Pub Date : 2022-10-01DOI: 10.1109/MBITS.2022.3186293
J. Bunn
The National Archives, U.K., faces a number of information processing challenges relating to the volume, variety and velocity of the data it handles, as well as its need to ensure value and veracity. This feature highlights some of these challenges as well as some of the work it is undertaking to address them.
{"title":"Information Processing Challenges at the National Archives","authors":"J. Bunn","doi":"10.1109/MBITS.2022.3186293","DOIUrl":"https://doi.org/10.1109/MBITS.2022.3186293","url":null,"abstract":"The National Archives, U.K., faces a number of information processing challenges relating to the volume, variety and velocity of the data it handles, as well as its need to ensure value and veracity. This feature highlights some of these challenges as well as some of the work it is undertaking to address them.","PeriodicalId":448036,"journal":{"name":"IEEE BITS the Information Theory Magazine","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133147135","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-10-01DOI: 10.1109/MBITS.2022.3200641
Deborah Abramson Kroll
The Arts and Humanities Research Council (AHRC), part of UK Research and Innovation (UKRI) has supported independent academic research involving information processing tools since its founding in 2005.
{"title":"Support for AI Research at the Arts and Humanities Research Council","authors":"Deborah Abramson Kroll","doi":"10.1109/MBITS.2022.3200641","DOIUrl":"https://doi.org/10.1109/MBITS.2022.3200641","url":null,"abstract":"The Arts and Humanities Research Council (AHRC), part of UK Research and Innovation (UKRI) has supported independent academic research involving information processing tools since its founding in 2005.","PeriodicalId":448036,"journal":{"name":"IEEE BITS the Information Theory Magazine","volume":"142 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123264867","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-10-01DOI: 10.1109/MBITS.2022.3197100
Henry H. Chopp, A. McGeachy, M. Alfeld, O. Cossairt, M. Walton, A. Katsaggelos
X-ray fluorescence (XRF) analysis of art objects has rapidly gained popularity since the late 2000s due to its increased accessibility to scientists. This introduced an imaging component whereby the XRF image volume provides clues as to which chemical elements are present and where they are located spatially in the object. However, as is the nature of collecting measurements, there are limitations preventing perfect acquisition; e.g, spatial resolution, signal-to-noise ratio, etc. The field of image processing, in part, aims to overcome these limitations. Image processing applications in XRF imaging are only just starting to arise due to the increased interest and availability in XRF analysis. In this article, we aim to reach readers in XRF imaging or image processing in an effort to call for further research in the field. We review the basics of XRF imaging and analysis that is tailored for those unfamiliar with this imaging modality. We then delve into various publications of image processing methods as applied to XRF data. Throughout this article, we examine (and opine on) the XRF field through a lens of the image processing field.
{"title":"Image Processing Perspectives of X-Ray Fluorescence Data in Cultural Heritage Sciences","authors":"Henry H. Chopp, A. McGeachy, M. Alfeld, O. Cossairt, M. Walton, A. Katsaggelos","doi":"10.1109/MBITS.2022.3197100","DOIUrl":"https://doi.org/10.1109/MBITS.2022.3197100","url":null,"abstract":"X-ray fluorescence (XRF) analysis of art objects has rapidly gained popularity since the late 2000s due to its increased accessibility to scientists. This introduced an imaging component whereby the XRF image volume provides clues as to which chemical elements are present and where they are located spatially in the object. However, as is the nature of collecting measurements, there are limitations preventing perfect acquisition; e.g, spatial resolution, signal-to-noise ratio, etc. The field of image processing, in part, aims to overcome these limitations. Image processing applications in XRF imaging are only just starting to arise due to the increased interest and availability in XRF analysis. In this article, we aim to reach readers in XRF imaging or image processing in an effort to call for further research in the field. We review the basics of XRF imaging and analysis that is tailored for those unfamiliar with this imaging modality. We then delve into various publications of image processing methods as applied to XRF data. Throughout this article, we examine (and opine on) the XRF field through a lens of the image processing field.","PeriodicalId":448036,"journal":{"name":"IEEE BITS the Information Theory Magazine","volume":"136 32","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113940190","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-10-01DOI: 10.1109/MBITS.2022.3187947
D. K. Crkvenjakov
Technical studies of paintings are based on many analytical techniques that complement art historical studies. Understanding the processes that happen with the aging of the paint is very important for conservators. The paint layer cracks and lifts, the materials discolor and new layers are added over time, slowly changing the appearance of the artwork. Crack patterns in the paint layer can be used in the study of the composition of the paint layer as well as its conservation history, even for more in-depth studies of the artwork creation. Particularly interesting examples are coming from the transition periods in art history, in which the changes in the painting style and painting technique were happening. Image analysis powered by machine learning was applied in the study of the two Serbian Baroque icons. The resulting crack pattern, besides being valuable conservation documentation, opened new research questions regarding the origin of the degradation processes in the paint layer.
