@article{chenDigitalExtractionSegmentation2025,
	title = {Digital extraction and segmentation of intangible cultural heritage paper-cut patterns},
	copyright = {https://academic.oup.com/pages/standard-publication-reuse-rights},
	issn = {2055-7671, 2055-768X},
	url = {https://academic.oup.com/dsh/advance-article/doi/10.1093/llc/fqaf006/8380328},
	doi = {10.1093/llc/fqaf006},
	abstract = {Abstract
            As a unique intangible cultural heritage in Chinese traditional culture, paper-cut art is now facing the dilemma of inheritance and development, and with the death of paper-cut artists and the damage and loss of paper-cut works, some paper-cut types also disappear. Therefore, the digital protection of paper-cut art is urgent. This research is based on the improved genetic algorithm adaptive optimization of Canny operator threshold and Grab-Cut algorithm to achieve intelligent extraction and segmentation of intangible cultural heritage paper-cut patterns. First, the collected paper-cut images are smoothed by bilateral filtering to improve the image quality. Second, based on the Canny operator optimized by the improved genetic algorithm, the overall contour of the paper-cut pattern is extracted. Then, the Grab-Cut algorithm is designed to segment the contours of decoupage design elements in a targeted way, and the vector image is processed by CDR software to obtain an independent editable vector image. Finally, the contour extraction experiments of different kinds of paper-cut images are compared by different algorithms. The results show that the method proposed in this article can effectively detect the true edge of the pattern in paper-cut images and complete the extraction of the pattern contour, and the accuracy of the segmentation pixels of each design element of paper-cut pattern is greater than 96 per cent. It provides a new method for the digital protection and innovative application of intangible cultural heritage paper-cut art.},
	language = {en},
	urldate = {2026-01-19},
	journal = {Digital Scholarship in the Humanities},
	author = {Chen, Daoling and Cheng, Pengpeng},
	month = dec,
	year = {2025},
	pages = {fqaf006},
}

@incollection{dancygier2016multimodality,
	title = {Multimodality and theatre: {Material} objects, bodies and language},
	booktitle = {Theatre, performance, and cognition: {Languages}, bodies and ecologies},
	publisher = {Bloomsbury Methuen},
	author = {Dancygier, Barbara},
	editor = {Blair, Rhonda and Cook, Amy},
	year = {2016},
	pages = {21--39},
}

@article{soriano-gonzalezExploringImageText2025,
	title = {Exploring image–text combinations in visual humour through large language models ({LLMs})},
	volume = {40},
	copyright = {https://academic.oup.com/pages/standard-publication-reuse-rights},
	issn = {2055-7671, 2055-768X},
	url = {https://academic.oup.com/dsh/article/40/1/280/7909470},
	doi = {10.1093/llc/fqae068},
	abstract = {Abstract
            This article aims to advance the scholarly discourse on the linguistic capabilities of Artificial Intelligence (AI) by analysing how three different Large Language models (LLMs) approach visual humour. Specifically, it focuses on meme generation and interpretation, with an emphasis on image–text combinations. In the first section, three LLMs were prompted to generate accompanying text for ten preselected images. In the second section, they were prompted to analyse one hundred human-made memes. Results show that, despite a generally positive evaluation in humour detection, applying non-literal meaning remains a challenge, even for the best-performing AI models.},
	language = {en},
	number = {1},
	urldate = {2025-09-30},
	journal = {Digital Scholarship in the Humanities},
	author = {Soriano-Gonzalez, Laura and Belda-Medina, Jose},
	month = apr,
	year = {2025},
	pages = {280--294},
}

