- Amsterdam, the Netherlands
Fons Verbeek
Universiteit Leiden, CS (LIACS), imaging & bioinformatics, Faculty Member
In life sciences, light microscopy is used to study specimens. On the organism-level a bright-field representation present an overview for the whole shape of a specimen; the organ-level fluorescent staining representation supports in the... more
In life sciences, light microscopy is used to study specimens. On the organism-level a bright-field representation present an overview for the whole shape of a specimen; the organ-level fluorescent staining representation supports in the interpretation of the detailed intrinsic structures. We present light microscopy axial-view imaging based on the Vertebrate Automated Screening Technology to acquire axial-view images for the organism and organs of zebrafish larvae. We obtain multi-modal 3D reconstruction using a profile-based method, from which we can derive the 3D measurements of volume and surface area. In this method, we employ a microscope camera calibration using voxel residual volume maximization algorithm. We intuitively align and fuse the obtained multi-models. Experimental results show natural visualization both for the whole organism and organ of zebrafish larvae; subsequently accurate 3D measurements are obtained. This method is very suitable for high-throughput research...
Research Interests:
As an important technique for data pre-processing, outlier detection plays a crucial role in various real applications and has gained substantial attention, especially in medical fields. Despite the importance of outlier detection, many... more
As an important technique for data pre-processing, outlier detection plays a crucial role in various real applications and has gained substantial attention, especially in medical fields. Despite the importance of outlier detection, many existing methods are vulnerable to the distribution of outliers and require prior knowledge, such as the outlier proportion. To address this problem to some extent, this article proposes an adaptive mini-minimum spanning tree-based outlier detection (MMOD) method, which utilizes a novel distance measure by scaling the Euclidean distance. For datasets containing different densities and taking on different shapes, our method can identify outliers without prior knowledge of outlier percentages. The results on both real-world medical data corpora and intuitive synthetic datasets demonstrate the effectiveness of the proposed method compared to state-of-the-art methods.
Macrophage-expressed gene 1 <i>(MPEG1)</i> encodes an evolutionarily conserved protein with a predicted membrane attack complex/perforin domain associated with host defence against invading pathogens. In vertebrates,... more
Macrophage-expressed gene 1 <i>(MPEG1)</i> encodes an evolutionarily conserved protein with a predicted membrane attack complex/perforin domain associated with host defence against invading pathogens. In vertebrates, MPEG1/perforin-2 is an integral membrane protein of macrophages, suspected to be involved in the killing of intracellular bacteria by pore-forming activity. Zebrafish have 3 copies of <i>MPEG1</i>; 2 are expressed in macrophages, whereas the third could be a pseudogene. The <i>mpeg1</i> and <i>mpeg1.2</i> genes show differential regulation during infection of zebrafish embryos with the bacterial pathogens <i>Mycobacterium marinum</i> and <i>Salmonella typhimurium.</i> While <i>mpeg1</i> is downregulated during infection with both pathogens, <i>mpeg1.2</i> is infection inducible. Upregulation of <i>mpeg1.2</i> is partially dependent on the presence of functional Mpeg1 and requires the Toll-like receptor adaptor molecule MyD88 and the transcription factor NFκB. Knockdown of <i>mpeg1</i> alters the immune response to <i>M. marinum</i> infection and results in an increased bacterial burden. In <i>Salmonella typhimurium</i> infection, both <i>mpeg1</i> and <i>mpeg1.2</i> knockdown increase the bacterial burdens, but <i>mpeg1</i> morphants show increased survival times. The combined results of these two in vivo infection models support the anti-bacterial function of the MPEG1/perforin-2 family and indicate that the intricate cross-regulation of the two <i>mpeg1</i> copies aids the zebrafish host in combatting infection of various pathogens.
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
The aristaless-related homeobox genes Prx1 and Prx2 are required for correct skeletogenesis in many structures. Mice that lack both Prx1 and Prx2 functions display reduction or absence of skeletal elements in the skull, face, limbs and... more
The aristaless-related homeobox genes Prx1 and Prx2 are required for correct skeletogenesis in many structures. Mice that lack both Prx1 and Prx2 functions display reduction or absence of skeletal elements in the skull, face, limbs and vertebral column. A striking phenotype is found in the lower jaw, which shows loss of midline structures, and the presence of a single, medially located incisor. We investigated development of the mandibular arch of Prx1−/−Prx2−/− mutants to obtain insight into the molecular basis of the lower jaw abnormalities. We observed in mutant embryos a local decrease in proliferation of mandibular arch mesenchyme in a medial area. Interestingly, in the oral epithelium adjacent to this mesenchyme, sonic hedgehog (Shh) expression was strongly reduced, indicative of a function for Prx genes in indirect regulation of Shh. Wild-type embryos that were exposed to the hedgehog-pathway inhibitor, jervine, partially phenocopied the lower jaw defects of Prx1−/−Prx2−/− mutants. In addition, this treatment led to loss of the mandibular incisors. We present a model that describes how loss of Shh expression in Prx1−/−Prx2−/− mutants leads to abnormal morphogenesis of the mandibular arch.