{"title":"Image Processing and the Analysis of Paintings—The Case of Serbian Baroque Icons","authors":"D. K. Crkvenjakov","doi":"10.1109/MBITS.2022.3187947","DOIUrl":"https://doi.org/10.1109/MBITS.2022.3187947","url":null,"abstract":"Technical studies of paintings are based on many analytical techniques that complement art historical studies. Understanding the processes that happen with the aging of the paint is very important for conservators. The paint layer cracks and lifts, the materials discolor and new layers are added over time, slowly changing the appearance of the artwork. Crack patterns in the paint layer can be used in the study of the composition of the paint layer as well as its conservation history, even for more in-depth studies of the artwork creation. Particularly interesting examples are coming from the transition periods in art history, in which the changes in the painting style and painting technique were happening. Image analysis powered by machine learning was applied in the study of the two Serbian Baroque icons. The resulting crack pattern, besides being valuable conservation documentation, opened new research questions regarding the origin of the degradation processes in the paint layer.","PeriodicalId":448036,"journal":{"name":"IEEE BITS the Information Theory Magazine","volume":"102 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115748871","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-10-01DOI: 10.1109/MBITS.2022.3196332
Bhavesh Shah, Emily R Long
Heritage objects are continually at risk from the harmful agents of deterioration, and these risks may be exacerbated by climate change [2]. Therefore, heritage institutions need to adopt a position of climate resilience; they must “anticipate, absorb, and adapt” to the effects of climate change to preserve cultural heritage for future generations [10]. One crucial step is to understand how the future climate may affect the environments surrounding heritage objects whether they are on display or in storage. Every museum and its collection is unique, so most recent research has focused on climate change case studies for particular heritage sites [9]. The next challenge is to forecast the environmental conditions and associated risks to heritage objects at a broader scale. Machine learning and data science have the potential to make this analysis accessible for more heritage institutions.
{"title":"Forecasting Environmental Conditions to Foster Climate Resilience in Heritage","authors":"Bhavesh Shah, Emily R Long","doi":"10.1109/MBITS.2022.3196332","DOIUrl":"https://doi.org/10.1109/MBITS.2022.3196332","url":null,"abstract":"Heritage objects are continually at risk from the harmful agents of deterioration, and these risks may be exacerbated by climate change [2]. Therefore, heritage institutions need to adopt a position of climate resilience; they must “anticipate, absorb, and adapt” to the effects of climate change to preserve cultural heritage for future generations [10]. One crucial step is to understand how the future climate may affect the environments surrounding heritage objects whether they are on display or in storage. Every museum and its collection is unique, so most recent research has focused on climate change case studies for particular heritage sites [9]. The next challenge is to forecast the environmental conditions and associated risks to heritage objects at a broader scale. Machine learning and data science have the potential to make this analysis accessible for more heritage institutions.","PeriodicalId":448036,"journal":{"name":"IEEE BITS the Information Theory Magazine","volume":"201 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134216734","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-10-01DOI: 10.1109/MBITS.2022.3199678
Tan Lu, A. Dooms
Textual documents, such as manuscripts and historical newspapers, make up an important part of our cultural heritage. Massive digitization projects have been conducted across the globe for a better preservation of, and for providing easier access to such, often vulnerable, documents. These digital counterparts also allow to unlock the rich information contained inside and across them thanks to various types of computational models for document image understanding. In this article, we will shed a light on the document image processing pipeline, from scan to information extraction. As it turns out, human perceptual-driven algorithms are among the most powerful approaches for generic document image understanding, required to deal with a myriad of layouts. In this context, we will in particular explain Gestalt visioning and the linked concept of text homogeneity that allows for enhanced layout analysis and even damage recognition, especially relevant in a cultural heritage setting. We conclude with a recent promising development, namely joint visual and language processing, that will take document image understanding to the next level in the future.
