Tomislav Kartalov | Ss. Cyril & Methodius University in Skopje (original) (raw)

Papers by Tomislav Kartalov

2023 30th International Conference on Systems, Signals and Image Processing (IWSSIP)

2023 30th International Conference on Systems, Signals and Image Processing (IWSSIP)

Informatics in Education

With the development of technology allowing for a rapid expansion of data science and machine lea... more With the development of technology allowing for a rapid expansion of data science and machine learning in our everyday lives, a significant gap is forming in the global job market where the demand for qualified workers in these fields cannot be properly satisfied. This worrying trend calls for an immediate action in education, where these skills must be taught to students at all levels in an efficient and up-to-date manner. This paper gives an overview of the current state of data science and machine learning education globally and both at the high school and university levels, while outlining some illustrative and positive examples. Special focus is given to vocational education and training (VET), where the teaching of these skills is at its very beginning. Also presented and analysed are survey results concerning VET students in Slovenia, Serbia, and North Macedonia, and their knowledge, interests, and prerequisites regarding data science and machine learning. These results confi...

2023 30th International Conference on Systems, Signals and Image Processing (IWSSIP)

EUROCON 2005 - The International Conference on "Computer as a Tool", 2005

In this paper we propose an iterative algorithm, based on modeling of the degradation system, for... more In this paper we propose an iterative algorithm, based on modeling of the degradation system, for reducing coding distortions in wavelet-based compressed images. The proposed algorithm iteratively reconstructs the degraded image. In every step of the iteration, image enhancement processes are implemented dependent of the image content. The performance of the proposed algorithm is evaluated experimentally

Organization of video databases is becoming difficult task as the amount of video content increas... more Organization of video databases is becoming difficult task as the amount of video content increases. Video classification based on the content of videos can significantly increase the speed of tasks such as browsing and searching for a particular video in a database. In this paper, a content-based videos classification system for the classes indoor and outdoor is presented. The system is intended to be used on a mobile platform with modest resources. The algorithm makes use of the temporal redundancy in videos, which allows using an uncomplicated classification model while still achieving reasonable accuracy. The training and evaluation was done on a video database of 443 videos downloaded from a video sharing service. A total accuracy of 87.36% was achieved.

2020 28th Telecommunications Forum (TELFOR), 2020

Intelligent Traffic Surveillance systems have helped improve road safety through ensuring timely ... more Intelligent Traffic Surveillance systems have helped improve road safety through ensuring timely response to events such as traffic accidents and congestion. Our aim is to devise a robust system capable of traffic audio events detection in a real-life environment. At the core of this system is a deep learning model capable of detecting anomalous events and their classification based on their acoustic waveform. We present the results of a series of experiments designed to optimize the architecture of this model based on different algorithms for audio processing. The results show that the designed model has competitive performance to approaches published in literature.

IEEE EUROCON 2017 -17th International Conference on Smart Technologies, 2017

In this paper, a new approach for high quality automated exposure fusion on mobile or handheld de... more In this paper, a new approach for high quality automated exposure fusion on mobile or handheld devices is presented. A utilization of the device's viewfinder screen video feed data is proposed, in order to increase the overall performance of the exposure fusion, both in static scenes and in scenes with moving objects. The introduced novelties are computationally inexpensive, since the preview video is of low frame resolution. The proposed extensions are embedded to an existing exposure fusion algorithm, and the performed experimental tests show that the new extended algorithm is better than its predecessor, both visually and in terms of objective quality measures.

Some of the most successful exposure fusion algorithms are based on image decomposition in Gaussi... more Some of the most successful exposure fusion algorithms are based on image decomposition in Gaussian/Laplacian pyramids. However, the visual quality of the fused result is highly dependent on the number of decomposition levels, i.e. the pyramid height. In this paper, the analysis of that dependence is performed, and an automated algorithm for optimization of the pyramid height is proposed. The algorithm is computationally inexpensive, as it uses results and parameters already computed in the pyramid decomposition process. This algorithm is intended to be a part of a fully automated, low processing power exposure fusion solution, designed for implementation on mobile platform devices. Key Words— exposure fusion, Gaussian/Laplacian pyramid, mobile platform 1 The results were obtained in the course of a research project commissioned and funded by NXP Software B.V., Eindhoven

IEEE EUROCON 2019 -18th International Conference on Smart Technologies, 2019

In this paper, a new approach for automated perceptual quality evaluation for pyramid-based expos... more In this paper, a new approach for automated perceptual quality evaluation for pyramid-based exposure fusion is presented. A machine learning method, using neural network training is used. The obtained results are verified using both established objective measures, and subjective evaluation of the same set, acquired by mean opinion score survey on multiple human subjects. The main advantage of the proposed approach is that it can grade the perceptual quality of the fused image even prior to the completing of the fusing process, in the stage of pyramid decomposition. This also allows implementation of a mechanism that could stop the pyramid decomposition in the most optimal pyramid level, in order to achieve the highest quality output image.

