techniques and devices of colonoscopy and the medical expertise of the gastroenterologist. In case of images acquired through colonoscopes the automatic segmentation of the polyps from their environment (i.e., from the bowel wall) is an essential task within computer aided diagnosis system development. As the number of the publicly available polyp images in various databases is still rather limited, it is important to develop metaheuristic methods, such as fuzzy inference methods, along with the deep learning algorithms to improve and validate detection and classification techniques. In the present manuscript firstly a fuzzy rule set is generated and validated. The former process is based on a statistical approach and makes use of histograms of the antecedents. Secondly, a method for selecting relevant antecedent variables is presented. The selection is based on the comparision of the histograms computed from the measured values for the training set. Then the inclusion of the Rényi-entropy-based structural entropy and the spatial filling factor into the set of input variables is proposed and assessed. The beneficial effect of including the mentioned structural entropy of the entropies from the hue and saturation (H and S) colour channels resulted in 65% true positive and 60% true negative rate of the classification for an advantageously selected set of antecedents when working with HSV images.

Open Access: Yes

DOI: 10.3390/e23080936

On the Applicability of Fuzzy Rule Interpolation and Wavelet Analysis in Colorectal Image Segment Classification

Ferenc Lilik Brigita Sziová Melinda Kovacs L. T. Koczy Szilvia Nagy

Publication Name: Studies in Fuzziness and Soft Computing

Publication Date: 2021-01-01

Volume: 394

Issue: Unknown

Page Range: 243-255

Description:

The automatic detection of colorectal polyps could serve as a visual aid for gastroenterologists when screening the population for colorectal cancer. A fuzzy inference based method was developed for determining whether a segment of an image has polyps. Its antecedent dimensions were the mean pixel intensity, the intensity’s standard deviation, the edge density, the structural entropies and the gradients, not only for the original image segments, but for its wavelet transformed versions. The method performed moderately well, even though the number of the input parameters was very large. In the present contribution we studied, that based on the necessary and usually applied conditions of the applicability of fuzzy rule interpolation, which antecedent dimensions should remain, and how omitting the other input parameters influences the results of the method.

Open Access: Yes

DOI: 10.1007/978-3-030-54341-9_21

The Effects of Preprocessing on Colorectal Polyp Detecting by Fuzzy Algorithm

Brigita Sziová L. T. Koczy Szilvia Nagy

Publication Name: Studies in Fuzziness and Soft Computing

Publication Date: 2021-01-01

Volume: 393

Issue: Unknown

Page Range: 347-357

Description:

In the following study the effects of two image preprocessing methods, namely Gaussian filtering and Wiener filtering, is studied on the results of a fuzzy inference method previously developed by the authors, for determining whether a colonoscopy picture segment contains any colorectal polyp. As earlier results show that less blurry, less compressed and less noisy images tend to be better classifiable, the effects of noise suppression with a Gaussian filter, which makes the images also blurrier, was beneficial on noisy, compressed images, and rather maleficent in good quality pictures. The effects of the Wiener filter, which both decreases noise and enhances edges, did not really manifest in classification improvement.

Open Access: Yes

DOI: 10.1007/978-3-030-47124-8_28

Fuzzy rulebase parameter determination for stabilized KH interpolation based detection of colorectal polyps on colonoscopy images

Ferenc Lilik Brigita Sziová Raneem Ismail L. T. Koczy Szilvia Nagy

Publication Name: IEEE International Conference on Fuzzy Systems

Publication Date: 2020-07-01

Volume: 2020-July

Issue: Unknown

Page Range: Unknown

Description:

In the case of computer aided diagnosis it is advantageous to apply such computational intelligence methods, that can be related to direct measured data by means easily understandable to medical experts. Fuzzy reasoning, if the rulebase is generated from plausible statistical parameters of the image to be analysed, is easy to understand thus can be easily accepted by the society.In the case of colorectal polyps, which might develop into colorectal cancer, thus the population-wide screening would be advisable, more methods are available, but none of them is accepted as standard and effective method. A method based on simple statistical parameters and entropies of image segments is presented, and the effect of determining the rulebase parameters on the efficiency of finding the polyp segment is studied for stabilized Koczy-Hirota rule interpolation.