Research Interests:
The shipping industry is one of the strongest anthropogenic emitters of NOx—a substance harmful both to human health and the environment. The rapid growth of the industry causes societal pressure on controlling the emission levels... more
The shipping industry is one of the strongest anthropogenic emitters of NOx—a substance harmful both to human health and the environment. The rapid growth of the industry causes societal pressure on controlling the emission levels produced by ships. All the methods currently used for ship emission monitoring are costly and require proximity to a ship, which makes global and continuous emission monitoring impossible. A promising approach is the application of remote sensing. Studies showed that some of the NO2 plumes from individual ships can visually be distinguished using the TROPOspheric Monitoring Instrument on board the Copernicus Sentinel 5 Precursor (TROPOMI/S5P). To deploy a remote-sensing-based global emission monitoring system, an automated procedure for the estimation of NO2 emissions from individual ships is needed. The extremely low signal-to-noise ratio of the available data, as well as the absence of the ground truth makes the task very challenging. Here, we present a ...
Research Interests:
Augmented Play Spaces (APS) are (semi-) public environments where playful interaction is facilitated by enriching the existing environment with interactive technology. APS can potentially facilitate social interaction and physical... more
Augmented Play Spaces (APS) are (semi-) public environments where playful interaction is facilitated by enriching the existing environment with interactive technology. APS can potentially facilitate social interaction and physical activity in (semi-)public environments. In controlled settings APS show promising effects. However, people’s willingness to engage with APSin situ, depends on many factors that do not occur in aforementioned controlled settings (where participation is obvious). To be able to achieve and demonstrate the positive effects of APS when implemented in (semi-)public environments, it is important to gain more insight in how to motivate people to engage with them and better understand when and how those decisions can be influenced by certain (design) factors. The Participant Journey Map (PJM) was developed following multiple iterations. First, based on related work, and insights gained from previously developed and implemented APS, a concept of the PJM was develope...
Research Interests:
Research Interests:
As AI systems increasingly pervade modern society and lead to manifold and diverse consequences, the development of internationally recognized and industry-specific frameworks focusing on legal and ethical principles is crucial. This... more
As AI systems increasingly pervade modern society and lead to manifold and diverse consequences, the development of internationally recognized and industry-specific frameworks focusing on legal and ethical principles is crucial. This report aims at (a) understanding how the 7 Key Requirements for Trustworthy AI impact the Media and Technology sector (MTS) and at (b) putting forward guidelines to ensure compliance with the 7 Key Requirements. The report identifies four application areas of AI MTS, i.e. automating data capture and processing, automating content generation, automating content mediation and automating communication. Subsequently, the 7 Key Requirements are discussed within each of the four identified themes. Ultimately, recommendations are made to ensure that AI development and adoption in Media and Technology sector is compliant with the 7 Key Requirements. Three clusters of recommendations are proposed: (1) addressing data power and positive obligations, (2) empowerment by design and risk assessments and (3) cooperative responsibility and stakeholder engagements
Research Interests:
Research Interests:
Research Interests:
We propose a research direction into the role of the peak-end rule to engage people into Augmented Play Spaces (APS). The peak(s) and ending of an experience are defining moments for how an experience is remembered afterwards. An... more
We propose a research direction into the role of the peak-end rule to engage people into Augmented Play Spaces (APS). The peak(s) and ending of an experience are defining moments for how an experience is remembered afterwards. An important factor contributing to the likelihood of engagement in an APS is a positive previous experience (with the same or a similar system).
Research Interests:
This paper introduces The Morality Machine, a system that tracks ethical sentiment in Twitter discussions. Empirical approaches to ethics are rare, and to our knowledge this system is the first to take a machine learning approach. It is... more
This paper introduces The Morality Machine, a system that tracks ethical sentiment in Twitter discussions. Empirical approaches to ethics are rare, and to our knowledge this system is the first to take a machine learning approach. It is based on Moral Foundations Theory, a framework of moral values that are assumed to be universal. Carefully handcrafted keyword dictionaries for Moral Foundations Theory exist, but experiments demonstrate that models that do not leverage these have similar or superior performance, thus proving the value of a more pure machine learning approach.
