Petra Perner
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Petra Perner has a total of 62 co-authors. Here are the top co-authors by number of shared publications:
Horst Perner
Institute of Computer Vision and Applied Computer Sciences, Leipzig, Germany
7 shared publications- Ovidio Salvetti
Istituto di Scienza e Tecnologie dell’Informazione “Alessandro Faedo” CNR, 56124 Pisa, Italy
7 shared publications Silke Jänichen
Institute of Computer Vision and Applied Computer Sciences, IBaI, Leipzig, Germany
7 shared publicationsAnja Attig
IBaI
6 shared publicationsSuzanne Little
Institute of Computer Vision and Applied Computer Sciences
5 shared publications- Maria Frucci
Institute for High Performance Computing and Networking National Research Council of Italy (ICAR-CNR)
4 shared publications
Latest Publications
- 11 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 73 (00189456) , 1-15
MR-Matcher: A Multirouting Transformer-Based Network for Accurate Local Feature Matching
Local feature matching aims to identify pixel-wise correspondences between a pair of images and serves as an indispensable component of numerous visual applications. Recently, detector-free methods built upon Transformers have acquired impressive results, surpassing typical convolutional neural network (CNN)-based methods by a significant margin. However, one concern about current Transformer-based detector-free methods is their lack of concurrent integration of global, local, and multi-scale features for feature aggregation, thus hampering the capability of network to establish accurate and well-localized correspondences. Typically, local feature can capture geometric structure information to bolster the representation ability of the network while multi-scale feature can promote the differentiation of regions or objects of diverse sizes to improve the robustness of network to scale shifts. Specifically, we propose Multi-routing Transformer (MRFormer) Block that consists of: (1) Multi-scale Representation (MR) Layer to generate multi-scale feature representations and (2) parallel Local Routing (L-Routing) and Global Routings (G-Routings) to acquire local and global feature representations based on (1), thus enabling multi-scale, local, and global feature extraction at the same feature level. After obtaining such copious feature representations, we introduce a lightweight Expert Feature Compensator (EFC) to effectively calibrate these feature representations from both local and global perspectives. Benefiting from the diverse feature representations, MR-Matcher exceeds the state-of-the-art approaches over multiple benchmarks.
- 11 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 73 (00189456) , 1-15
MR-Matcher: A Multirouting Transformer-Based Network for Accurate Local Feature Matching
Local feature matching aims to identify pixel-wise correspondences between a pair of images and serves as an indispensable component of numerous visual applications. Recently, detector-free methods built upon Transformers have acquired impressive results, surpassing typical convolutional neural network (CNN)-based methods by a significant margin. However, one concern about current Transformer-based detector-free methods is their lack of concurrent integration of global, local, and multi-scale features for feature aggregation, thus hampering the capability of network to establish accurate and well-localized correspondences. Typically, local feature can capture geometric structure information to bolster the representation ability of the network while multi-scale feature can promote the differentiation of regions or objects of diverse sizes to improve the robustness of network to scale shifts. Specifically, we propose Multi-routing Transformer (MRFormer) Block that consists of: (1) Multi-scale Representation (MR) Layer to generate multi-scale feature representations and (2) parallel Local Routing (L-Routing) and Global Routings (G-Routings) to acquire local and global feature representations based on (1), thus enabling multi-scale, local, and global feature extraction at the same feature level. After obtaining such copious feature representations, we introduce a lightweight Expert Feature Compensator (EFC) to effectively calibrate these feature representations from both local and global perspectives. Benefiting from the diverse feature representations, MR-Matcher exceeds the state-of-the-art approaches over multiple benchmarks.