International Journal of Reasoning-based Intelligent Systems, 2021

Journal of Electrical Engineering and Information Technologies, 2017

This paper presents a fully automated, computationally inexpensive and high quality exposure fusi... more This paper presents a fully automated, computationally inexpensive and high quality exposure fusion algorithm, intended for use on mobile or handheld devices. A utilization of the device's viewfinder screen video feed data is proposed, in order to increase the overall performance of the exposure fusion, both in static scenes and in scenes with moving objects. Several novel ideas are implemented in order to make the whole procedure fully automated, working without need for any intervention, or parameter adjustment by the end-user. The performed experimental tests show an efficient performance and high quality results, both in visual and objective terms.

Proceedings of the 12th IEEE Mediterranean Electrotechnical Conference (IEEE Cat. No.04CH37521)

In this paper we propose a novel strategy for channel allocation in multi-class mobile networks w... more In this paper we propose a novel strategy for channel allocation in multi-class mobile networks with prioritized handovers, which uses dynamically variable guard channels to improve network utilization under given quality of service (QoS) constraints. We define user classes, each of them with different utilization of network channels. We consider the guard channel policy where certain number of channels is

2011 IEEE EUROCON - International Conference on Computer as a Tool, 2011

The paper presents a global motion compensation algorithm, designed to work in real time on low m... more The paper presents a global motion compensation algorithm, designed to work in real time on low memory and low processing power hardware platforms, such as mobile phones. The algorithm is designed as one of the parts of a fully automated exposure fusion algorithm also intended for mobile platform. It implements translational shifts to one or both of the input images

2009 16th IEEE International Conference on Image Processing (ICIP), 2009

Analytical and numerical modeling of composites with an isotropic dielectric base and multiphase ... more Analytical and numerical modeling of composites with an isotropic dielectric base and multiphase conducting inclusions for the development of wideband microwave shields is considered. The model uses Maxwell Garnett formalism for multiphase mixtures. Such composites are required in many engineering applications, including electromagnetic compatibility.

Lecture Notes in Computer Science, 2009

This paper focuses on the problems of video annotation of outdoor user generated low bit-rate vid... more This paper focuses on the problems of video annotation of outdoor user generated low bit-rate videos. An effective algorithm for estimating percentage of artificial (man-made) and natural content in a video frame is presented. The algorithm is based on edge information from the luminance frame only and it is intended to be executed on a mobile platform in an acceptable

2007 9th International Symposium on Signal Processing and Its Applications, 2007

An effective compression artifacts removal algorithm is proposed based on the theory of projectio... more An effective compression artifacts removal algorithm is proposed based on the theory of projections onto convex sets (POCS). It includes a block classification procedure, a ringing detection procedure, prediction of the spatial distribution of the quantization errors and estimation of the visibility of the compression artifacts. Information gained from both the spatial and transform domains, is incorporated into adaptive projections. Experiments performed on JPEG-compressed images, demonstrate the effectiveness of the proposed algorithm in suppressing both blocking and ringing artifacts, as well as the ability of the algorithm to preserve the image sharpness.

Melecon 2010 - 2010 15th IEEE Mediterranean Electrotechnical Conference, 2010

A real time algorithm for fusion of differently exposed images is proposed in this paper. The alg... more A real time algorithm for fusion of differently exposed images is proposed in this paper. The algorithm blends the details from two images of high dynamic range scene, acquired with different exposure values, into one output image which can be displayed on low dynamic range devices. The blending is performed in the spatial domain, using pixel by pixel approach, thus eliminating the need for expensive block processing or transform domain coding. The proposed scheme works both on grey and color images. The algorithm shows high efficiency, which make it applicable on low processing power platforms, such as mobile devices. The obtained results are visually comparable with previously published algorithms that are computationally much more expensive.

2012 20th Telecommunications Forum (TELFOR), 2012

ABSTRACT In this paper, a low cost focus fusion algorithm is proposed. The algorithm is based on ... more ABSTRACT In this paper, a low cost focus fusion algorithm is proposed. The algorithm is based on Laplacian pyramid decomposition of the input images. The included operations are designed for real time implementation on a hardware platforms with very limited resources, such as mobile devices. The whole process is fully automated. The experimental results show high speed and efficiency of the algorithm, while maintaining excellent visual quality of the resulting images.

