Results 41 to 50 of about 682 (182)

Two-Step CNN Framework for Text Line Recognition in Camera-Captured Images

IEEE Access, 2020
In this paper, we introduce an “on the device” text line recognition framework that is designed for mobile or embedded systems. We consider per-character segmentation as a language-independent problem and individual character recognition as
Yulia S. Chernyshova, Alexander V. Sheshkus, Vladimir V. Arlazarov   +2 more
doaj   +1 more source

Funding, Facilities, and the Face of Homelessness: Heterogeneous Impacts of Federal Grants on Sheltered and Unsheltered Counts

Southern Economic Journal, EarlyView.
ABSTRACT This paper examines the causal impact of federal homeless‐assistance grants on reported homelessness and shelter capacity across 370 Continuums of Care in 2019. We exploit cross‐sectional variation in pre‐1940 housing shares, used in Community Development Block Grant formula allocations, as an instrument for combined CoC and Emergency ...
Luke Maddock, Anita Alves Pena
wiley   +1 more source

Mending Fractured Texts

Digital Humanities in the Nordic and Baltic Countries Publications, 2022
In this paper we present an OCR correction pipeline for 19th century printed Danish fraktur (gothic/blackletter). The work has been carried out at the University of Copenhagen in relation to a research project involving digital explorations of a corpus
Jens Bjerring-Hansen, Ross Deans Kristensen-McLachlan, Philip Diderichsen, Dorte Haltrup Hansen   +3 more
doaj   +1 more source

Dual‐Branch Attention Fusion for Multimodal Sanskrit Script Classification

Engineering Reports, Volume 8, Issue 6, June 2026.
The proposed system adopts a dual‐branch architecture in which a transformer‐based visual module extracts hierarchical structural features from manuscript images, while a textual module captures linguistic representations derived from recognized script content.
Basaraboyina Yohoshiva, Nagendra Panini Challa   +1 more
wiley   +1 more source

A Comprehensive Study of Bengali Language Tools and Applications for Artificial Intelligence Research

Engineering Reports, Volume 8, Issue 6, June 2026.
This study presents a comprehensive analysis of Bengali AI resources, including NLP tools, machine translation systems, speech technologies, and benchmarking datasets. The findings highlight fragmented development across tasks and emphasize the need for integrated resources, unified benchmarks, and multimodal datasets to build a scalable and robust ...
Fairooz Maliha, Supprio Ghosh Nil, Saymadeen Tabassum, Md. Ataur Rahman, Arifa Rahman, Md. Tarek Habib   +5 more
wiley   +1 more source

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

Key Frame Extraction for Text Based Video Retrieval Using Maximally Stable Extremal Regions

EAI Endorsed Transactions on e-Learning, 2015
This paper presents a new approach for text-based video content retrieval system. The proposed scheme consists of three main processes that are key frame extraction, text localization and keyword matching.
Werachard Wattanarachothai, Karn Patanukhom   +1 more
doaj   +1 more source

High‐throughput information extraction of printed specimen labels from large‐scale digitization of entomological collections using a semi‐automated pipeline

Methods in Ecology and Evolution, Volume 17, Issue 3, Page 790-804, March 2026.
Abstract Natural history museums curate billions of insect specimens, representing an unparalleled record of biodiversity. Although large‐scale digitization has expanded access to specimen images, extracting label metadata remains a major bottleneck, typically requiring time‐intensive manual transcription.
Margot Belot, Joël Tuberosa, Leonardo Preuss, Olha Svezhentseva, Magdalena Claessen, Christian Bölling, Franziska Schuster, Théo Léger   +7 more
wiley   +1 more source

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

Vision-based patient identification recognition based on image content analysis and support vector machine for medical information system

EURASIP Journal on Advances in Signal Processing, 2020
In this paper, a vision-based patient identification recognition system based on image content analysis and support vector machine is proposed for medical information system, especially in dermatology. This proposed system is composed of three parts: pre-
Guo-Shiang Lin, Sin-Kuo Chai, Hsiang-Min Li, Jen-Yung Lin   +3 more
doaj   +1 more source