@article{arnoldDistantViewingAnalyzing2019,
	title = {Distant viewing: analyzing large visual corpora},
	volume = {34},
	copyright = {https://academic.oup.com/journals/pages/open\_access/funder\_policies/chorus/standard\_publication\_model},
	issn = {2055-7671, 2055-768X},
	shorttitle = {Distant viewing},
	url = {https://academic.oup.com/dsh/article/34/Supplement_1/i3/5694340},
	doi = {10.1093/llc/fqz013},
	abstract = {Abstract
            In this article we establish a methodological and theoretical framework for the study of large collections of visual materials. Our framework, distant viewing, is distinguished from other approaches by making explicit the interpretive nature of extracting semantic metadata from images. In other words, one must ‘view’ visual materials before studying them. We illustrate the need for the interpretive process of viewing by simultaneously drawing on theories of visual semiotics, photography, and computer vision. Two illustrative applications of the distant viewing framework to our own research are draw upon to explicate the potential and breadth of the approach. A study of television series shows how facial detection is used to compare the role of actors within the narrative arcs across two competing series. An analysis of the Farm Security Administration–Office of War Information corpus of documentary photography is used to establish how photographic style compared and differed amongst those photographers involved with the collection. We then aim to show how our framework engages with current methodological and theoretical conversations occurring within the digital humanities.},
	language = {en},
	number = {Supplement\_1},
	urldate = {2025-09-25},
	journal = {Digital Scholarship in the Humanities},
	author = {Arnold, Taylor and Tilton, Lauren},
	month = dec,
	year = {2019},
	pages = {i3--i16},
	file = {PDF:/home/thomas/Zotero/storage/BHGPPQZ4/Arnold und Tilton - 2019 - Distant viewing analyzing large visual corpora.pdf:application/pdf},
}

@book{ayyadevaraModernComputerVision2024,
	address = {Birmingham},
	edition = {1},
	title = {Modern {Computer} {Vision} with {PyTorch}: {A} practical roadmap from deep learning fundamentals to advanced applications and {Generative} {AI}},
	isbn = {978-1-80324-093-0},
	shorttitle = {Modern {Computer} {Vision} with {PyTorch}},
	abstract = {The definitive computer vision book is back, featuring the latest neural network architectures and an exploration of foundation and diffusion models Purchase of the print or Kindle book includes a free eBook in PDF formatKey FeaturesUnderstand the inner workings of various neural network architectures and their implementation, including image classification, object detection, segmentation, generative adversarial networks, transformers, and diffusion modelsBuild solutions for real-world computer vision problems using PyTorchAll the code files are available on GitHub and can be run on Google ColabBook DescriptionWhether you are a beginner or are looking to progress in your computer vision career, this book guides you through the fundamentals of neural networks (NNs) and PyTorch and how to implement state-of-the-art architectures for real-world tasks. The second edition of Modern Computer Vision with PyTorch is fully updated to explain and provide practical examples of the latest multimodal models, CLIP, and Stable Diffusion. You' ll discover best practices for working with images, tweaking hyperparameters, and moving models into production. As you progress, you'll implement various use cases for facial keypoint recognition, multi-object detection, segmentation, and human pose detection. This book provides a solid foundation in image generation as you explore different GAN architectures. You' ll leverage transformer-based architectures like ViT, TrOCR, BLIP2, and LayoutLM to perform various real-world tasks and build a diffusion model from scratch. Additionally, you' ll utilize foundation models' capabilities to perform zero-shot object detection and image segmentation. Finally, you' ll learn best practices for deploying a model to production. By the end of this deep learning book, you'll confidently leverage modern NN architectures to solve real-world computer vision problems.What you will learnGet to grips with various transformer-based architectures for computer vision, CLIP, Segment-Anything, and Stable Diffusion, and test their applications, such as in-painting and pose transferCombine CV with NLP to perform OCR, key-value extraction from document images, visual question-answering, and generative AI tasksImplement multi-object detection and segmentationLeverage foundation models to perform object detection and segmentation without any training data pointsLearn best practices for moving a model to productionWho this book is forThis book is for beginners to PyTorch and intermediate-level machine learning practitioners who want to learn computer vision techniques using deep learning and PyTorch. It's useful for those just getting started with neural networks, as it will enable readers to learn from real-world use cases accompanied by notebooks on GitHub. Basic knowledge of the Python programming language and ML is all you need to get started with this book. For more experienced computer vision scientists, this book takes you through more advanced models in the latter part of the book},
	language = {eng},
	publisher = {Packt Publishing Limited},
	author = {Ayyadevara, V. Kishore},
	collaborator = {Reddy, Yeshwanth},
	year = {2024},
	file = {PDF:/home/thomas/Zotero/storage/K526WD6N/Ayyadevara - 2024 - Modern Computer Vision with PyTorch A practical roadmap from deep learning fundamentals to advanced.pdf:application/pdf},
}