Research Interests:
Research Interests:
Petri nets have been widely used to model and analyze biological system. The formalism comprises different types of paradigms, integrating qualitative and quantitative (i.e., stochastic, continuous, or hybrid) modeling and analysis... more
Petri nets have been widely used to model and analyze biological system. The formalism comprises different types of paradigms, integrating qualitative and quantitative (i.e., stochastic, continuous, or hybrid) modeling and analysis techniques. In this chapter, we describe the Petri net formalism and a broad view of its structure and characteristics applied in the modeling process in systems biology. We present the different net classes of the formalism, its color extension, and model analysis. The objective is to provide a discussion on the Petri net formalism as basis for research in computational biology.
Research Interests:
Biology is 3D. Therefore, it is important to be able to analyze phenomena in a spatiotemporal manner. Different fields in computational sciences are useful for analysis in biology; i.e. image analysis, pattern recognition and machine... more
Biology is 3D. Therefore, it is important to be able to analyze phenomena in a spatiotemporal manner. Different fields in computational sciences are useful for analysis in biology; i.e. image analysis, pattern recognition and machine learning. To fit an empirical model to a higher abstraction, however, theoretical computer science methods are probed. We explore the construction of empirical 3D graphical models and develop abstractions from these models in L-systems. These systems are provided with a profound formalization in a grammar allowing generalization and exploration of mathematical structures in topologies. The connections between these computational approaches are illustrated by a case study of the development of the lactiferous duct in mice and the phenotypical effects from different environmental conditions we can observe on it. We have constructed a workflow to get 3D models from different experimental conditions and use these models to extract features. Our aim is to co...
Research Interests:
Three-dimensional reconstruction of tomograms from optical projection microscopy is confronted with several drawbacks. In this paper we employ iterative reconstruction algorithms to avoid streak artefacts in the reconstruction and explore... more
Three-dimensional reconstruction of tomograms from optical projection microscopy is confronted with several drawbacks. In this paper we employ iterative reconstruction algorithms to avoid streak artefacts in the reconstruction and explore possible ways to optimize two parameters of the algorithms, i.e., iteration number and initialization, in order to improve the reconstruction performance. As benchmarks for direct reconstruction evaluation in optical projection tomography are absent, we consider the assessment through the performance of the segmentation on the 3D reconstruction. In our explorative experiments we use the zebrafish model system which is a typical specimen for use in optical projection tomography system; and as such frequently used. In this manner data can be easily obtained from which a benchmark set can be built. For the segmentation approach we apply a two-dimensional U-net convolutional neural network because it is recognized to have a good performance in biomedical image segmentation. In order to prevent the training from getting stuck in local minima, a novel learning rate schema is proposed. This optimization achieves a lower training loss during the training process, as compared to an optimal constant learning rate. Our experiments demonstrate that the approach to the benchmarking of iterative reconstruction via results of segmentation is very useful. It contributes an important tool to the development of computational tools for optical projection tomography.
Research Interests:
Research Interests:
Recent developments in the field of HCI draw our attention to the potential of playful interfaces, play, and games. This chapter identifies a new but relevant application domain for playful interfaces (i.e. scientific practice involving... more
Recent developments in the field of HCI draw our attention to the potential of playful interfaces, play, and games. This chapter identifies a new but relevant application domain for playful interfaces (i.e. scientific practice involving image data). Given the thesis that play and playfulness are relevant for a researcher's interaction with scientific images, the question remains: How do we design playful interfaces that support meaningful ways to playfully engage with scientific images? This chapter introduces, investigates, and implements storytelling with scientific images as a worthwhile instance of playful interaction with scientific images. To better understand and further exemplify the potential of storytelling with scientific images, the chapter contributes both a review of utilitarian usages of storytelling with images and findings from a case study storytelling game.