Open Access: Yes

DOI: 10.1109/FUZZ48607.2020.9177839

The effect of background and outlier subtraction on the structural entropy of two-dimensional measured data

Brigita Sziová Levente Solecki Szilvia Nagy

Publication Name: International Journal of Reasoning Based Intelligent Systems

Publication Date: 2020-01-01

Volume: 12

Issue: 3

Page Range: 200-209

Description:

For colonoscopy images the main information is in the fine structure of the surface of the bowel or colorectal polyps, similarly to the case of combustion engine cylinder surface scans, where the grooving and wear can be detected from the fine pattern superposed to a cylinder curvature. In both cases appear outliers, colonoscopy images have many reflections, whereas the roughness scanners detect small dust particles as well as the micron scale vibrations from the environment. The method presented in this paper takes care of both the problems using histogram stretching together with a special type of filtering. Also, masks are introduced in order to control the effect of the operators. The effects of the processing steps on the structural entropy of the image is also studied, as structural entropies are used in characterisation of the images. By removing the background makes the structural entropies much smaller, and by suppressing the outliers the structural entropies increase.

Open Access: Yes

DOI: DOI not available

On wavelet based enhancing possibilities of fuzzy classification methods

Ferenc Lilik Brigita Sziová Levente Solecki L. T. Koczy Szilvia Nagy

Publication Name: Journal of Automation Mobile Robotics and Intelligent Systems

Publication Date: 2020-01-01

Volume: 14

Issue: 2

Page Range: 32-41

Description:

If the antecedents of a fuzzy classification method are derived from pictures or measured data, it might have too many dimensions to handle. A classification scheme based on such data has to apply a careful selection or processing of the measured results: either a sampling, re-sampling is necessary. or the usage of functions, transfor-mations that reduce the long, high dimensional observed data vector or matrix into a single point or to a low number of points. Wavelet analysis can be useful in such cases in two ways. As the number of resulting points of the wavelet analysis is approximately half at each filters, a consecutive application of wavelet transform can compress the me-asurement data, thus reducing the dimensionality of the signal, i.e., the antecedent. An SHDSL telecommunication line evaluation is used to demonstrate this type of appli-cability, wavelets help in this case to overcome the pro-blem of a one dimensional signal sampling. In the case of using statistical functions, like mean, variance, gradient, edge density, Shannon or Rényi entropies for the extraction of the information from a picture or a measured data set, and they don not produce enough information for performing the classification well enough, one or two consecutive steps of wavelet analysis and applying the same functions for the thus resulting data can extend the number of antecedents, and can dis-till such parameters that were invisible for these functions in the original data set. We give two examples, two fuzzy classification schemes to show the improvement caused by wavelet analysis: a measured surface of a combustion engine cylinder and a colonoscopy picture. In the case of the first example the wear degree is to be deter-mine, in the case of the second one, the roundish polyp content of the picture. In the first case the applied statistical functions are Rényi entropy differences, the structural entropies, in the second case mean, standard deviation, Canny filtered edge density, gradients and the entropies. In all the examples stabilized KH rule interpolation was used to treat sparse rulebases.

Open Access: Yes

DOI: 10.14313/JAMRIS/2-2020/18

Applying fuzzy hough transform for identifying honed microgeometrical surfaces

Brigita Sziová Levente Solecki Balázs Sarkadi-Nagy L. T. Koczy Szilvia Nagy

Publication Name: Studies in Computational Intelligence

Publication Date: 2020-01-01

Volume: 819

Issue: Unknown

Page Range: 35-42

Description:

In the measurement of microgeometrical surfaces it is useful if the same location can be found on a surface for two or more different and independent measurements, as in this case not only statistical parameters of the measurements can be compared, but direct differences can be calculated. Honing is a typical surface processing method resulting in pattern consisting of straight valleys crossing at various angles. Honing pattern is of great help to find a special location. The main goal of this article is to find a method that is able to give some characteristic points that can be used for fitting two measured surfaces together. Hough transform is used in finding straight lines in an image or map, thus it could be used for determining crossing points of the honed surface. However, classical Hough transform either finds way too many disturbing lines in the case of a typical honed surface or almost none, depending on the parameter selection. To solve this rapid changing in the number of the resulting lines, we introduced fuzzy Hough transform. If a fuzzified version of the weights of the individual points in the Hough transform is used, the inverse of the transform becomes clearer, resulting in a pattern more suitable for finding the same location on two measured versions of a surface.

Open Access: Yes

DOI: 10.1007/978-3-030-16024-1_5

On wavelet based enhancing possibilities of fuzzy classification methods

Ferenc Lilik Brigita Sziová Levente Solecki L. T. Koczy Szilvia Nagy

Publication Name: Advances in Intelligent Systems and Computing

Publication Date: 2020-01-01

Volume: 945

Issue: Unknown

Page Range: 56-73

Description:

If the antecedents of a fuzzy classification method are derived from pictures or measured data, it might have too many dimensions to handle. A classification scheme based on such data has to apply a careful selection or processing of the measured results: either a sampling, re-sampling is necessary or the usage of functions, transformations that reduce the long, high dimensional observed data vector or matrix into a single point or to a low number of points. Wavelet analysis can be useful in such cases in two ways. As the number of resulting points of the wavelet analysis is approximately half at each filters, a consecutive application of wavelet transform can compress the measurement data, thus reducing the dimensionality of the signal, i.e., the antecedent. An SHDSL telecommunication line evaluation is used to demonstrate this type of applicability, wavelets help in this case to overcome the problem of a one dimensional signal sampling. In the case of using statistical functions, like mean, variance, gradient, edge density, Shannon or Rényi entropies for the extraction of the information from a picture or a measured data set, and they don not produce enough information for performing the classification well enough, one or two consecutive steps of wavelet analysis and applying the same functions for the thus resulting data can extend the number of antecedents, and can distill such parameters that were invisible for these functions in the original data set. We give two examples, two fuzzy classification schemes to show the improvement caused by wavelet analysis: a measured surface of a combustion engine cylinder and a colonoscopy picture. In the case of the first example the wear degree is to be determine, in the case of the second one, the roundish polyp content of the picture. In the first case the applied statistical functions are Rényi entropy differences, the structural entropies, in the second case mean, standard deviation, Canny filtered edge density, gradients and the entropies. In all the examples stabilized KH rule interpolation was used to treat sparse rulebases. The preliminary version of this paper was presented at the 3rd Conference on Information Technology, Systems Research and Computational Physics, 2–5 July 2018, Cracow, Poland [1].

Open Access: Yes

DOI: 10.1007/978-3-030-18058-4_5

Fuzzy Hough transformation in aiding computer tomography based liver diagnosis

Brigita Sziová Melinda Kovacs L. T. Koczy Szilvia Nagy

Publication Name: IEEE AFRICON Conference

Publication Date: 2019-09-01

Volume: 2019-September

Issue: Unknown

Page Range: Unknown

Description:

In the liver many types of roundish lesions can appear, as well as near the liver. Finding the contour of such objects can improve both the segmentation of the liver from its environment, and the segmentation of the lesions within the liver. However, classical Hough transform, which is one of the main methods for finding objects described by a predefined parameterized formula, usually fails to identify these object as they possess not perfectly round or elliptic contours. A fuzzification of the Hough transform is described and suggested for using in image preprocessing for liver diagnosis based on CT images in this paper. Fuzzifying the Hough transform improves the detection of roundish contours.

Open Access: Yes

DOI: 10.1109/AFRICON46755.2019.9133793

On structural entropy and spatial filling factor analysis of colonoscopy pictures

Brigita Sziová János Pipek Szilvia Nagy

Publication Name: Entropy

Publication Date: 2019-03-01

Volume: 21

Issue: 3

Page Range: Unknown

Description:

Colonoscopy is the standard device for diagnosing colorectal cancer, which develops from little lesions on the bowel wall called polyps. The Rényi entropies-based structural entropy and spatial filling factor are two scale- and resolution-independent quantities that characterize the shape of a probability distribution with the help of characteristic curves of the structural entropy-spatial filling factor map. This alternative definition of structural entropy is easy to calculate, independent of the image resolution, and does not require the calculation of neighbor statistics, unlike the other graph-based structural entropies.The distant goal of this study was to help computer aided diagnosis in finding colorectal polyps by making the Rényi entropy based structural entropy more understood. The direct goal was to determine characteristic curves that can differentiate between polyps and other structure on the picture. After analyzing the distribution of colonoscopy picture color channels, the typical structures were modeled with simple geometrical functions and the structural entropy-spatial filling factor characteristic curves were determined for these model structures for various parameter sets. A colonoscopy image analying method, i.e., the line- or column-wise scanning of the picture, was also tested, with satisfactory matching of the characteristic curve and the image.

Open Access: Yes

DOI: 10.3390/e21030256

The effect of image feature qualifiers on fuzzy colorectal polyp detection schemes using KH interpolation - Towards hierarchical fuzzy classification of coloscopic still images

Brigita Sziová L. T. Koczy Szilvia Nagy

Publication Name: IEEE International Conference on Fuzzy Systems

Publication Date: 2018-10-12

Volume: 2018-July

Issue: Unknown

Page Range: Unknown

Description:

Previous studies showed that intensities, intensity variation, edge densities, structural entropies of colonoscopy images and their wavelet transforms are good candidates for being selected as antecedents in fuzzy decision methods using KH interpolation for determining whether an image segment contains colorectal polyp segment. In the present consideration, we check which possible antecedent dimensions need interpolation, whether the average and variation of the gradients makes the classification more effective and whether some of the features can be omitted for some classes of images. The method is tested on three available databases consisting of images of three different resolutions, and according to the results, different resolutions, different types of polyps require different classification schemes, thus a hierarchical decision system needs to be built.