2023 30th International Conference on Systems, Signals and Image Processing (IWSSIP)

2023 30th International Conference on Systems, Signals and Image Processing (IWSSIP)

Informatics in Education

With the development of technology allowing for a rapid expansion of data science and machine lea... more With the development of technology allowing for a rapid expansion of data science and machine learning in our everyday lives, a significant gap is forming in the global job market where the demand for qualified workers in these fields cannot be properly satisfied. This worrying trend calls for an immediate action in education, where these skills must be taught to students at all levels in an efficient and up-to-date manner. This paper gives an overview of the current state of data science and machine learning education globally and both at the high school and university levels, while outlining some illustrative and positive examples. Special focus is given to vocational education and training (VET), where the teaching of these skills is at its very beginning. Also presented and analysed are survey results concerning VET students in Slovenia, Serbia, and North Macedonia, and their knowledge, interests, and prerequisites regarding data science and machine learning. These results confi...

2023 30th International Conference on Systems, Signals and Image Processing (IWSSIP)

EUROCON 2005 - The International Conference on "Computer as a Tool", 2005

In this paper we propose an iterative algorithm, based on modeling of the degradation system, for... more In this paper we propose an iterative algorithm, based on modeling of the degradation system, for reducing coding distortions in wavelet-based compressed images. The proposed algorithm iteratively reconstructs the degraded image. In every step of the iteration, image enhancement processes are implemented dependent of the image content. The performance of the proposed algorithm is evaluated experimentally

Organization of video databases is becoming difficult task as the amount of video content increas... more Organization of video databases is becoming difficult task as the amount of video content increases. Video classification based on the content of videos can significantly increase the speed of tasks such as browsing and searching for a particular video in a database. In this paper, a content-based videos classification system for the classes indoor and outdoor is presented. The system is intended to be used on a mobile platform with modest resources. The algorithm makes use of the temporal redundancy in videos, which allows using an uncomplicated classification model while still achieving reasonable accuracy. The training and evaluation was done on a video database of 443 videos downloaded from a video sharing service. A total accuracy of 87.36% was achieved.

2020 28th Telecommunications Forum (TELFOR), 2020

Intelligent Traffic Surveillance systems have helped improve road safety through ensuring timely ... more Intelligent Traffic Surveillance systems have helped improve road safety through ensuring timely response to events such as traffic accidents and congestion. Our aim is to devise a robust system capable of traffic audio events detection in a real-life environment. At the core of this system is a deep learning model capable of detecting anomalous events and their classification based on their acoustic waveform. We present the results of a series of experiments designed to optimize the architecture of this model based on different algorithms for audio processing. The results show that the designed model has competitive performance to approaches published in literature.

IEEE EUROCON 2017 -17th International Conference on Smart Technologies, 2017

In this paper, a new approach for high quality automated exposure fusion on mobile or handheld de... more In this paper, a new approach for high quality automated exposure fusion on mobile or handheld devices is presented. A utilization of the device's viewfinder screen video feed data is proposed, in order to increase the overall performance of the exposure fusion, both in static scenes and in scenes with moving objects. The introduced novelties are computationally inexpensive, since the preview video is of low frame resolution. The proposed extensions are embedded to an existing exposure fusion algorithm, and the performed experimental tests show that the new extended algorithm is better than its predecessor, both visually and in terms of objective quality measures.

Some of the most successful exposure fusion algorithms are based on image decomposition in Gaussi... more Some of the most successful exposure fusion algorithms are based on image decomposition in Gaussian/Laplacian pyramids. However, the visual quality of the fused result is highly dependent on the number of decomposition levels, i.e. the pyramid height. In this paper, the analysis of that dependence is performed, and an automated algorithm for optimization of the pyramid height is proposed. The algorithm is computationally inexpensive, as it uses results and parameters already computed in the pyramid decomposition process. This algorithm is intended to be a part of a fully automated, low processing power exposure fusion solution, designed for implementation on mobile platform devices. Key Words— exposure fusion, Gaussian/Laplacian pyramid, mobile platform 1 The results were obtained in the course of a research project commissioned and funded by NXP Software B.V., Eindhoven

IEEE EUROCON 2019 -18th International Conference on Smart Technologies, 2019

In this paper, a new approach for automated perceptual quality evaluation for pyramid-based expos... more In this paper, a new approach for automated perceptual quality evaluation for pyramid-based exposure fusion is presented. A machine learning method, using neural network training is used. The obtained results are verified using both established objective measures, and subjective evaluation of the same set, acquired by mean opinion score survey on multiple human subjects. The main advantage of the proposed approach is that it can grade the perceptual quality of the fused image even prior to the completing of the fusing process, in the stage of pyramid decomposition. This also allows implementation of a mechanism that could stop the pyramid decomposition in the most optimal pyramid level, in order to achieve the highest quality output image.

