Results 11 to 20 of about 34,020 (164)
An Efficient Unsupervised Approach for OCR Error Correction of Vietnamese OCR Text
IEEE Access, 2023 Different types of OCR errors often occur in OCR texts due to the low quality of scanned document images or limitations in OCR software. In this paper, we propose a novel unsupervised approach for OCR error correction. Correction candidates for OCR errors are generated and explored in their neighborhoods using correction character edits controlled by ...
Pavel Krömer +2 more
exaly +4 more sources
OCR17: Ground Truth and Models for 17th c. French Prints (and hopefully more) [PDF]
Journal of Data Mining and Digital Humanities, 2023 Machine learning begins with machine teaching: in the following paper, we present the data that we have prepared to kick-start the training of reliable OCR models for 17th century prints written in French. The construction of a representative corpus is a
Simon Gabay +2 more
doaj +1 more source
Distinctive features of recognition for documents printed in the Romanian transitional alphabets [PDF]
Computer Science Journal of Moldova, 2023 In this paper, we summarize the research of digitization of documents printed by Romanian transitional alphabet. These printings are the most original Romanian historical documents, which makes our experience useful when researching OCR methods for ...
Tudor Bumbu +4 more
doaj +1 more source
Big Data and Cognitive Computing, 2021 The accessibility and reuse of legal data is paramount for promoting transparency, accountability and, ultimately, trust towards governance institutions.
Sotiris Leventis +2 more
doaj +1 more source
SCRIPT IDENTIFICATION FROM CAMERA CAPTURED INDIAN DOCUMENT IMAGES WITH CNN MODEL [PDF]
ICTACT Journal on Soft Computing, 2023 Compared to typical scanners, handheld cameras offer convenient, flexible, portable, and noncontact image capture, which enables many new applications and breathes new life into existing ones, but camera-captured documents may suffer from distortions ...
Satishkumar Mallappa +2 more
doaj +1 more source
Extent of optico-carotid recess is significantly associated with presence of bony dehiscences and bone thickness in the optico-carotid area [PDF]
Rhinology Online, 2021 Background: The objectives of this study were to evaluate the frequency of bony dehiscences in the optico-carotid recess (OCR) area and to measure the thickness of the bony lamellas bordering the OCR, according to our previously proposed OCR ...
A. Andrianakis +8 more
doaj +1 more source
, 2022 A novel scene text recognizer based on Vision-Language Transformer (VLT) is presented. Inspired by Levenshtein Transformer in the area of NLP, the proposed method (named Levenshtein OCR, and LevOCR for short) explores an alternative way for automatically transcribing textual content from cropped natural images.
Cheng Da, Peng Wang 0103, Cong Yao
openaire +2 more sources
Кібернетика та комп'ютерні технології, 2021 Introduction. The implementation of information technologies in various spheres of public life dictates the creation of efficient and productive systems for entering information into computer systems. In such systems it is important to build an effective
Elshan Mustafayev, Rustam Azimov
doaj +1 more source
Visión Electrónica, 2021 En un mundo cada vez más conectado con la tecnología y con la creciente necesidad de seguridad en todos los aspectos de la vida, surge este proyecto donde se abordará el problema de seguridad en los establecimientos educativos, pero que puede ser ...
Fanny Suárez-Mosquera +2 more
doaj +1 more source
IMAGE BACKGROUND PROCESSING FOR COMPARING ACCURACY VALUES OF OCR PERFORMANCE
Pilar Nusa Mandiri, 2020 Optical Character Recognition (OCR) is an application used to process digital text images into text. Many documents that have a background in the form of images in the visual context of the background image increase the security of documents that state ...
Desiana Nur Kholifah +2 more
doaj +1 more source