Marta Bistroń
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Marta Bistroń has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Zbigniew Piotrowski
Institute of Communication Systems, Faculty of Electronics, Military University of Technology, 00-908 Warsaw, Poland
8 shared publications - Dymitr Pietrow
Faculty of Electronics, Military University of Technology, Warsaw, Poland
1 shared publication - Gabriel Jekateryńczuk
Faculty of Electronics, Military University of Technology, 00-908 Warsaw, Poland
1 shared publication - Jacek M. Zurada
Department of Electrical and Computer Engineering, University of Louisville, Louisville, KY, USA
1 shared publication - Paweł Kaczmarek
Institute of Communication Systems, Faculty of Electronics, Military University of Technology, 00-908 Warsaw, Poland
1 shared publication
Latest Publications
- Top Cited PapersOpen Access
Deep Learning for Image Watermarking: A Comprehensive Review and Analysis of Techniques, Challenges, and Applications
The growing demand for digital content protection has significantly increased the importance of image watermarking, particularly in light of the rising vulnerability of multimedia content to unauthorized modifications. In recent years, research has increasingly focused on leveraging deep learning architectures to enhance watermarking performance, addressing challenges related to transparency, robustness, and payload capacity. Numerous deep learning-based watermarking methods have demonstrated superior effectiveness compared to traditional approaches, particularly those based on Convolutional Neural Networks (CNNs), Generative Adversarial Networks (GANs), Transformers, and diffusion models. This paper presents a comprehensive survey of recent developments in both conventional and deep learning-based image watermarking techniques. While traditional methods remain prevalent, deep learning approaches offer notable improvements in embedding and extraction efficiency, particularly when facing complex attacks, including those generated by advanced AI models. Applications in areas such as deepfake detection, cybersecurity, and Internet of Things (IoT) systems highlight the practical significance of these advancements. Despite substantial progress, challenges remain in achieving an optimal balance between invisibility, robustness, and capacity, particularly in high-resolution and real-time scenarios. This study concludes by outlining future research directions toward develop robust, scalable, and efficient deep learning-based watermarking systems capable of addressing emerging threats in digital media environments.
Top Cited PapersOpen AccessDeep Learning for Image Watermarking: A Comprehensive Review and Analysis of Techniques, Challenges, and Applications
The growing demand for digital content protection has significantly increased the importance of image watermarking, particularly in light of the rising vulnerability of multimedia content to unauthorized modifications. In recent years, research has increasingly focused on leveraging deep learning architectures to enhance watermarking performance, addressing challenges related to transparency, robustness, and payload capacity. Numerous deep learning-based watermarking methods have demonstrated superior effectiveness compared to traditional approaches, particularly those based on Convolutional Neural Networks (CNNs), Generative Adversarial Networks (GANs), Transformers, and diffusion models. This paper presents a comprehensive survey of recent developments in both conventional and deep learning-based image watermarking techniques. While traditional methods remain prevalent, deep learning approaches offer notable improvements in embedding and extraction efficiency, particularly when facing complex attacks, including those generated by advanced AI models. Applications in areas such as deepfake detection, cybersecurity, and Internet of Things (IoT) systems highlight the practical significance of these advancements. Despite substantial progress, challenges remain in achieving an optimal balance between invisibility, robustness, and capacity, particularly in high-resolution and real-time scenarios. This study concludes by outlining future research directions toward develop robust, scalable, and efficient deep learning-based watermarking systems capable of addressing emerging threats in digital media environments.
- Open Access
- 13 January 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (2) , 727
Victim Verification with the Use of Deep Metric Learning in DVI System Supported by Mobile Application
This paper presents the design of a system to support the identification of victims of disasters and terrorist attacks. The system, called ID Victim (IDV), is a web application using a mobile app and data server. The DVI (Disaster Victim Identification) procedure, an international standard developed by Interpol, is used. The purpose of the IDV system is to facilitate and expedite the process of determining victims’ identities. A neural identification module was developed and trained on approximately 13,000 images from the LFW dataset and fine-tuned using 400 simulated PostMortem (PM) and AnteMortem (AM) images. Postmortem data include photographs of victims while antemortem data consist of pre-disaster photos of potential victims. The module generates a hypothesis, linking PM to AM, which is then verified. The module achieved test identification accuracy of up to 60% for 25 sample PM and AM sets. The system partially automates photo comparisons by DVI teams, improving efficiency, reducing identification time, and limiting the exposure of operators to graphic images. Implementing the system as a mobile application accelerates the process by enabling direct data entry during victim examinations on-site.