Research Interests:
Research Interests:
Research Interests:
Research Interests: Neurogenesis, Fear, Biology, Medicine, Molecular Psychiatry, and 15 moreMotivation, Biological Sciences, Molecular, Hippocampus, Classical Conditioning, Dendritic Spines, Mice, Animals, Corticosterone, Dendrites, Neurons, Memory Disorders, Hippocampal formation, Medical and Health Sciences, and In Vitro Techniques
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
As AI systems increasingly pervade modern society and lead to manifold and diverse consequences, the development of internationally recognized and industry-specific frameworks focusing on legal and ethical principles is crucial. This... more
As AI systems increasingly pervade modern society and lead to manifold and diverse consequences, the development of internationally recognized and industry-specific frameworks focusing on legal and ethical principles is crucial. This report aims at (a) understanding how the 7 Key Requirements for Trustworthy AI impact the Media and Technology sector (MTS) and at (b) putting forward guidelines to ensure compliance with the 7 Key Requirements. The report identifies four application areas of AI MTS, i.e. automating data capture and processing, automating content generation, automating content mediation and automating communication. Subsequently, the 7 Key Requirements are discussed within each of the four identified themes. Ultimately, recommendations are made to ensure that AI development and adoption in Media and Technology sector is compliant with the 7 Key Requirements. Three clusters of recommendations are proposed: (1) addressing data power and positive obligations, (2) empowerme...
Research Interests:
Pay-what-you want (PWYW) is an attractive pricing mechanism that allows customers to pay the amount they are motivated to spend. The model has been successfully implemented in restaurants and stores, but online applications remain risky.... more
Pay-what-you want (PWYW) is an attractive pricing mechanism that allows customers to pay the amount they are motivated to spend. The model has been successfully implemented in restaurants and stores, but online applications remain risky. Online customers are less driven by guilt and less influenced by what others might think of them when deciding on a price, as they are anonymous and do not meet the seller. In the present study, social comparison was considered as a variable that might influence a payment decision. A participatory experiment was designed in the form of a mock online PWYW store to investigate this. Results show that customers were generally more likely to compare themselves to others who had paid lower prices and decrease the amount of money they wanted to pay. Additionally, individualists were more likely to increase, while competitors were more likely to decrease their final offer after comparison.
In image captioning models, the main challenge in describing an image is identifying all the objects by precisely considering the relationships between the objects and producing various captions. Over the past few years, many methods have... more
In image captioning models, the main challenge in describing an image is identifying all the objects by precisely considering the relationships between the objects and producing various captions. Over the past few years, many methods have been proposed, from an attribute-to-attribute comparison approach to handling issues related to semantics and their relationships. Despite the improvements, the existing techniques suffer from inadequate positional and geometrical attributes concepts. The reason is that most of the abovementioned approaches depend on Convolutional Neural Networks (CNNs) for object detection. CNN is notorious for failing to detect equivariance and rotational invariance in objects. Moreover, the pooling layers in CNNs cause valuable information to be lost. Inspired by the recent successful approaches, this paper introduces a novel framework for extracting meaningful descriptions based on a parallelized capsule network that describes the content of images through a hi...
Research Interests:
Motivation: The hallmarks of cancer provide a highly cited and well-used conceptual framework for describing the processes involved in cancer cell development and tumourigenesis. However, methods for translating these high-level hallmarks... more
Motivation: The hallmarks of cancer provide a highly cited and well-used conceptual framework for describing the processes involved in cancer cell development and tumourigenesis. However, methods for translating these high-level hallmarks concepts into data level-links between individual genes and individual cancer hallmarks varies widely between studies. When we examine different strategies for linking and mapping cancer hallmarks in detail, we see significant differences, but also consensus. Results: Here we compare hallmark mapping schemes from multiple studies and explore the consensus knowledge from these different approaches, in order to help us better understand the core biological processes and pathways that are associated with the hallmarks of cancer. We also explore the differences between mapping schemes and identify which differences represent changes in our understanding of cancer, changes in our understanding of biological processes in the non-disease state, or the acc...
Research Interests:
Research Interests:
Research Interests:
This paper considers the problem the improvement and application of the KDE Mean Shift tracking algorithm and data analysis in a migration study of MTLn3 cells. The aim is to convert cell migration videos into numeric description of... more
This paper considers the problem the improvement and application of the KDE Mean Shift tracking algorithm and data analysis in a migration study of MTLn3 cells. The aim is to convert cell migration videos into numeric description of changes in cell behavior. The choice of KDE Mean ...