International Journal of Reasoning-based Intelligent Systems, 2021

Journal of Electrical Engineering and Information Technologies, 2017

This paper presents a fully automated, computationally inexpensive and high quality exposure fusi... more This paper presents a fully automated, computationally inexpensive and high quality exposure fusion algorithm, intended for use on mobile or handheld devices. A utilization of the device's viewfinder screen video feed data is proposed, in order to increase the overall performance of the exposure fusion, both in static scenes and in scenes with moving objects. Several novel ideas are implemented in order to make the whole procedure fully automated, working without need for any intervention, or parameter adjustment by the end-user. The performed experimental tests show an efficient performance and high quality results, both in visual and objective terms.

Proceedings of the 12th IEEE Mediterranean Electrotechnical Conference (IEEE Cat. No.04CH37521)

In this paper we propose a novel strategy for channel allocation in multi-class mobile networks w... more In this paper we propose a novel strategy for channel allocation in multi-class mobile networks with prioritized handovers, which uses dynamically variable guard channels to improve network utilization under given quality of service (QoS) constraints. We define user classes, each of them with different utilization of network channels. We consider the guard channel policy where certain number of channels is

2011 IEEE EUROCON - International Conference on Computer as a Tool, 2011

The paper presents a global motion compensation algorithm, designed to work in real time on low m... more The paper presents a global motion compensation algorithm, designed to work in real time on low memory and low processing power hardware platforms, such as mobile phones. The algorithm is designed as one of the parts of a fully automated exposure fusion algorithm also intended for mobile platform. It implements translational shifts to one or both of the input images

2009 16th IEEE International Conference on Image Processing (ICIP), 2009

Analytical and numerical modeling of composites with an isotropic dielectric base and multiphase ... more Analytical and numerical modeling of composites with an isotropic dielectric base and multiphase conducting inclusions for the development of wideband microwave shields is considered. The model uses Maxwell Garnett formalism for multiphase mixtures. Such composites are required in many engineering applications, including electromagnetic compatibility.

Lecture Notes in Computer Science, 2009

This paper focuses on the problems of video annotation of outdoor user generated low bit-rate vid... more This paper focuses on the problems of video annotation of outdoor user generated low bit-rate videos. An effective algorithm for estimating percentage of artificial (man-made) and natural content in a video frame is presented. The algorithm is based on edge information from the luminance frame only and it is intended to be executed on a mobile platform in an acceptable

2007 9th International Symposium on Signal Processing and Its Applications, 2007

An effective compression artifacts removal algorithm is proposed based on the theory of projectio... more An effective compression artifacts removal algorithm is proposed based on the theory of projections onto convex sets (POCS). It includes a block classification procedure, a ringing detection procedure, prediction of the spatial distribution of the quantization errors and estimation of the visibility of the compression artifacts. Information gained from both the spatial and transform domains, is incorporated into adaptive projections. Experiments performed on JPEG-compressed images, demonstrate the effectiveness of the proposed algorithm in suppressing both blocking and ringing artifacts, as well as the ability of the algorithm to preserve the image sharpness.

Melecon 2010 - 2010 15th IEEE Mediterranean Electrotechnical Conference, 2010

A real time algorithm for fusion of differently exposed images is proposed in this paper. The alg... more A real time algorithm for fusion of differently exposed images is proposed in this paper. The algorithm blends the details from two images of high dynamic range scene, acquired with different exposure values, into one output image which can be displayed on low dynamic range devices. The blending is performed in the spatial domain, using pixel by pixel approach, thus eliminating the need for expensive block processing or transform domain coding. The proposed scheme works both on grey and color images. The algorithm shows high efficiency, which make it applicable on low processing power platforms, such as mobile devices. The obtained results are visually comparable with previously published algorithms that are computationally much more expensive.

2012 20th Telecommunications Forum (TELFOR), 2012

ABSTRACT In this paper, a low cost focus fusion algorithm is proposed. The algorithm is based on ... more ABSTRACT In this paper, a low cost focus fusion algorithm is proposed. The algorithm is based on Laplacian pyramid decomposition of the input images. The included operations are designed for real time implementation on a hardware platforms with very limited resources, such as mobile devices. The whole process is fully automated. The experimental results show high speed and efficiency of the algorithm, while maintaining excellent visual quality of the resulting images.