{"title":"Document Image Understanding: Computational Image Processing in the Cultural Heritage Sector","authors":"Tan Lu, A. Dooms","doi":"10.1109/MBITS.2022.3199678","DOIUrl":"https://doi.org/10.1109/MBITS.2022.3199678","url":null,"abstract":"Textual documents, such as manuscripts and historical newspapers, make up an important part of our cultural heritage. Massive digitization projects have been conducted across the globe for a better preservation of, and for providing easier access to such, often vulnerable, documents. These digital counterparts also allow to unlock the rich information contained inside and across them thanks to various types of computational models for document image understanding. In this article, we will shed a light on the document image processing pipeline, from scan to information extraction. As it turns out, human perceptual-driven algorithms are among the most powerful approaches for generic document image understanding, required to deal with a myriad of layouts. In this context, we will in particular explain Gestalt visioning and the linked concept of text homogeneity that allows for enhanced layout analysis and even damage recognition, especially relevant in a cultural heritage setting. We conclude with a recent promising development, namely joint visual and language processing, that will take document image understanding to the next level in the future.","PeriodicalId":448036,"journal":{"name":"IEEE BITS the Information Theory Magazine","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130832708","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-10-01DOI: 10.1109/MBITS.2022.3197102
Zhuomin Zhang, Jia Li, David G. Stork, Elizabeth C. Mansfield, John Russell, Catherine Adams, James Ze Wang
Empirical research in science and the humanities is vulnerable to bias which, by definition, implies incorrect or misleading findings. Artificial intelligence-based analysis of visual artworks is vulnerable to bias in ways specific to the domain. Works of art belong to a distinct cultural category that often prioritizes such characteristics as hand-craftsmanship, uniqueness, originality, and imaginative content; works of art are also responsive to diverse social and cultural contexts. Ascertaining which features of an artwork can be rightly ascribed to an objective “truth,” without which the concept of bias is not even relevant, is itself challenging. Incorporating expert knowledge into machine learning applications can help reduce bias in final estimates. We review several sources of bias that can occur across different stages of AI-based analysis, protocols, and best practices for reducing bias, and approaches to measuring these biases. This systematic investigation of various types of bias can help researchers better understand bias, become aware of practical solutions, and ultimately cultivate the prudent adoption of AI-based approaches to artwork analysis.
{"title":"Reducing Bias in AI-Based Analysis of Visual Artworks","authors":"Zhuomin Zhang, Jia Li, David G. Stork, Elizabeth C. Mansfield, John Russell, Catherine Adams, James Ze Wang","doi":"10.1109/MBITS.2022.3197102","DOIUrl":"https://doi.org/10.1109/MBITS.2022.3197102","url":null,"abstract":"Empirical research in science and the humanities is vulnerable to bias which, by definition, implies incorrect or misleading findings. Artificial intelligence-based analysis of visual artworks is vulnerable to bias in ways specific to the domain. Works of art belong to a distinct cultural category that often prioritizes such characteristics as hand-craftsmanship, uniqueness, originality, and imaginative content; works of art are also responsive to diverse social and cultural contexts. Ascertaining which features of an artwork can be rightly ascribed to an objective “truth,” without which the concept of bias is not even relevant, is itself challenging. Incorporating expert knowledge into machine learning applications can help reduce bias in final estimates. We review several sources of bias that can occur across different stages of AI-based analysis, protocols, and best practices for reducing bias, and approaches to measuring these biases. This systematic investigation of various types of bias can help researchers better understand bias, become aware of practical solutions, and ultimately cultivate the prudent adoption of AI-based approaches to artwork analysis.","PeriodicalId":448036,"journal":{"name":"IEEE BITS the Information Theory Magazine","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126149461","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-10-01DOI: 10.1109/MBITS.2022.3207125
B. Sober, S. Bucklow, Nathan Daly, I. Daubechies, P. Dragotti, C. Higgitt, Jun-Jie Huang, A. Pižurica, Wei Pu, Suzanne Reynolds, Miguel R. D. Rodrigues, C. Schönlieb, Su Yan
In recent decades, cultural heritage research—and in particular art investigation—has been undergoing a digital revolution. This is due both to improvements in the digitization and the acquisition of artifact’s images generated using traditional 2-D imaging methods as well as the growing adoption of a range of more recently introduced spectroscopic imaging techniques. A number of these imaging modalities use wavelengths of electromagnetic radiation that can penetrate surface layers thus yielding information from hidden features noninvasively. Different techniques are often used in combination to provide evidence of construction, condition, and past treatment. These can also be used to characterize the materials used, how they were combined, and map their distribution, giving insight into an artist’s working method and the means to understand changes that have occurred over time. This wealth of data calls for the development of algorithmic approaches in order to handle and fully explore and interpret it. The questions one seeks to answer are in some cases sufficiently different from those addressed in other fields that no existing off-the-shelf approaches can be applied. In this article, we discuss a few of the algorithmic challenges that arise in art investigation and conservation using modern imaging techniques.