@article{schmidtExploringComputerVision2021,
	title = {Exploring {Computer} {Vision} for {Film} {Analysis}: {A} {Case} {Study} for {Five} {Canonical} {Movies}},
	shorttitle = {Exploring {Computer} {Vision} for {Film} {Analysis}},
	url = {https://epub.uni-regensburg.de/id/eprint/50867},
	doi = {10.5283/EPUB.50867},
	abstract = {We present an exploratory study in the context of digital film analysis inspecting and comparing five canonical movies by applying methods of computer vision. We extract one frame per second of each movie which we regard as our sample. As computer vision methods we explore image-based object detection, emotion recognition, gender and age detection with state-of-the-art models. We were able to identify significant differences between the movies for all methods. We present our results and discuss the limitations and benefits of each method. We close by formulating future research questions we plan to answer by applying and optimizing the methods.},
	urldate = {2025-09-22},
	publisher = {Universität Regensburg},
	author = {Schmidt, Thomas and El-Keilany, Alina and Eger, Johannes and Kurek, Sarah},
	year = {2021},
	keywords = {004 Informatik, 791 Öffentliche Darbietungen, Film, Rundfunk, film studies, film analysis, computer vision, object detection, emotion recognition, gender, age},
}

@article{smitsMultimodalTurnDigital2023,
	title = {A multimodal turn in {Digital} {Humanities}. {Using} contrastive machine learning models to explore, enrich, and analyze digital visual historical collections},
	volume = {38},
	copyright = {https://creativecommons.org/licenses/by-nc/4.0/},
	issn = {2055-7671, 2055-768X},
	url = {https://academic.oup.com/dsh/article/38/3/1267/7078540},
	doi = {10.1093/llc/fqad008},
	abstract = {Abstract
            Until recently, most research in the Digital Humanities (DH) was monomodal, meaning that the object of analysis was either textual or visual. Seeking to integrate multimodality theory into the DH, this article demonstrates that recently developed multimodal deep learning models, such as Contrastive Language Image Pre-training (CLIP), offer new possibilities to explore and analyze image–text combinations at scale. These models, which are trained on image and text pairs, can be applied to a wide range of text-to-image, image-to-image, and image-to-text prediction tasks. Moreover, multimodal models show high accuracy in zero-shot classification, i.e. predicting unseen categories across heterogeneous datasets. Based on three exploratory case studies, we argue that this zero-shot capability opens up the way for a multimodal turn in DH research. Moreover, multimodal models allow scholars to move past the artificial separation of text and images that was dominant in the field and analyze multimodal meaning at scale. However, we also need to be aware of the specific (historical) bias of multimodal deep learning that stems from biases in the training data used to train these models.},
	language = {en},
	number = {3},
	urldate = {2025-09-22},
	journal = {Digital Scholarship in the Humanities},
	author = {Smits, Thomas and Wevers, Melvin},
	month = aug,
	year = {2023},
	pages = {1267--1280},
	file = {Volltext:/home/thomas/Zotero/storage/IFHRIGQG/Smits und Wevers - 2023 - A multimodal turn in Digital Humanities. Using contrastive machine learning models to explore, enric.pdf:application/pdf},
}

