Sökning: "handwritten documents"

Visar resultat 1 - 5 av 21 uppsatser innehållade orden handwritten documents.

  1. 1. Semi-automatic Segmentation & Alignment of Handwritten Historical Text Images with the use of Bayesian Optimisation

    Uppsats för yrkesexamina på avancerad nivå, Uppsala universitet/Avdelningen Vi3

    Författare :Philip MacCormack; [2023]
    Nyckelord :handwritten text recognition; machine learning; bayesian optimisation; image analysis; segmentation; alignment;

    Sammanfattning : To effortlessly digitise historical documents has risen to be of great interest for some time. Part of the digitisation is what is called annotating of the data. Such data annotations are obtained in a process called alignment which links words in an image to the transcript. LÄS MER

  3. 2. HTR in the making : En studie av hur Handwritten Text Recognition görs vid tre svenska arkivverksamheter

    Master-uppsats, Lunds universitet/Avdelningen för ABM, digitala kulturer samt förlags- och bokmarknadskunskap

    Författare :Camilla Schön; [2023]
    Nyckelord :Archival science; Handwritten Text Recognition; Actor-Network Theory; artificial intelligence; The Swedish National Archives; Swedish National Heritage Board; Uppsala University Library; Cultural Sciences;

    Sammanfattning : In the current archival science paradigm, archives implement AI-technologies to provide content as structured, machine-readable data. One of these technologies is Handwritten Text recognition (HTR) which can transcribe handwritten text. Thus, HTR turn raw digitized archival documents into machine-readable format. LÄS MER

  4. 3. A Comparison of Advanced DeepLearning Algorithms for Multi-digit Detection in Historical Documents

    Master-uppsats, Blekinge Tekniska Högskola/Institutionen för datavetenskap

    Författare :Manaswini Chethireddy; Sai Teja Palla; [2023]
    Nyckelord :Deep Learning Methods; Handwritten digits; Digit Detection; Image processing on document images; YOLOV5; Faster R-CNN; RetinaNet; YOLOV7;

    Sammanfattning : Background: Historical handwritten documents are assets for future generations and should be appropriately secured, so handwritten digit detection plays an important role to preserve them. Handwritten digit detection is a fundamental problem and has been studied extensively for many years. LÄS MER

  5. 4. Matching Sticky Notes Using Latent Representations

    Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Författare :Javier García San Vicent; [2022]
    Nyckelord :Pattern matching; Image matching; Image recognition; Representation learning; Unsupervised learning; Semisupervised learning; Siamese architecture; Deep learning; Transfer learning; Mönstermatchning; Bildmatchning; Bildigenkänning; Representationsinlärning; Oövervakat lärande; Halvövervakat lärande; Siamesisk arkitektur; Djup lärning; Överfört lärande;

    Sammanfattning : his project addresses the issue of accurately identifying repeated images of sticky notes. Due to environmental conditions and the 3D location of the camera, different pictures taken of sticky notes may look distinct enough to be hard to determine if they belong to the same note. LÄS MER

  7. 5. Lost in Transcription : Evaluating Clustering and Few-Shot learningfor transcription of historical ciphers

    Master-uppsats, Uppsala universitet/Institutionen för lingvistik och filologi

    Författare :Giacomo Magnifico; [2021]
    Nyckelord :Image Recognition; Handwritten Text Recognition; HTR; Deep-learning; K-mean clustering; NN; Neural Network; Few-Shot;

    Sammanfattning : Where there has been a steady development of Optical Character Recognition (OCR) techniques for printed documents, the instruments that provide good quality for hand-written manuscripts by Hand-written Text Recognition  methods (HTR) and transcriptions are still some steps behind. With the main focus on historical ciphers (i.e. LÄS MER