- 13 January 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (2) , 727
Open AccessVictim Verification with the Use of Deep Metric Learning in DVI System Supported by Mobile Application
This paper presents the design of a system to support the identification of victims of disasters and terrorist attacks. The system, called ID Victim (IDV), is a web application using a mobile app and data server. The DVI (Disaster Victim Identification) procedure, an international standard developed by Interpol, is used. The purpose of the IDV system is to facilitate and expedite the process of determining victims’ identities. A neural identification module was developed and trained on approximately 13,000 images from the LFW dataset and fine-tuned using 400 simulated PostMortem (PM) and AnteMortem (AM) images. Postmortem data include photographs of victims while antemortem data consist of pre-disaster photos of potential victims. The module generates a hypothesis, linking PM to AM, which is then verified. The module achieved test identification accuracy of up to 60% for 25 sample PM and AM sets. The system partially automates photo comparisons by DVI teams, improving efficiency, reducing identification time, and limiting the exposure of operators to graphic images. Implementing the system as a mobile application accelerates the process by enabling direct data entry during victim examinations on-site.
- Open Access
Optimization of Imaging Reconnaissance Systems Using Super-Resolution: Efficiency Analysis in Interference Conditions
Image reconnaissance systems are critical in modern applications, where the ability to accurately detect and identify objects is crucial. However, distortions in real-world operational conditions, such as motion blur, noise, and compression artifacts, often degrade image quality, affecting the performance of detection systems. This study analyzed the impact of super-resolution (SR) technology, in particular, the Real-ESRGAN model, on the performance of a detection model under disturbed conditions. The methodology involved training and evaluating the Faster R-CNN detection model with original and modified data sets. The results showed that SR significantly improved detection precision and mAP in most interference scenarios. These findings underscore SR’s potential to improve imaging systems while identifying key areas for future development and further research.
Open AccessOptimization of Imaging Reconnaissance Systems Using Super-Resolution: Efficiency Analysis in Interference Conditions
Image reconnaissance systems are critical in modern applications, where the ability to accurately detect and identify objects is crucial. However, distortions in real-world operational conditions, such as motion blur, noise, and compression artifacts, often degrade image quality, affecting the performance of detection systems. This study analyzed the impact of super-resolution (SR) technology, in particular, the Real-ESRGAN model, on the performance of a detection model under disturbed conditions. The methodology involved training and evaluating the Faster R-CNN detection model with original and modified data sets. The results showed that SR significantly improved detection precision and mAP in most interference scenarios. These findings underscore SR’s potential to improve imaging systems while identifying key areas for future development and further research.
- Open Access
- 28 November 2024
- Published by MDPI AG in Preprints.org
Optimization of Imaging Reconnaissance Systems Using Super-Resolution: Efficiency Analysis in Interference Conditions
Image reconnaissance systems are critical to modern military operations, where the ability to accurately detect and identify objects is crucial. However, distortions in real-world operational conditions, such as motion blur, noise and compression artifacts, often degrade image quality, affecting the performance of detection systems. This study analyzed the impact of super-resolution (SR) technology, in particular the Real-ESRGAN model, on the performance of a detection model under disturbed conditions. The methodology involved training and evaluating the Faster R-CNN detection model with original and modified data sets. The results showed that SR significantly improved detection precision and mAP in most interference scenarios. These findings underscore SR's potential to improve military imaging systems, while identifying key areas for future development and further research.
- 28 November 2024
- Published by MDPI AG in Preprints.org
Open AccessOptimization of Imaging Reconnaissance Systems Using Super-Resolution: Efficiency Analysis in Interference Conditions
Image reconnaissance systems are critical to modern military operations, where the ability to accurately detect and identify objects is crucial. However, distortions in real-world operational conditions, such as motion blur, noise and compression artifacts, often degrade image quality, affecting the performance of detection systems. This study analyzed the impact of super-resolution (SR) technology, in particular the Real-ESRGAN model, on the performance of a detection model under disturbed conditions. The methodology involved training and evaluating the Faster R-CNN detection model with original and modified data sets. The results showed that SR significantly improved detection precision and mAP in most interference scenarios. These findings underscore SR's potential to improve military imaging systems, while identifying key areas for future development and further research.
- Open Access
Efficient Video Watermarking Algorithm Based on Convolutional Neural Networks with Entropy-Based Information Mapper
This paper presents a method for the transparent, robust, and highly capacitive watermarking of video signals using an information mapper. The proposed architecture is based on the use of deep neural networks to embed the watermark in the luminance channel in the YUV color space. An information mapper was used to enable the transformation of a multi-bit binary signature of varying capacitance reflecting the entropy measure of the system into a watermark embedded in the signal frame. To confirm the effectiveness of the method, tests were carried out for video frames with a resolution of 256 × 256 pixels, with a watermark capacity of 4 to 16,384 bits. Transparency metrics (SSIM and PSNR) and a robustness metric—the bit error rate (BER)—were used to assess the performance of the algorithms.