@article{fischerSemiautomatischeErschliessungFotografien2025,
	title = {Semiautomatische {Erschließung} von {Fotografien} auf beschrifteten {Bildkarten} im {Archiv}. {Dokumentenerkennung} mit {Deep} {Learning} sowie {Large}-{Language}-{Modellen}},
	volume = {10},
	issn = {2510-1358},
	url = {https://zfdg.de/2025_009},
	doi = {10.17175/2025_009},
	abstract = {The automated extraction of image-text archival material can make their cataloguing and FAIR provision more efficient, improve their findability and subsequent uses such as semantic search or data-based analyses. We report on an experiment in which the texts of record cards from the Leibniz-Zentrum für Archäologie (LEIZA) were semantically extracted using two methods: a classical deep learning pipeline and large language models (LLMs) such as GPT-4o. Both approaches achieved good results, with the LLMs being better able to deal with the different structures of the record cards. With automated pre– and post-processing, we achieved recognition rates of over 90 \%. Challenges comprise the different record card structures and handwritten entries, for which the extraction performs significantly worse.},
	language = {de},
	urldate = {2025-09-03},
	journal = {Zeitschrift für digitale Geisteswissenschaften},
	publisher = {Forschungsverbund Marbach Weimar Wolfenbüttel / Digital Humanities im deutschsprachigen Raum e. V.},
	author = {Fischer, Norbert and Kimmel, Dominik and Puppe, Frank},
	year = {2025},
	note = {Version Number: 1.0},
	keywords = {Archäologie, Archiv, Bilderkennung, Bildkarte, Großes Sprachmodell, Optische Zeichenerkennung},
}

@article{bammanMeasuringDiversityHollywood2024,
	title = {Measuring diversity in {Hollywood} through the large-scale computational analysis of film},
	volume = {121},
	issn = {0027-8424, 1091-6490},
	url = {https://pnas.org/doi/10.1073/pnas.2409770121},
	doi = {10.1073/pnas.2409770121},
	abstract = {Movies are a massively popular and influential form of media, but their computational study at scale has largely been off-limits to researchers in the United States due to the Digital Millennium Copyright Act. In this work, we illustrate use of a new regulatory framework to enable computational research on film that permits circumvention of technological protection measures on digital video discs (DVDs). We use this exemption to legally digitize a collection of 2,307 films representing the top 50 movies by U.S. box office over the period 1980 to 2022, along with award nominees. We design a computational pipeline for measuring the representation of gender and race/ethnicity in film, drawing on computer vision models for recognizing actors and human perceptions of gender and race/ethnicity. Doing so allows us to learn substantive facts about representation and diversity in Hollywood over this period, confirming earlier studies that see an increase in diversity over the past decade, while allowing us to use computational methods to uncover a range of ad hoc analytical findings. Our work illustrates the affordances of the data-driven analysis of film at a large scale.},
	language = {en},
	number = {46},
	urldate = {2025-06-10},
	journal = {Proceedings of the National Academy of Sciences},
	author = {Bamman, David and Samberg, Rachael and So, Richard Jean and Zhou, Naitian},
	month = nov,
	year = {2024},
	pages = {e2409770121},
	file = {Full Text PDF:/home/thomas/Zotero/storage/V7UW86E7/Bamman et al. - 2024 - Measuring diversity in Hollywood through the large-scale computational analysis of film.pdf:application/pdf},
}

@book{arnoldDistantViewingComputational2023,
	title = {Distant {Viewing}: {Computational} {Exploration} of {Digital} {Images}},
	copyright = {https://creativecommons.org/licenses/by-nc-nd/4.0/},
	isbn = {978-0-262-37516-0},
	shorttitle = {Distant {Viewing}},
	url = {https://direct.mit.edu/books/book/5674/Distant-ViewingComputational-Exploration-of},
	doi = {10.7551/mitpress/14046.001.0001},
	abstract = {A new theory and methodology for the application of computer vision methods to the computational analysis of collected, digitized visual materials, called “distant viewing.”
            Distant Viewing: Computational Exploration of Digital Images presents a new theory and methodology for the computational analysis of digital images, offering a lively, constructive critique of computer vision that you can actually use. What does it mean to say that computer vision “understands” visual inputs? Annotations never capture a whole image. The way digital images convey information requires what researchers Taylor Arnold and Lauren Tilton call “distant viewing”—a play on the well-known term “distant reading” from computational literary analysis.
            Recognizing computer vision's limitations, Arnold and Tilton's spirited examination makes the technical exciting by applying distant viewing to the sitcoms Bewitched and I Dream of Jeannie, movie posters and other popular forms of advertising, and Dorothea Lange's photography. In the tradition of visual culture studies and computer vision, Distant Viewing's interdisciplinary perspective encompasses film and media studies, visual semiotics, and the sciences to create a playful, accessible guide for an international audience working in digital humanities, data science, media studies, and visual culture studies.},
	language = {en},
	urldate = {2026-02-09},
	publisher = {The MIT Press},
	author = {Arnold, Taylor and Tilton, Lauren},
	month = oct,
	year = {2023},
	file = {PDF:/home/thomas/Zotero/storage/D4A7SJ5G/Arnold und Tilton - 2023 - Distant Viewing Computational Exploration of Digital Images.pdf:application/pdf},
}

