Yuriy Batko
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yuriy Batko has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
- Oleh Berezsky
Department of Computer Engineering, West Ukrainian National University, 46009 Ternopil, Ukraine
6 shared publications - Grygoriy Melnyk
West Ukrainian National University
5 shared publications - Oleh Pitsun
Department of Computer Engineering, West Ukrainian National University, Lvivska, 11, 46003 Ternopil, Ukraine
3 shared publications - Serhiy Verbovyy
Computer Engineering Department, Ternopil National Economic University, Ternopil, Ukraine
2 shared publications Dolynyuk T.M.
1 shared publicationG.M. Melnyk
Computer Engineering Department, Ternopil National Economic University, Ukraine, Ternopil
1 shared publication
Latest Publications
- Open Access
- 30 July 2024
- Published by MDPI AG in Preprints.org
MLOps Approach for Automatic Image Segmentation Based on U-Net
The usage of classic segmentation methods has drastically decreased recently. Implementation of convolutional neural networks and their modifications leads to significantly improved results. With the help of U-net, you can perform automatic segmentation. However, this requires significantly more hardware and software resources. The use of cloud computing now provides a wide range of possibilities, which allows processing and sharing the obtained experience and results to improve the quality of diagnosis. This article presents an approach to implementing MLOPS for automatic image segmentation using U-net technology. The approach's key feature is the developed software block that allows the creation of a dataset based on given rules. The infrastructure also supports automatically deploying the necessary environment on the cloud, particularly on DigitalOcean.
- 30 July 2024
- Published by MDPI AG in Preprints.org
Open AccessMLOps Approach for Automatic Image Segmentation Based on U-Net
The usage of classic segmentation methods has drastically decreased recently. Implementation of convolutional neural networks and their modifications leads to significantly improved results. With the help of U-net, you can perform automatic segmentation. However, this requires significantly more hardware and software resources. The use of cloud computing now provides a wide range of possibilities, which allows processing and sharing the obtained experience and results to improve the quality of diagnosis. This article presents an approach to implementing MLOPS for automatic image segmentation using U-net technology. The approach's key feature is the developed software block that allows the creation of a dataset based on given rules. The infrastructure also supports automatically deploying the necessary environment on the cloud, particularly on DigitalOcean.
- Open Access
- 30 June 2023
- Published by Ukrainian Research and Design Institute of Building Materials and Products in European Science
- No. sge51-02,p. 9-31
CLASSIFICATION AND CHARACTERIZATION OF DIGITAL IMAGE PROCESSING ALGORITHMS
The chapter examines modern approaches to the classification and characterization of digital image processing algorithms. The theoretical foundations of digital image processing are presented, and a classification of algorithms is provided according to th
- 30 June 2023
- Published by Ukrainian Research and Design Institute of Building Materials and Products in European Science
- No. sge51-02,p. 9-31
Open AccessCLASSIFICATION AND CHARACTERIZATION OF DIGITAL IMAGE PROCESSING ALGORITHMS
The chapter examines modern approaches to the classification and characterization of digital image processing algorithms. The theoretical foundations of digital image processing are presented, and a classification of algorithms is provided according to th
- 27 December 2019
- Published by National Academy of Sciences of Ukraine (Co. LTD Ukrinformnauka) (Publications) in Artificial Intelligence
- Vol. 24 (3-4) , 73-81
Paralleling process of searching objects on cytological images by a template
Modern approaches to finding image elements are analyzed. An algorithm for searching micro-objects in histological and cytological images using a database is developed. A tiered-parallel form of parallelization of the process of micro-object pattern search is designed. Micro-object pattern search software is implemented. The obtained result show that the operating time of the software module with parallelization speeds up the processing on average by 20% for cytological images
- 27 December 2019
- Published by National Academy of Sciences of Ukraine (Co. LTD Ukrinformnauka) (Publications) in Artificial Intelligence
- Vol. 24 (3-4) , 73-81
Paralleling process of searching objects on cytological images by a template