Article / Letter to editorLeiden Inst Advanced Computer SciencesInstituut Biologie Leide
Research Interests:
This paper considers the problem the improvement and application of the KDE Mean Shift tracking algorithm and data analysis in a migration study of MTLn3 cells. The aim is to convert cell migration videos into numeric description of... more
This paper considers the problem the improvement and application of the KDE Mean Shift tracking algorithm and data analysis in a migration study of MTLn3 cells. The aim is to convert cell migration videos into numeric description of changes in cell behavior. The choice of KDE Mean Shift Tracking is based on its robust and prominent performance in time-lapse studies compared to other algorithms. Morphology and motility measurements are defined by considering both statistics and true biological translation. The detection of significant behavior change relies on both feature selection and hypothesis testing in the feature space. The feedback from the “wet-lab ” to our tracking analysis and results indicate that the accuracy of cell migration analysis is increased significantly and labor time is reduced enormously (over 300%). In addition, it is also believed that the current feature measurements reveal several important behavior measurements, which cannot be determined by manual observ...
Research Interests:
Monitoring of airborne pollen concentrations provides an important source of information for the globally increasing number of hay fever patients. Airborne pollen are traditionally counted under the microscope, but with the latest... more
Monitoring of airborne pollen concentrations provides an important source of information for the globally increasing number of hay fever patients. Airborne pollen are traditionally counted under the microscope, but with the latest developments in image recognition methods, automating this process has become feasible. A challenge that persists, however, is that many pollen grains cannot be distinguished beyond the genus or family level using a microscope. Here, we assess the use of a Convolutional Neural Network (CNN) to increase taxonomic accuracy for airborne pollen. As a case study we use the nettle family (Urticaceae), which contains two main genera (Urtica and Parietaria) common in European landscapes which pollen cannot be separated by trained specialists. While pollen from Urtica species have very low allergenic relevance, those from several species of Parietaria are severely allergenic. We collect pollen from both fresh as well as from herbarium specimens and use these to tra...
Research Interests:
Performing tasks in virtual environments are to increasing extent becoming normal practice; such is possible due to the developments in graphic rendering systems and interaction techniques. Application areas from entertainment to medical... more
Performing tasks in virtual environments are to increasing extent becoming normal practice; such is possible due to the developments in graphic rendering systems and interaction techniques. Application areas from entertainment to medical industry benefit from gestural 3D interaction. With this in mind, we set out a study aiming to research the relevance of using determined 6DoF input devices in interacting with three-dimensional models in graphical interfaces. In this paper we present an evaluation of 3D pointing tasks using Leap Motion sensor to support 3D object manipulation. Three controlled experiments were performed in the study, exposing test subjects to pointing task evaluations and object deformation, measuring the time taken to perform mesh extrusion and object translation. Qualitative data was gathered using the System Usability Scale questionnaire. The data show a strong correlation between input device and performance time suggesting a dominance of the Leap Motion gestur...
Research Interests:
The typical black coloured ebony wood (Diospyros, Ebenaceae) is desired as a commercial timber because of its durable and aesthetic properties. Surprisingly, a comprehensive wood anatomical overview of the genus is lacking, making it... more
The typical black coloured ebony wood (Diospyros, Ebenaceae) is desired as a commercial timber because of its durable and aesthetic properties. Surprisingly, a comprehensive wood anatomical overview of the genus is lacking, making it impossible to fully grasp the diversity in microscopic anatomy and to distinguish between CITES protected species native to Madagascar and the rest. We present the largest microscopic wood anatomical reference database for ebony woods and reconstruct evolutionary patterns in the microscopic wood anatomy within the family level using an earlier generated molecular phylogeny. Wood samples from 246 Diospyros species are described based on standardised light microscope observations. For the ancestral state reconstruction, we selected eight wood anatomical characters from 88 Ebenaceae species (including 29 Malagasy Diospyros species) that were included in the most recently reconstructed family phylogeny. Within Diospyros, the localisation of prismatic crysta...
Research Interests:
Monitoring of airborne pollen concentrations provides an important source of information for the globally increasing number of hay fever patients. Airborne pollen is traditionally counted under the microscope, but with the latest... more
Monitoring of airborne pollen concentrations provides an important source of information for the globally increasing number of hay fever patients. Airborne pollen is traditionally counted under the microscope, but with the latest developments in image recognition methods, automating this process has become feasible. A challenge that persists, however, is that many pollen grains cannot be distinguished beyond the genus or family level using a microscope. Here, we assess the use of Convolutional Neural Networks (CNNs) to increase taxonomic accuracy for airborne pollen. As a case study we use the nettle family (Urticaceae), which contains two main genera (Urtica and Parietaria) common in European landscapes which pollen cannot be separated by trained specialists. While pollen from Urtica species has very low allergenic relevance, pollen from several species of Parietaria is severely allergenic. We collect pollen from both fresh as well as from herbarium specimens and use these without ...