@article{somandepalliComputationalMediaIntelligence2021,
	title = {Computational {Media} {Intelligence}: {Human}-{Centered} {Machine} {Analysis} of {Media}},
	volume = {109},
	copyright = {https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html},
	issn = {0018-9219, 1558-2256},
	shorttitle = {Computational {Media} {Intelligence}},
	url = {https://ieeexplore.ieee.org/document/9319168/},
	doi = {10.1109/JPROC.2020.3047978},
	number = {5},
	urldate = {2026-05-06},
	journal = {Proceedings of the IEEE},
	author = {Somandepalli, Krishna and Guha, Tanaya and Martinez, Victor R. and Kumar, Naveen and Adam, Hartwig and Narayanan, Shrikanth},
	month = may,
	year = {2021},
	pages = {891--910},
	file = {PDF:/home/thomas/Zotero/storage/R8Y4IS6C/Somandepalli et al. - 2021 - Computational Media Intelligence Human-Centered Machine Analysis of Media.pdf:application/pdf},
}

@article{cuttingQuickerFasterDarker2011,
	title = {Quicker, {Faster}, {Darker}: {Changes} in {Hollywood} {Film} over 75 {Years}},
	volume = {2},
	issn = {2041-6695, 2041-6695},
	shorttitle = {Quicker, {Faster}, {Darker}},
	url = {https://journals.sagepub.com/doi/10.1068/i0441aap},
	doi = {10.1068/i0441aap},
	abstract = {We measured 160 English-language films released from 1935 to 2010 and found four changes. First, shot lengths have gotten shorter, a trend also reported by others. Second, contemporary films have more motion and movement than earlier films. Third, in contemporary films shorter shots also have proportionately more motion than longer shots, whereas there is no such relation in older films. And finally films have gotten darker. That is, the mean luminance value of frames across the length of a film has decreased over time. We discuss psychological effects associated with these four changes and suggest that all four linear trends have a single cause: Filmmakers have incrementally tried to exercise more control over the attention of filmgoers. We suggest these changes are signatures of the evolution of popular film; they do not reflect changes in film style.},
	language = {en},
	number = {6},
	urldate = {2026-05-06},
	journal = {i-Perception},
	author = {Cutting, James E and Brunick, Kaitlin L and DeLong, Jordan E and Iricinschi, Catalina and Candan, Ayse},
	month = aug,
	year = {2011},
	pages = {569--576},
	file = {SAGE PDF Full Text:/home/thomas/Zotero/storage/ZRFM9TRW/Cutting et al. - 2011 - Quicker, Faster, Darker Changes in Hollywood Film over 75 Years.pdf:application/pdf},
}

@article{arnoldVisualStyleTwo2019,
	title = {Visual {Style} in {Two} {Network} {Era} {Sitcoms}},
	volume = {4},
	issn = {2371-4549},
	url = {https://culturalanalytics.org/article/id/1194/},
	doi = {10.22148/16.043},
	number = {2},
	urldate = {2026-05-06},
	journal = {Journal of Cultural Analytics},
	author = {Arnold, Taylor and Tilton, Lauren and Berke, Annie},
	month = jul,
	year = {2019},
	pages = {1194},
	file = {Full Text PDF:/home/thomas/Zotero/storage/YZQV4K4H/Arnold et al. - 2019 - Visual Style in Two Network Era Sitcoms.pdf:application/pdf},
}