Modern approaches to finding image elements are analyzed. An algorithm for searching micro-objects in histological and cytological images using a database is developed. A tiered-parallel form of parallelization of the process of micro-object pattern search is designed. Micro-object pattern search software is implemented. The obtained result show that the operating time of the software module with parallelization speeds up the processing on average by 20% for cytological images
- Open Access
- 25 December 2017
- Published by Private Company Technology Center in Eastern-European Journal of Enterprise Technologies
- Vol. 6 (4 (90)) , 35-44
Development of algorithms for biomedical image segmentation based on preliminary markup and texture attributes
Biomedical images are used for diagnosis and treatment of malignant neoplasms. Images of normal and pathological cells and tissues are derived using light microscopes. These images are the objects of study in histology and cytology. One of the most important stages in the automation of measuring optical and geometrical parameters of images is the segmentation of micro objects. Analysis of biomedical images is complicated due to the highly variable parameters and weak contrast in most micro objects.The use of point connections for segmenting the images has several advantages: processing images of any type, splitting micro objects that are in contact, insensitivity to noise. A method of image segmentation based on preliminary markup implies splitting a color image into homogeneous regions, calculating the coefficient of relation between adjacent points, and merging points into homogeneous regions. The algorithm allows for the automated segmentation.A texture segmentation method involves computing values of spatial moments for each point of the image. A feature space, obtained in this way, is segmented by the algorithm. The algorithm calculates thresholds based on mathematical expectation. This makes it possible to identify such complex micro objects as the layers of cells, cross-sections of blood vessels and ducts.The quality of segmentation was estimated using a metric approach. The developed segmentation algorithms made it possible to improve quality of the biomedical image segmentation by 18−21 % on average
- 25 December 2017
- Published by Private Company Technology Center in Eastern-European Journal of Enterprise Technologies
- Vol. 6 (4 (90)) , 35-44
Open AccessDevelopment of algorithms for biomedical image segmentation based on preliminary markup and texture attributes
Biomedical images are used for diagnosis and treatment of malignant neoplasms. Images of normal and pathological cells and tissues are derived using light microscopes. These images are the objects of study in histology and cytology. One of the most important stages in the automation of measuring optical and geometrical parameters of images is the segmentation of micro objects. Analysis of biomedical images is complicated due to the highly variable parameters and weak contrast in most micro objects.The use of point connections for segmenting the images has several advantages: processing images of any type, splitting micro objects that are in contact, insensitivity to noise. A method of image segmentation based on preliminary markup implies splitting a color image into homogeneous regions, calculating the coefficient of relation between adjacent points, and merging points into homogeneous regions. The algorithm allows for the automated segmentation.A texture segmentation method involves computing values of spatial moments for each point of the image. A feature space, obtained in this way, is segmented by the algorithm. The algorithm calculates thresholds based on mathematical expectation. This makes it possible to identify such complex micro objects as the layers of cells, cross-sections of blood vessels and ducts.The quality of segmentation was estimated using a metric approach. The developed segmentation algorithms made it possible to improve quality of the biomedical image segmentation by 18−21 % on average
- 1 September 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1, 40-43
Evaluation of automated system conceptual model for oncology diagnosing
The purpose of this research study is to investigate the problems of design and requirements to diagnostic automated systems based on image processing. To realize the research purpose, the authors designed a conceptual model, a use case diagram, and a prototype of automated system object model.
- 1 September 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1, 40-43
Evaluation of automated system conceptual model for oncology diagnosing
The purpose of this research study is to investigate the problems of design and requirements to diagnostic automated systems based on image processing. To realize the research purpose, the authors designed a conceptual model, a use case diagram, and a prototype of automated system object model.