Open AccessEfficient Video Watermarking Algorithm Based on Convolutional Neural Networks with Entropy-Based Information Mapper
This paper presents a method for the transparent, robust, and highly capacitive watermarking of video signals using an information mapper. The proposed architecture is based on the use of deep neural networks to embed the watermark in the luminance channel in the YUV color space. An information mapper was used to enable the transformation of a multi-bit binary signature of varying capacitance reflecting the entropy measure of the system into a watermark embedded in the signal frame. To confirm the effectiveness of the method, tests were carried out for video frames with a resolution of 256 × 256 pixels, with a watermark capacity of 4 to 16,384 bits. Transparency metrics (SSIM and PSNR) and a robustness metric—the bit error rate (BER)—were used to assess the performance of the algorithms.
- Open Access
- 3 October 2022
- Published by MDPI AG in Applied Sciences
- Vol. 12 (19) , 9960
Comparison of Machine Learning Algorithms Used for Skin Cancer Diagnosis
The paper presents a comparison of automatic skin cancer diagnosis algorithms based on analyses of skin lesions photos. Two approaches are presented: the first one is based on the extraction of features from images using simple feature descriptors, and then the use of selected machine learning algorithms for the purpose of classification, and the second approach uses selected algorithms belonging to the subgroup of machine learning—deep learning, i.e., convolutional neural networks (CNN), which perform both the feature extraction and classification in one algorithm. The following algorithms were analyzed and compared: Logistic Regression, k-Nearest Neighbors, Naive Bayes, Decision Tree, Random Forest, and Support Vector Machine, and four CNN–VGG-16, ResNet60, InceptionV3, and Inception-ResNetV2 In the first variant, before the classification process, the image features were extracted using 4 different feature descriptors and combined in various combinations in order to obtain the most accurate image features vector, and thus the highest classification accuracy. The presented approaches have been validated using the image dataset from the ISIC database, which includes data from two categories—benign and malignant skin lesions. Common machine learning metrics and saved values of training time were used to evaluate the effectiveness and the performance (computational complexity) of the algorithms.
- 3 October 2022
- Published by MDPI AG in Applied Sciences
- Vol. 12 (19) , 9960
Open AccessComparison of Machine Learning Algorithms Used for Skin Cancer Diagnosis
The paper presents a comparison of automatic skin cancer diagnosis algorithms based on analyses of skin lesions photos. Two approaches are presented: the first one is based on the extraction of features from images using simple feature descriptors, and then the use of selected machine learning algorithms for the purpose of classification, and the second approach uses selected algorithms belonging to the subgroup of machine learning—deep learning, i.e., convolutional neural networks (CNN), which perform both the feature extraction and classification in one algorithm. The following algorithms were analyzed and compared: Logistic Regression, k-Nearest Neighbors, Naive Bayes, Decision Tree, Random Forest, and Support Vector Machine, and four CNN–VGG-16, ResNet60, InceptionV3, and Inception-ResNetV2 In the first variant, before the classification process, the image features were extracted using 4 different feature descriptors and combined in various combinations in order to obtain the most accurate image features vector, and thus the highest classification accuracy. The presented approaches have been validated using the image dataset from the ISIC database, which includes data from two categories—benign and malignant skin lesions. Common machine learning metrics and saved values of training time were used to evaluate the effectiveness and the performance (computational complexity) of the algorithms.
- Open Access
- 6 April 2021
- Published by MDPI AG in Electronics
- Vol. 10 (7) , 871
Artificial Intelligence Applications in Military Systems and Their Influence on Sense of Security of Citizens
The paper presents an overview of current and expected prospects for the development of artificial intelligence algorithms, especially in military applications, and conducted research regarding applications in the area of civilian life. Attention was paid mainly to the use of AI algorithms in cybersecurity, object detection, military logistics and robotics. It discusses the problems connected with the present solutions and how artificial intelligence can help solve them. It briefly presents also mathematical structures and descriptions for ART, CNN and SVM networks as well as Expectation–Maximization and Gaussian Mixture Model algorithms that are used in solving of discussed problems. The third chapter discusses the attitude of society towards the use of neural network algorithms in military applications. The basic problems related to ethics in the application of artificial intelligence and issues of responsibility for errors made by autonomous systems are discussed.
- 6 April 2021
- Published by MDPI AG in Electronics
- Vol. 10 (7) , 871
Open AccessArtificial Intelligence Applications in Military Systems and Their Influence on Sense of Security of Citizens
The paper presents an overview of current and expected prospects for the development of artificial intelligence algorithms, especially in military applications, and conducted research regarding applications in the area of civilian life. Attention was paid mainly to the use of AI algorithms in cybersecurity, object detection, military logistics and robotics. It discusses the problems connected with the present solutions and how artificial intelligence can help solve them. It briefly presents also mathematical structures and descriptions for ART, CNN and SVM networks as well as Expectation–Maximization and Gaussian Mixture Model algorithms that are used in solving of discussed problems. The third chapter discusses the attitude of society towards the use of neural network algorithms in military applications. The basic problems related to ethics in the application of artificial intelligence and issues of responsibility for errors made by autonomous systems are discussed.