{"title":"Revealing and Reconstructing Hidden or Lost Features in Art Investigation","authors":"B. Sober, S. Bucklow, Nathan Daly, I. Daubechies, P. Dragotti, C. Higgitt, Jun-Jie Huang, A. Pižurica, Wei Pu, Suzanne Reynolds, Miguel R. D. Rodrigues, C. Schönlieb, Su Yan","doi":"10.1109/MBITS.2022.3207125","DOIUrl":"https://doi.org/10.1109/MBITS.2022.3207125","url":null,"abstract":"In recent decades, cultural heritage research—and in particular art investigation—has been undergoing a digital revolution. This is due both to improvements in the digitization and the acquisition of artifact’s images generated using traditional 2-D imaging methods as well as the growing adoption of a range of more recently introduced spectroscopic imaging techniques. A number of these imaging modalities use wavelengths of electromagnetic radiation that can penetrate surface layers thus yielding information from hidden features noninvasively. Different techniques are often used in combination to provide evidence of construction, condition, and past treatment. These can also be used to characterize the materials used, how they were combined, and map their distribution, giving insight into an artist’s working method and the means to understand changes that have occurred over time. This wealth of data calls for the development of algorithmic approaches in order to handle and fully explore and interpret it. The questions one seeks to answer are in some cases sufficiently different from those addressed in other fields that no existing off-the-shelf approaches can be applied. In this article, we discuss a few of the algorithmic challenges that arise in art investigation and conservation using modern imaging techniques.","PeriodicalId":448036,"journal":{"name":"IEEE BITS the Information Theory Magazine","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129957596","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-10-01DOI: 10.1109/MBITS.2022.3205876
Bart Devolder
As a conservator specializing in paintings, I first got in contact with machine (deep) learning in 2015, when I was working as part of a team of conservators from the Royal Institute for Cultural Heritage (KIK-IRPA) restoring the Ghent Altarpiece (1426) by the van Eyck brothers.
{"title":"Machine Learning in the Eyes of a Painting Conservator","authors":"Bart Devolder","doi":"10.1109/MBITS.2022.3205876","DOIUrl":"https://doi.org/10.1109/MBITS.2022.3205876","url":null,"abstract":"As a conservator specializing in paintings, I first got in contact with machine (deep) learning in 2015, when I was working as part of a team of conservators from the Royal Institute for Cultural Heritage (KIK-IRPA) restoring the Ghent Altarpiece (1426) by the van Eyck brothers.","PeriodicalId":448036,"journal":{"name":"IEEE BITS the Information Theory Magazine","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113971302","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-10-01DOI: 10.1109/MBITS.2022.3205288
Haizi Yu, L. Varshney, Heinrich Taube, James A. Evans
Information lattice learning (ILL) is a novel framework for knowledge discovery based on group-theoretic and information-theoretic foundations, which can rediscover the rules of music as known in the canon of music theory and also discover new rules that have remained unexamined. Such probabilistic rules are further demonstrated to be human-interpretable. ILL itself is a rediscovery and generalization of Shannon’s lattice theory of information, where probability measures are not given but are learned from training data. This article explains the basics of the ILL framework, including both how to construct a lattice-structured abstraction universe that specifies the structural possibilities of rules, and how to find the most informative rules by performing statistical learning through an iterative student–teacher algorithmic architecture that optimizes information functionals. The ILL framework is finally shown to support both pedagogy and novel patterns of music co-creativity.
{"title":"(Re)discovering Laws of Music Theory Using Information Lattice Learning","authors":"Haizi Yu, L. Varshney, Heinrich Taube, James A. Evans","doi":"10.1109/MBITS.2022.3205288","DOIUrl":"https://doi.org/10.1109/MBITS.2022.3205288","url":null,"abstract":"Information lattice learning (ILL) is a novel framework for knowledge discovery based on group-theoretic and information-theoretic foundations, which can rediscover the rules of music as known in the canon of music theory and also discover new rules that have remained unexamined. Such probabilistic rules are further demonstrated to be human-interpretable. ILL itself is a rediscovery and generalization of Shannon’s lattice theory of information, where probability measures are not given but are learned from training data. This article explains the basics of the ILL framework, including both how to construct a lattice-structured abstraction universe that specifies the structural possibilities of rules, and how to find the most informative rules by performing statistical learning through an iterative student–teacher algorithmic architecture that optimizes information functionals. The ILL framework is finally shown to support both pedagogy and novel patterns of music co-creativity.","PeriodicalId":448036,"journal":{"name":"IEEE BITS the Information Theory Magazine","volume":"137 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116411540","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：