- 13 October 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 33-36
Regions matching algorithms analysis to quantify the image segmentation results
In the paper the matching algorithms of region images are analyzed. The work also presents their advantages and disadvantages. The comparing images algorithm of regions is developed on the basis of the measured chords. The comparison regions algorithms are used to evaluate segmentation algorithms in the Gromov-Hausdorff metric. The algorithm of metric evaluation is developed as an example of biomedical images segmentation.
- 13 October 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 33-36
Regions matching algorithms analysis to quantify the image segmentation results
In the paper the matching algorithms of region images are analyzed. The work also presents their advantages and disadvantages. The comparing images algorithm of regions is developed on the basis of the measured chords. The comparison regions algorithms are used to evaluate segmentation algorithms in the Gromov-Hausdorff metric. The algorithm of metric evaluation is developed as an example of biomedical images segmentation.
- 6 October 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 121-124
Graphical interface of hybrid intelligent systems for biomedical imaging analysis
Biomedical images analysis systems become popular nowadays. Their use can reduce the expenses for patients' transporting to hospitals as well as allows receiving some medical advice from experts in relevant fields. Among the deficiencies that may affect the use of these systems we can name the imperfection of the user interface. Overload of visual elements workspaces reduce the effectiveness of software systems to work with them and improve the training of users. The hybrid system includes: dictionary of pathological conditions of cancer, a database of numerical features of microobjects, annotated images, the knowledge base of qualitative features microobjects, conclusion subsystems conclusion.
- 6 October 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 121-124
Graphical interface of hybrid intelligent systems for biomedical imaging analysis
Biomedical images analysis systems become popular nowadays. Their use can reduce the expenses for patients' transporting to hospitals as well as allows receiving some medical advice from experts in relevant fields. Among the deficiencies that may affect the use of these systems we can name the imperfection of the user interface. Overload of visual elements workspaces reduce the effectiveness of software systems to work with them and improve the training of users. The hybrid system includes: dictionary of pathological conditions of cancer, a database of numerical features of microobjects, annotated images, the knowledge base of qualitative features microobjects, conclusion subsystems conclusion.
- 1 September 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1, 287-292
Segmentation of cytological and histological images of breast cancer cells
Comparative analysis of the biomedical image segmentation methods is presented in this paper. The segmentation methods are offered on the basis of previous labeling and spatial moments. Experimental results show that the developed methods have higher accuracy by signal-noise ratio (up to 40%) compared to the nowadays known.
- 1 September 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1, 287-292
Segmentation of cytological and histological images of breast cancer cells
Comparative analysis of the biomedical image segmentation methods is presented in this paper. The segmentation methods are offered on the basis of previous labeling and spatial moments. Experimental results show that the developed methods have higher accuracy by signal-noise ratio (up to 40%) compared to the nowadays known.
- 1 September 2009
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 409-413
Synthesis of complex images on the basis of theory of crystallographic groups
The article deals with a group-theoretical approach, which is proposed to the synthesis of symmetric and asymmetric images. It also describes algorithms of image synthesis. Integrated environment of programming Visual C++ Express Edition and opened library of functions of computer vision Open CV is used for software implementation of the proposed algorithms.
- 1 September 2009
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 409-413
Synthesis of complex images on the basis of theory of crystallographic groups
The article deals with a group-theoretical approach, which is proposed to the synthesis of symmetric and asymmetric images. It also describes algorithms of image synthesis. Integrated environment of programming Visual C++ Express Edition and opened library of functions of computer vision Open CV is used for software implementation of the proposed algorithms.
- 1 February 2006
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 642-644
Algorithm of Determination of Image Contours of Biological Nature
Algorithms of selection of contours of images are explored, algorithm of determination of external contour of images is offered and analyzed, and also an example of program realization of offered algorithm and results of its work is introduced.
- 1 February 2006
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 642-644
Algorithm of Determination of Image Contours of Biological Nature
Algorithms of selection of contours of images are explored, algorithm of determination of external contour of images is offered and analyzed, and also an example of program realization of offered algorithm and results of its work is introduced.