@article{saltStatisticalStyleAnalysis1974,
	title = {Statistical {Style} {Analysis} of {Motion} {Pictures}},
	volume = {28},
	issn = {0015-1386},
	url = {https://online.ucpress.edu/fq/article/28/1/13/38835/Statistical-Style-Analysis-of-Motion-Pictures},
	doi = {10.2307/1211438},
	language = {en},
	number = {1},
	urldate = {2026-05-06},
	journal = {Film Quarterly},
	author = {Salt, Barry},
	month = oct,
	year = {1974},
	pages = {13--22},
	file = {PDF:/home/thomas/Zotero/storage/I4QAEJ27/Salt - 1974 - Statistical Style Analysis of Motion Pictures.pdf:application/pdf},
}

@article{butlerStatisticalAnalysisTelevision2014,
	title = {Statistical {Analysis} of {Television} {Style}: {What} {Can} {Numbers} {Tell} {Us} about {TV} {Editing}?},
	volume = {54},
	issn = {1527-2087},
	shorttitle = {Statistical {Analysis} of {Television} {Style}},
	url = {https://muse.jhu.edu/article/558858},
	doi = {10.1353/cj.2014.0066},
	abstract = {This article assays the value of splicing together humanities-based analysis of television style with digitally generated statistical data. The editing style of the situation comedy Happy Days (1974–1984) provides an intriguing test case for the utility of such analyses, as the show made a radical shift in its mode of production after its second season—switching from single camera to multiple camera (with a studio audience). Using data collected on Shot Logger ( http://www.shotlogger.org ), this article measures the cutting rates correlated with each mode of production and finds a statistically significant difference between the two. Additionally, the article examines the general acceleration of cutting rates on American television since 1951 and comes to a perhaps surprising conclusion about the impact of individual editors on television style.},
	language = {en},
	number = {1},
	urldate = {2026-05-06},
	journal = {Cinema Journal},
	author = {Butler, Jeremy},
	month = sep,
	year = {2014},
	pages = {25--44},
	file = {PDF:/home/thomas/Zotero/storage/FBBCIELM/Butler - 2014 - Statistical Analysis of Television Style What Can Numbers Tell Us about TV Editing.pdf:application/pdf},
}

@inproceedings{burghardtShotLengthsUsing2016,
	address = {Kraków},
	title = {Beyond {Shot} {Lengths} – {Using} {Language} {Data} and {Color} {Information} as {Additional} {Parameters} for {Quantitative} {Movie} {Analysis}},
	url = {https://www.researchgate.net/publication/305277308_Beyond_Shot_Lengths_-_Using_Language_Data_and_Color_Information_as_Additional_Parameters_for_Quantitative_Movie_Analysis},
	urldate = {2026-05-06},
	booktitle = {Digital {Humanities} 2016: {Conference} {Abstracts}},
	publisher = {Jagiellonian University \& Pedagogical University},
	author = {Burghardt, Manuel and Kao, Michael and Wolff, Christian},
	year = {2016},
	pages = {753--755},
	file = {PDF:/home/thomas/Zotero/storage/P6C4EZ5B/Burghardt et al. - 2016 - Beyond Shot Lengths – Using Language Data and Color Information as Additional Parameters for Quantit.pdf:application/pdf},
}