- 19 September 2022
- Published by Elsevier in Optics and Lasers in Engineering
- Vol. 160
A novel hierarchical iterative hypothesis strategy for intrinsic parameters calibration of laser structured-light weld vision sensor
- 19 September 2022
- Published by Elsevier in Optics and Lasers in Engineering
- Vol. 160
A novel hierarchical iterative hypothesis strategy for intrinsic parameters calibration of laser structured-light weld vision sensor
- Open Access
- 30 September 2020
- Published by IntechOpen
Novel Methods for Forensic Multimedia Data Analysis: Part I
The increased usage of digital media in daily life has resulted in the demand for novel multimedia data analysis techniques that can help to use these data for forensic purposes. Processing of such data for police investigation and as evidence in a court of law, such that data interpretation is reliable, trustworthy, and efficient in terms of human time and other resources required, will help greatly to speed up investigation and make investigation more effective. If such data are to be used as evidence in a court of law, techniques that can confirm origin and integrity are necessary. In this chapter, we are proposing a new concept for new multimedia processing techniques for varied multimedia sources. We describe the background and motivation for our work. The overall system architecture is explained. We present the data to be used. After a review of the state of the art of related work of the multimedia data we consider in this work, we describe the method and techniques we are developing that go beyond the state of the art. The work will be continued in a Chapter Part II of this topic.
- 30 September 2020
- Published by IntechOpen
Open AccessNovel Methods for Forensic Multimedia Data Analysis: Part I
The increased usage of digital media in daily life has resulted in the demand for novel multimedia data analysis techniques that can help to use these data for forensic purposes. Processing of such data for police investigation and as evidence in a court of law, such that data interpretation is reliable, trustworthy, and efficient in terms of human time and other resources required, will help greatly to speed up investigation and make investigation more effective. If such data are to be used as evidence in a court of law, techniques that can confirm origin and integrity are necessary. In this chapter, we are proposing a new concept for new multimedia processing techniques for varied multimedia sources. We describe the background and motivation for our work. The overall system architecture is explained. We present the data to be used. After a review of the state of the art of related work of the multimedia data we consider in this work, we describe the method and techniques we are developing that go beyond the state of the art. The work will be continued in a Chapter Part II of this topic.
- Open Access
- 30 September 2020
- Published by IntechOpen
Novel Methods for Forensic Multimedia Data Analysis: Part II
We are proposing a new concept for new multimedia data processing techniques for varied multimedia sources. We address our work toward speech, video and images, handwriting and text documents. The methods and techniques will form a toolkit that can be used for different cases in a court of law in order to extract information from different multimedia sources. In addition to the data mentioned above, social media (e.g., Facebook and Twitter) provide multimedia data in new formats. Such data allow the investigator to identify and compare objects, events or persons based on data properties, including biometric features or more symbolic features that point to coincidences and anomalies. We continue our work of novel methods for forensic multimedia data analysis Part I by a description of related work and a proposal of the methods and techniques we are developing beyond the state of the art for handwriting, multimedia feature extraction, novelty detection, legal aspects and cloud computing. Then, we describe the tasks that should be solved by the system and the different multimedia data. We describe expected results of our proposed toolkit. Finally, we summarize the objective of our work.
- 30 September 2020
- Published by IntechOpen
Open AccessNovel Methods for Forensic Multimedia Data Analysis: Part II
We are proposing a new concept for new multimedia data processing techniques for varied multimedia sources. We address our work toward speech, video and images, handwriting and text documents. The methods and techniques will form a toolkit that can be used for different cases in a court of law in order to extract information from different multimedia sources. In addition to the data mentioned above, social media (e.g., Facebook and Twitter) provide multimedia data in new formats. Such data allow the investigator to identify and compare objects, events or persons based on data properties, including biometric features or more symbolic features that point to coincidences and anomalies. We continue our work of novel methods for forensic multimedia data analysis Part I by a description of related work and a proposal of the methods and techniques we are developing beyond the state of the art for handwriting, multimedia feature extraction, novelty detection, legal aspects and cloud computing. Then, we describe the tasks that should be solved by the system and the different multimedia data. We describe expected results of our proposed toolkit. Finally, we summarize the objective of our work.