Open Access: Yes

DOI: 10.1109/FUZZ-IEEE.2018.8491479

A survey of the applications of fuzzy methods in recommender systems

P. Földesi Alex Tormási Brigita Sziová L. T. Koczy

Publication Name: Studies in Fuzziness and Soft Computing

Publication Date: 2018-01-01

Volume: 361

Issue: Unknown

Page Range: 483-495

Description:

In the past half century of fuzzy systems they were used to solve a wide range of complex problems, and the field of recommendation is no exception. The mathematical properties and the ability to efficiently process uncertain data enable fuzzy systems to face the common challenges in recommender systems. The main contribution of this paper is to give a comprehensive literature overview of various fuzzy based approaches to the solving of common problems and tasks in recommendation systems. As a conclusion possible new areas of research are discussed.

Open Access: Yes

DOI: 10.1007/978-3-319-75408-6_37

Detecting contours of pathological forms in colonoscopy images using a hybrid method

Plamen Petrov Veska Georgieva Brigita Sziová Szilvia Nagy

Publication Name: Communication Electromagnetics and Medical Application

Publication Date: 2018-01-01

Volume: 2018-October

Issue: Unknown

Page Range: 27-30

Description:

As colonoscopy is needed for screening colorectal polyps, and the first step of classification these polyps is recognizing them, it is worth to research, whether the colonoscopy databases could be improved by image processing and contour detection. In the following considerations a reflection filtering and background subtraction with large-sized mean filter is used as image preprocessing tools, and hybrid method for segmentation of pathological forms, based on template matching and active contour model as contour fitting for segmentation of the image is made.

Open Access: Yes

DOI: DOI not available

The effect of wavelet analyis on entropy based fuzzy classification of colonoscopy images

Brigita Sziová L. T. Koczy Szilvia Nagy

Publication Name: Iwaciii 2017 5th International Workshop on Advanced Computational Intelligence and Intelligent Informatics

Publication Date: 2017-01-01

Volume: Unknown

Issue: Unknown

Page Range: Unknown

Description:

Colorectal polyp detection is important in preventing cancer. Structural entropy can detect different structures of distributions, such as image pixel brightness. Wavelet analysis can help in separating large-scale and fine resolution behaviour. In the method presented in this paper, the colonoscopy images are separated into segments, and a classification scheme is built in order to determine, whether there is a polyp part in the image segment or not. Without wavelet analysis edge density and structural entropy can be a basis of fuzzy classification for the polyp content of only good quality colonoscopy images, and still has about 10 percent false classification. In this contribution the effect of wavelet analysis on the classification scheme is studied.

Open Access: Yes

DOI: DOI not available

Multiresolution modeling of cavity resonators in microwave systems

András Fehér Brigita Sziová János Pipek Szilvia Nagy

Publication Name: 2016 13th International Conference on Synthesis Modeling Analysis and Simulation Methods and Applications to Circuit Design Smacd 2016

Publication Date: 2016-07-25

Volume: Unknown

Issue: Unknown

Page Range: Unknown

Description:

Multiresolution analysis or wavelet analysis provides a toolbox not only for signal processing, but also for synthesis of complex systems. Wavelets can be used for modeling complex parts of microwave circuits, such as cavity resonators. The differential equations describing the physical behavior of the device can be discretized using multiple resolutions simultaneously, i.e., high resolutions, where the details of the geometry demand it, and low resolutions, where the geometry is smooth. Using wavelet analysis offers the possibility of systematic and adaptive refinement, where the result is not sufficiently precise. Our method gives an approximation for the error of the solution in order to make it possible to decide, whether refinements are necessary.

Open Access: Yes

DOI: 10.1109/SMACD.2016.7520651

Optimization of the prediction of second refined wavelet coefficients in electron structure calculations

Brigita Sziová János Pipek Szilvia Nagy

Publication Name: Open Physics

Publication Date: 2016-01-01

Volume: 14

Issue: 1

Page Range: 643-650

Description:

In wavelet-based solution of eigenvalue-type differential equations, like the Schrödinger equation, refinement in the resolution of the solution is a costly task, as the number of the potential coefficients in the wavelet expansion of the solution increases exponentially with the resolution. Predicting the magnitude of the next resolution level coefficients from an already existing solution in an economic way helps to either refine the solution,or to select the coefficients, which are to be included into the next resolution level calculations, or to estimate the magnitude of the error of the solution. However, after accepting a solution with a predicted refinement as a basis, the error can still be estimated by a second prediction, i.e., from a prediction to the second finer resolution level coefficients. These secondary predicted coefficients are proven to be oscillating around the values of the wavelet expansion coefficients of the exact solution. The optimal averaging of these coefficients is presented in the following paper using a sliding average with three optimized coefficients for simple, one-dimensional electron structures.

Open Access: Yes

DOI: 10.1515/phys-2016-0063