@article{fergusonDigitalSurrealismVisualizing2016,
	title = {Digital {Surrealism}: {Visualizing} {Walt} {Disney} {Animation} {Studios}},
	volume = {11},
	issn = {1938-4122},
	shorttitle = {Digital {Surrealism}},
	url = {https://dhq.digitalhumanities.org/vol/11/1/000276/000276.html},
	doi = {10.63744/xtpq8gu3cfct},
	abstract = {There are a number of fruitful digital humanities approaches to cinema and media studies, but most of them only pursue traditional forms of scholarship by extracting a single variable from the audiovisual text that is already legible to scholars. As an alternative, cinema and media studies should pursue a mostly-ignored digital surrealism that uses computer-based methods to transform film texts in radical ways not previously possible. This article describes one such method using the z-projection function of the scientific image analysis software ImageJ to sum film frames in order to create new composite images. Working with the fifty-five feature-length films from Walt Disney Animation Studios, I describe how this method allows for a unique understanding of a film corpus not otherwise available to cinema and media studies scholars.},
	language = {en},
	number = {1},
	urldate = {2026-05-06},
	journal = {Digital Humanities Quarterly},
	author = {Ferguson, Kevin L.},
	month = nov,
	year = {2016},
}

@article{burgesCollectiveReadingShot2016,
	title = {Collective {Reading}: {Shot} {Analysis} and {Data} {Visualization} in the {Digital} {Humanities}},
	volume = {3},
	url = {https://teachingmedia.org/collective-reading-shot-analysis-and-data-visualization-in-the-digital-humanities/},
	number = {3},
	urldate = {2026-05-06},
	journal = {Cinema Journal Teaching Dossier},
	author = {Burges, Joel and Dimmock, Nora and Romphf, Joshua},
	month = jan,
	year = {2016},
}

@book{gonzalez_digital_2018,
	address = {New York, New York},
	edition = {Fourth, global edition},
	title = {Digital image processing},
	isbn = {978-1-292-22304-9 978-1-292-22307-0},
	abstract = {For years, Image Processing has been the foundational text for the study of digital image processing. The book is suited for students at the college senior and first-year graduate level with prior background in mathematical analysis, vectors, matrices, probability, statistics, linear systems, and computer programming. As in all earlier editions, the focus of this edition of the book is on fundamentals. The 4th Edition is based on an extensive survey of faculty, students, and independent readers in 5 institutions from 3 countries. Their feedback led to expanded or new coverage of topics such as deep learning and deep neural networks, including convolutional neural nets, the scale-invariant feature transform (SIFT), MERS, graph cuts, k-means clustering and superpiels, active contours (snakes and level sets), and each histogram matching. Major improvements were made in reorganising the material on image transforms into a more cohesive presentation, and in the discussion of spatial kernels and spatial filtering. Major revisions and additions were made to examples and homework exercises throughout the book},
	language = {eng},
	publisher = {Pearson Education},
	author = {Gonzalez, Rafael C. and Woods, Richard E.},
	year = {2018},
	file = {PDF:/home/thomas/Zotero/storage/BM6JFDLX/Gonzalez und Woods - 2018 - Digital image processing.pdf:application/pdf},
}

@article{loeffler_irgendwas_2026,
	title = {Irgendwas in {Japan}. {Erfahrungswerte} zur {Bildsuche} und {Bilderkennung} in der architekturhistorischen {Forschung}},
	volume = {Sonderband 8},
	issn = {2510-1366},
	url = {https://zfdg.de/sb008_007},
	doi = {10.17175/SB008_007},
	abstract = {Digital photography and retro-digitisation give architectural history research important impulses: they broaden our horizons, involve new materials and thus make it possible to ask new questions. At the same time, there are epistemic obstacles in image recognition that even AI developments are not yet able to overcome. The essay outlines these contexts and calls for further engagement in cross-disciplinary cooperation in the digital humanities in order to open up even more avenues for globally orientated architectural history.},
	language = {de},
	urldate = {2026-07-06},
	journal = {Bildähnlichkeit und Bildsuche: Geistes- und informationswissenschaftliche Zugänge zu historischem Material},
	publisher = {Forschungsverbund Marbach Weimar Wolfenbüttel / Digital Humanities im deutschsprachigen Raum e. V.},
	author = {Löffler, Beate},
	year = {2026},
	note = {Version Number: 1.0},
	keywords = {Japan, Metadaten, Architekturgeschichte, Fotografie},
	file = {PDF:/home/thomas/Zotero/storage/SAW4L7YP/Löffler - 2026 - Irgendwas in Japan. Erfahrungswerte zur Bildsuche und Bilderkennung in der architekturhistorischen F.pdf:application/pdf},
}

