The IAM-database: an English sentence database for offline handwriting recognition

By Urs-Viktor Marti, Horst Bunke. 2002

1,523 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Media Technology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Media Technology

Citations in the corpus

A Convergence Analysis of Log-Linear Training (2011, methodology): “Our second task is the IAM handwriting database [15].”
Handwriting Transformers (2021, methodology): “We perform extensive experiments on IAM handwriting dataset [19].”
Dropout Improves Recurrent Neural Networks for Handwriting Recognition (2013, methodology): “For IAM, we applied a 3 -gram language model trained on the LOB, Brown and Wellington corpora.”
Cross-entropy vs. squared error training: a theoretical and experimental comparison (2013, methodology): “For the HWR task the IAM database [9] was used, which consists of handwritten English sentences built upon the LOB corpus [10].”
Long-short term memory neural networks language modeling for handwriting recognition (2012, methodology): “The experiments are done on the IAM off-line database of modern English handwritten data [10].”
What matters when building vision-language models? (2024, neutral): “General visual question answering VQAv2 (Goyal et al., 2017) 82,772 443,757 1,595,929 5.72% COCO-QA (Ren et al., 2015) 46,287 78,736 286,982 1.47% Visual7W (Zhu et al., 2016) 14,366 69,817 279,268 1.43% A-OKVQA (Schwenk et al., 2022) 16,539 17,056 236,492 1.21% TallyQA (Acharya et al., 2019) 98,680 ”
Vectorization and Rasterization: Self-Supervised Learning for Sketch and Handwriting (2021, methodology): “We apply our self-supervised learning method on both sketch [22, 17] and handwriting data [40], as both can be represented in image and vector space.”
A Novel Connectionist System for Unconstrained Handwriting Recognition (2009, methodology): “For the offline experiments, we used the IAM-DB, a database acquired from scanned images of handwritten forms [36].”
Handwritten Optical Character Recognition (OCR): A Comprehensive Systematic Literature Review (SLR) (2020, methodology): “The IAM [118] is handwritten database of English language based on Lancaster-Oslo/Bergen (LOB) corpus.”
Differentiable Weighted Finite-State Transducers (2020, methodology): “Ofﬂine Handwriting Recognition To facilitate comparisons to prior academic studies, we test our approach on handwritten line recognition using the IAM database (Marti & Bunke, 2002).”
Bidirectional Language Model for Handwriting Recognition (2012, methodology): “For the experiments, we have used the IAM off-line database [11], which contains forms of unconstrained handwritten English text.”
CASIA Online and Offline Chinese Handwriting Databases (2011, methodology): “Among the offline sample datasets are the CENPARMI digits, CEDAR English words and characters [1], NIST handprinted forms and characters database [2], IAM English sentence database [3], Japanese Kanji character databases ETL8B and ETL9B, Indian database of ISI [4], Arabic databases [5], Farsi databa”
Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling (2024, neutral): “…zh) [253], ST-VQA (en) [17], EATEN (zh) [78], LLaVAR (en) [305], CASIA (zh) [146], Chinese-OCR (zh) [14], CyrillicHandwriting (ru) [239], IAM (en) [180], NAF (en) [52], POIE (en) [115], ReCTs (zh) [301], MTWI (zh) [82], TextOCR (en) [213], SROIE (en) [97], Synthetic Arxiv OCR (en), ) [227],…”