Browsing by Subject "Handwriting"

Now showing 1 - 2 of 2

Handwriting transcription using word spotting with humans in the loop
(2018-06-19) Dang, Brandon Uyvu; Karadkar, Unmil
Handwritten materials are increasingly being digitized and made available for scholarly analysis and research. To this end, numerous specialized software tools have been developed to support the crowdsourced transcription of such texts. However, as many of these tools operate at the page-level, they are unsuitable for documents containing privacy-sensitive data such as medical records, as displaying an entire page at a time risks the potential of disclosing such information to unintended parties. Additionally, manual transcription efforts can be slow and expensive. Automated optical character recognition (OCR) methods perform poorly on handwritten text due to factors such as the large variability in human handwriting, degradation of paper documents, and artifacts of scanning. Thus, handwritten text recognition and analysis remain active areas of research. With the renewed interest in neural networks, recent methods using deep learning have achieved unprecedented state-of-the-art results on benchmark datasets in areas including word recognition, word spotting, and character recognition. Despite this, current methods are not yet robust enough to fully automate handwriting transcription tasks alone. In this work, we report a novel approach that combines the efficiency of machine learning with the accuracy of human intelligence in order to semi-automatically transcribe a challenging real-world dataset of word images segmented from historical handwritten medical records as part of the Central State Hospital Digital (CSH) Library and Archives project. Specifically, we leverage a deep convolutional network to generate feature sets, identify groups of similar images using unsupervised hierarchical density-based clustering, and develop a system to obtain cluster transcriptions from human workers on an online crowdsourcing platform. In doing so, we aim to reduce the number of images to be sent to the crowd, thereby optimizing monetary and time costs while maintaining an acceptable level of accuracy as well as preserving the privacy of the data.
Scripted behavior : Michelangelo's evolving calligraphy and artistic self-representation
(2017-05-04) Hooker, Katie Alexandra; Waldman, Louis Alexander; Johns, Ann
In the age of digitization, archivists, scholars, and art historians have questioned the role of documents once they have been transcribed, published, and stored away in digital repositories. If the information is recorded and saved, how else can a manuscript speak to the art historian? Archival materials such as personal correspondence and manuscripts are traditionally divorced from an individual’s larger corpus of artistic output. The texts themselves are mined solely for information that can inform a work of art, and are typically not regarded for their own formal qualities. This thesis challenges such a practice, asserting that personal letters, particularly those of Michelangelo Buonarroti and his contemporaries, should be approached as artistic artifacts whose formal qualities alone offer a wealth of information regarding the artist and his social context. Focusing on the social implications of Michelangelo’s shift from using the mercantesca script to the cancelleresca script used by humanists and papal dignitaries, this paper proposes that developments in Michelangelo’s writing style mirror other efforts the artist made to construct a distinct identity. Ultimately, this thesis argues that by the dawn of the Cinquecento, script was an integral aspect of personal identity creation and professional reception for a Renaissance artist.