@article{otto_bodies_2026,
	title = {Bodies in {Relation}. {Theater} {Photography} and the {Distant} {Viewing} of {Performance}},
	volume = {Sonderband 8},
	issn = {2510-1366},
	url = {https://zfdg.de/sb008_006},
	doi = {10.17175/SB008_006},
	abstract = {Theaterfotografie schuf ein umfangreiches visuelles Archiv der darstellenden Künste des 20. Jahrhunderts, das wegen des prekären Status des Mediums und der Archivgröße vernachlässigt wurde. Der Aufsatz argumentiert, dass Deep Learning für Computer Vision beide Herausforderungen bewältigen kann und sich Distant-Viewing-Ansätze aus Digitaler Literaturwissenschaft und Kunstgeschichte auf Theaterwissenschaft anwenden lassen. Mit Fokus auf Szenenaufnahmen wird diskutiert, warum Skalierung diese Materialien interessant macht. Disziplinäre Einwände werden adressiert und es wird vorgeschlagen, dass der Nutzen des Ansatzes im Herausfordern vorherrschender Paradigmen liegt. Die Arbeit untersucht Bildkomposition, die theaterspezifische Perspektive und Technologien wie Pose Estimation, Mesh Recognition und Sentiment Analysis. Sie erforscht die Nutzung ›voreingenommener‹ kommerzieller Technologien als wissenschaftliche Instrumente und argumentiert, dass Skalierung empirische Perspektiven provoziert. An die Stelle der ästhetischen Diskussion einzelner Aufführungsereignisse rückt die Untersuchung der medialen Repräsentation theatraler Körperbilder.},
	language = {en},
	urldate = {2026-07-06},
	journal = {Bildähnlichkeit und Bildsuche: Geistes- und informationswissenschaftliche Zugänge zu historischem Material},
	publisher = {Forschungsverbund Marbach Weimar Wolfenbüttel / Digital Humanities im deutschsprachigen Raum e. V.},
	author = {Otto, Ulf},
	year = {2026},
	note = {Version Number: 1.0},
	keywords = {Bilderkennung, Fotografie, Maschinelles Sehen, OpenCV, Theaterwissenschaft},
	file = {PDF:/home/thomas/Zotero/storage/K63NJMJ5/Otto - 2026 - Bodies in Relation. Theater Photography and the Distant Viewing of Performance.pdf:application/pdf},
}

@article{nantke_quantitative_2026,
	title = {Quantitative {Analyse} visueller {Charakteristika} von {Briefen}},
	volume = {11},
	issn = {2510-1358},
	url = {https://zfdg.de/2026_011},
	doi = {10.17175/2026_011},
	abstract = {The analysis of visual and material characteristics of digital representations of historical documents still plays a minor role in computer-assisted methods. Most quantitative methods and the tools used in this context focus on the content and / or writing style of literary and historical texts; bibliographic codes are generally disregarded in analysis and interpretation beyond their representation as digitized images in digital scholarly editions. This paper presents an approach to the quantitative, algorithm-based analysis of visual-material characteristics in a corpus of letters from the period ›Germany around 1900‹ and demonstrates how various automatically determinable values regarding the visually perceptible spatial layout of the letters can be used to derive insights into letter-writing practices.},
	language = {de},
	urldate = {2026-09-04},
	journal = {Zeitschrift für digitale Geisteswissenschaften},
	publisher = {Forschungsverbund Marbach Weimar Wolfenbüttel / Digital Humanities im deutschsprachigen Raum e. V.},
	author = {Nantke, Julia and Leitgeb, Johannes and Reul, Christian},
	year = {2026},
	note = {Version Number: 1.0},
	keywords = {Optische Zeichenerkennung, Automatische Klassifikation, Brief, Konzeptionelle Modellierung},
}