OOIR: Observatory of International Research

Papers

(The TQCC of International Journal on Document Analysis and Recognition is 5. The table below lists those papers that are above that threshold based on CrossRef citation counts [max. 250 papers]. The publications cover those that have been published in the past four years, i.e., from 2020-04-01 to 2024-04-01.)

Article	Citations
Translating math formula images to LaTeX sequences using deep neural networks with sequence-level training	34
Optical character recognition with neural networks and post-correction with finite state methods	28
Persian handwritten digit, character and word recognition using deep learning	18
Robust text line detection in historical documents: learning and evaluation methods	17
Arrow R-CNN for handwritten diagram recognition	16
Beyond document object detection: instance-level segmentation of complex layouts	15
A survey of historical document image datasets	13
Data Augmentation using Geometric, Frequency, and Beta Modeling approaches for Improving Multi-lingual Online Handwriting Recognition	13
Segmentation for document layout analysis: not dead yet	11
Text recognition for Vietnamese identity card based on deep features network	11
Automatic room information retrieval and classification from floor plan using linear regression model	11
Boosting modern and historical handwritten text recognition with deformable convolutions	8
Feature learning and encoding for multi-script writer identification	8
Self-supervised deep metric learning for ancient papyrus fragments retrieval	8
CNN-based segmentation of speech balloons and narrative text boxes from comic book page images	8
DetectGAN: GAN-based text detector for camera-captured document images	8
A two-step framework for text line segmentation in historical Arabic and Latin document images	8
Revealing a history: palimpsest text separation with generative networks	7
YOLO-table: disclosure document table detection with involution	7
Asking questions on handwritten document collections	7
An end-to-end network for irregular printed Mongolian recognition	7
EAML: ensemble self-attention-based mutual learning network for document image classification	6
Conv-transformer architecture for unconstrained off-line Urdu handwriting recognition	6
Knowledge-driven description synthesis for floor plan interpretation	6
Segmentation of text lines using multi-scale CNN from warped printed and handwritten document images	6

Benchmarking online sequence-to-sequence and character-based handwriting recognition from IMU-enhanced pens	6
Combination of deep neural networks and logical rules for record segmentation in historical handwritten registers using few examples	6
WriterINet: a multi-path deep CNN for offline text-independent writer identification	5
A robust watermarking approach for security issue of binary documents using fully convolutional networks	5
TableSegNet: a fully convolutional network for table detection and segmentation in document images	5
MRZ code extraction from visa and passport documents using convolutional neural networks	5
Extracting text from scanned Arabic books: a large-scale benchmark dataset and a fine-tuned Faster-R-CNN model	5
SKFont: skeleton-driven Korean font generator with conditional deep adversarial networks	5