Results 71 to 80 of about 34,020 (164)

Enhancing OCR Accuracy on Indonesian ID Cards Using Dual-Pipeline Tesseract and Post-Processing

Journal of Electrical Engineering and Computer Sciences
Manual transcription of data from Indonesian identity cards (KTP) remains prevalent in public institutions, often resulting in inefficiencies and human errors that compromise data accuracy.
Rendy Dwi Reksiyano, Syafrial Fachri Pane, Rolly Maulana Awangga   +2 more
doaj   +1 more source

OCR-Quality: A Human-Annotated Dataset for OCR Quality Assessment

CoRR
We present OCR-Quality, a comprehensive human-annotated dataset designed for evaluating and developing OCR quality assessment methods. The dataset consists of 1,000 PDF pages converted to PNG images at 300 DPI, sampled from diverse real-world scenarios, including academic papers, textbooks, e-books, and multilingual documents.
openaire   +2 more sources

Computer vision for Pokémon Battles: A YOLO and Tesseract-Based System for Automated Recognition and Gameplay Analysis

Interfases
Pokémon Double Battles present a complex decision-making environment that has traditionally relied on manual data analysis. This paper introduces an automated system leveraging computer vision and deep learning to extract structured gameplay data from ...
Miguel R. Lladó, Terence Morley
doaj   +1 more source

Modernism’s Vector: Dataset for a Chinese-Language Journal in Late 1950s Malaya

Journal of Open Humanities Data
This paper discusses the creation and reuse potential of the dataset of .txt files of Chao Foon (Jiaofeng), a Chinese-language literary journal that was founded in November 1955 in colonial Malaya.
Nicholas Y. H. Wong
doaj   +1 more source

BHL and OCR

, 2010
Some quick notes on OCR. Revisiting my DjVu viewer experiments it really struck me how "dirty" the OCR text is. It's readable, but if we were to display the OCR text rather than the images, it would be a little offputting.
openaire   +2 more sources

UNSTRUCTURED DATA EXTRACTION AND INTELLIGENT DOCUMENT PROCESSING

Измерение, мониторинг, управление, контроль
Background. This paper examines modern approaches to data structuring and information enrichment in the context of digitalization. Approaches to solving the problem of automated data extraction are proposed using the example of tool manufacturers ...
Vitaly R. Aleksandrov, Aleksey A. Shchetkin, Aleksandr S. Bevz, Sergei A. Vyaznikov, Olga S. Kolesnikova   +4 more
doaj   +1 more source

Extracellular flux analyses indicate low ATP yield and require refinement for accurate determination of maximal oxygen consumption rate. [PDF]

Sci Rep
Ransy C, Boissan M, Hammad N, Bouaboud A, Issad T, De Dieuleveult M, Miotto B, Ye M, Pasmant E, Bouillaud F.   +9 more
europepmc   +1 more source

Short-term effects of ocrelizumab on cortical pathology in patients with multiple sclerosis. [PDF]

Neurotherapeutics
Cavalli N, Boffa G, Cipriano E, Boccia VD, Al Qudsi S, Baldisseri F, Leveraro E, Nasone L, Magon S, Cellerino M, Inglese M, Lapucci C.   +11 more
europepmc   +1 more source

Patient-derived glioblastoma cultures preserve respiration phenotypes during ex vivo maintenance and show sex-associated differences in migration. [PDF]

Acta Neuropathol Commun
Matschke V, Glover P, Lucaciu R, Pickmann D, Scholz M, Theiss C, Hoffmann D, Matschke J.   +7 more
europepmc   +1 more source

Real-world comparison of anti-CD20 therapies: efficacy, infections, and immune profiles in a German cohort. [PDF]

Front Immunol
Stögbauer J, Bewarder M, Groß L, Thurner L, Fassbender K, Urschel R, Høgestøl EA, Nygaard GO, Harbo HF, Stüve O, Pawlitzki M, Meuth SG, Sester M, Groppa S, Fousse M.   +14 more
europepmc   +1 more source