- 22 October 2019
- Published by Springer Nature
- p. 16-30
Case-Based Reasoning – Methods, Techniques, and Applications
- 22 October 2019
- Published by Springer Nature
- p. 16-30
Case-Based Reasoning – Methods, Techniques, and Applications
- 24 April 2019
- Published by Springer Nature
- p. 580-599
Learning of Shape Models from Exemplars of Biological Objects in Images
- 24 April 2019
- Published by Springer Nature
- p. 580-599
Learning of Shape Models from Exemplars of Biological Objects in Images
- Open Access
- 16 November 2018
- Published by Graphy Publications in International Journal of Computer & Software Engineering
- Vol. 3 (2)
Determining the Similarity Between Two Arbitrary 2-D Shapes and Its Application to Biological Objects
- 16 November 2018
- Published by Graphy Publications in International Journal of Computer & Software Engineering
- Vol. 3 (2)
Open AccessDetermining the Similarity Between Two Arbitrary 2-D Shapes and Its Application to Biological Objects
- 1 April 2018
- Published by EJournal Publishing in International Journal of Machine Learning and Computing
- Vol. 8 (2) , 144-151
An Automated Probe Handling and Image Inspection System for the Recognition of Biological Hazardous Material in the Air
- 1 April 2018
- Published by EJournal Publishing in International Journal of Machine Learning and Computing
- Vol. 8 (2) , 144-151
An Automated Probe Handling and Image Inspection System for the Recognition of Biological Hazardous Material in the Air
- Open Access
- 23 January 2018
- Published by Juniper Publishers in Current Trends in Biomedical Engineering & Biosciences
- Vol. 11 (2) , 1-11
Identifying Fungi Spores, Yeast, Bacteria by Opto-Electronic Imaging and Image Processing and Identification for Protecting Human Health
Human beings are exposed every day to bio-aerosols in their personal and/or professional life. The European Commission has issued regulations for protecting employees in the workplace from biological hazards. Airborne fungi can be detected and identified by an image-acquisition and interpretation system. In this paper we present recent results on the development of an automated image acquisition, sample handling and image-interpretation system for airborne fungi identification. We explain the application domain and describe the development issues. The development strategy and the architecture of the system are described and results are presented.
- 23 January 2018
- Published by Juniper Publishers in Current Trends in Biomedical Engineering & Biosciences
- Vol. 11 (2) , 1-11
Open AccessIdentifying Fungi Spores, Yeast, Bacteria by Opto-Electronic Imaging and Image Processing and Identification for Protecting Human Health
Human beings are exposed every day to bio-aerosols in their personal and/or professional life. The European Commission has issued regulations for protecting employees in the workplace from biological hazards. Airborne fungi can be detected and identified by an image-acquisition and interpretation system. In this paper we present recent results on the development of an automated image acquisition, sample handling and image-interpretation system for airborne fungi identification. We explain the application domain and describe the development issues. The development strategy and the architecture of the system are described and results are presented.
- 3 January 2018
- Published by World Scientific Pub Co Pte Ltd in International Journal of Pattern Recognition and Artificial Intelligence
- Vol. 32 (05)
A Hazy Image Database with Analysis of the Frequency Magnitude
Image haze removal has been extensively studied, but there has been no such an image database regarding the haze level. It is not convenient for readers to verify the assumptions or priors that are supposed to be useful for haze removal, and meanwhile, it is not fair to compare the performance of haze removal methods, which are effective for images with different haze levels. To solve this problem, we built a database consisting of more than 3464 images of different kinds of outdoor scenes. The images of the database are grouped into four classes regarding the haze level. Along with the database, we also observe a frequency magnitude prior, i.e. the frequency magnitude decreases with the increasing haze level, which can be used as a prior to develop haze removal methods. Our purpose is to help develop image haze removal methods, as well as verify existing statistical priors and discover new ones that can be used for image processing.
- 3 January 2018
- Published by World Scientific Pub Co Pte Ltd in International Journal of Pattern Recognition and Artificial Intelligence
- Vol. 32 (05)
A Hazy Image Database with Analysis of the Frequency Magnitude
Image haze removal has been extensively studied, but there has been no such an image database regarding the haze level. It is not convenient for readers to verify the assumptions or priors that are supposed to be useful for haze removal, and meanwhile, it is not fair to compare the performance of haze removal methods, which are effective for images with different haze levels. To solve this problem, we built a database consisting of more than 3464 images of different kinds of outdoor scenes. The images of the database are grouped into four classes regarding the haze level. Along with the database, we also observe a frequency magnitude prior, i.e. the frequency magnitude decreases with the increasing haze level, which can be used as a prior to develop haze removal methods. Our purpose is to help develop image haze removal methods, as well as verify existing statistical priors and discover new ones that can be used for image processing.