Research Interests:
The Gene Expression Management System (GEMS) is a database system for patterns of gene expression. These patterns result from systematic whole-mount fluorescent in situ hybridization studies on zebrafish embryos. GEMS is an integrative... more
The Gene Expression Management System (GEMS) is a database system for patterns of gene expression. These patterns result from systematic whole-mount fluorescent in situ hybridization studies on zebrafish embryos. GEMS is an integrative platform that addresses one of the important challenges of developmental biology: how to integrate genetic data that underpin morphological changes during embryogenesis. Our motivation to build this system was by the need to be able to organize and compare multiple patterns of gene expression at tissue level. Integration with other developmental and biomolecular databases will further support our understanding of development. The GEMS operates in concert with a database containing a digital atlas of zebrafish embryo; this digital atlas of zebrafish development has been conceived prior to the expansion of the GEMS. The atlas contains 3D volume models of canonical stages of zebrafish development in which in each volume model element is annotated with an...
Research Interests: Genetics, Computer Science, Ontology, Developmental Biology, Computational Biology, and 15 moreBiology, Medicine, Gene expression, Animals, Gene ontology, Database Integration, Management System, Data Integrity, Volume modeling, Embryos, Database System, Gene expression profiling, Gene Expression Data, Integrative Bioinformatics, and Expression pattern
Computational modeling of biological systems is becoming increasingly important in the endeavors to better understand complex biological behavior. It enables researchers to perform computerized simulations using a systems biology... more
Computational modeling of biological systems is becoming increasingly important in the endeavors to better understand complex biological behavior. It enables researchers to perform computerized simulations using a systems biology approach, in order to understand the underlying mechanisms of certain biological phenomena. It provides an opportunity to perform experiments that are otherwise impractical or infeasible in vivo/vitro experiments. In our approach we propose to model and simulate the pathogenesis ofMycobacterium marinum using Petri Net formalism based on data obtained from analysis of microscope images and to provide a three dimensional visualization of the whole infection process and granuloma formation. Image analysis will provide an accurate estimation of the infection in a structured database which will be used for the construction of the Petri Net model. The results of the simulation and analysis of the infection behavior will be visualized in 3D.
Research Interests:
This paper presents initial findings of the research project Making Sense of Illustrated Handwritten Archives and demonstrates the recognition capabilities of the MONK artificial intelligence system developed at the institute of... more
This paper presents initial findings of the research project Making Sense of Illustrated Handwritten Archives and demonstrates the recognition capabilities of the MONK artificial intelligence system developed at the institute of Artificial Intelligence and Cognitive Engineering (ALICE) at Groningen University. In a period of four years (2016-2019), our research project aims to produce an innovative and user-friendly tool, that combines both image and textual recognition, and allows an integrated study of fragmented historical heritage collections. Next to a short demonstration of MONK, we use this paper to outline how handwriting and image recognition helps to enrich the value of illustrated handwritten collections by adding information now inaccessible and disconnected. By doing so it advances the state of the art in automated extraction, classification, and networking of knowledge from heterogeneous manuscript collections and archives.
Research Interests:
Museums, archives and digital libraries make increasing use of Semantic Web technologies to enrich and publish their collection items. The contents of those items, however, are not often enriched in the same way. Extracting named entities... more
Museums, archives and digital libraries make increasing use of Semantic Web technologies to enrich and publish their collection items. The contents of those items, however, are not often enriched in the same way. Extracting named entities within historical manuscripts and disclosing the relationships between them would facilitate cultural heritage research, but it is a labour-intensive and time-consuming process, particularly for handwritten documents.
It requires either automated handwriting recognition techniques, or manual annotation by domain experts before the content can be semantically structured. Different workflows have been proposed to address this problem, involving full-text transcription and named entity extraction, with results ranging from unstructured files to semantically annotated knowledge bases. Here, we detail these workflows and describe the approach we have taken to disclose historical biodiversity data, which enables the direct labelling and semantic annotation of document images in hand-written archives.
It requires either automated handwriting recognition techniques, or manual annotation by domain experts before the content can be semantically structured. Different workflows have been proposed to address this problem, involving full-text transcription and named entity extraction, with results ranging from unstructured files to semantically annotated knowledge bases. Here, we detail these workflows and describe the approach we have taken to disclose historical biodiversity data, which enables the direct labelling and semantic annotation of document images in hand-written archives.