Papers with Code 아카이브

Optical Character Recognition (OCR)

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

하위 태스크: 10
평가표: 6
보존된 평가 기록: 20

Optical Character Recognition or Optical Character Reader (OCR) is the electronic or mechanical conversion of images of typed, handwritten or printed text into machine-encoded text, whether from a scanned document, a photo of a document, a scene-photo (for example the text on signs and billboards in a landscape photo, license plates in cars...) or from subtitle text superimposed on an image (for example: from a television broadcast)

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/GokulKarthik/EAST.pytorch

EAST: An Efficient and Accurate Scene Text Detector

https://github.com/Guillem96/deep-erase

DeepErase: Weakly Supervised Ink Artifact Removal in Document Text Images

https://github.com/HTR-United/cremma-medieval

Stylometry for Noisy Medieval Data: Evaluating Paul Meyer's Hagiographic Hypothesis

https://github.com/HassamChundrigar/Urdu-Ocr

An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition

https://github.com/HawkAaron/warp-transducer

Speech Recognition with Deep Recurrent Neural Networks

https://github.com/Hedgehogues/HoChiMinh

Single Classifier-based Passive System for Source Printer Classification using Local Texture Features

https://github.com/HoganZhang/few-shot-gnn

Few-Shot Learning with Graph Neural Networks

https://github.com/Holmeyoung/crnn-pytorch

An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition

https://github.com/HuakunShen/Super-Resolution

DDI-100: Dataset for Text Detection and Recognition

https://github.com/IVRL/w2s

Fully Unsupervised Diversity Denoising with Convolutional Variational Autoencoders

https://github.com/IirisSundin/active-learning-for-decision-making

Active Learning for Decision-Making from Imbalanced Observational Data

https://github.com/JTCodeStore/TextIimagesToolkit

A Hybrid Deep Learning Model for Arabic Text Recognition

https://github.com/JaidedAI/EasyOCR

An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition

https://github.com/JasonZK/Soccer_OCR

PP-OCR: A Practical Ultra Lightweight OCR System

https://github.com/JiaquanYe/TableMASTER-mmocr

Image-based table recognition: data, model, and evaluation

https://github.com/JohanPhan/Dual_active_sampling_Active_learning

Dual Active Sampling on Batch-Incremental Active Learning

https://github.com/JonnoB/reading_the_unreadable

Reading the unreadable: Creating a dataset of 19th century English newspapers using image-to-text language models

https://github.com/Kaushal28/FOTS-PyTorch

EAST: An Efficient and Accurate Scene Text Detector

https://github.com/Kaushalya/metal

MetAL: Active Semi-Supervised Learning on Graphs via Meta Learning

https://github.com/KumudaBG/Short-Story-Deep-Active-Learning

A Survey of Deep Active Learning

https://github.com/KyotoSunshine/CNN-for-handwritten-kanji

Deep Big Simple Neural Nets Excel on Handwritten Digit Recognition

https://github.com/L706077/OCR-CRNN

An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition

https://github.com/LONG-9621/IQA_02

Exploiting Unlabeled Data in CNNs by Self-supervised Learning to Rank

https://github.com/Lieberk/Paddle-FSL-GNN

Few-Shot Learning with Graph Neural Networks

https://github.com/LinXueyuanStdio/LaTeX_OCR_PRO

Image-to-Markup Generation with Coarse-to-Fine Attention

https://github.com/Line290/EDD-third-party

Image-based table recognition: data, model, and evaluation

https://github.com/LinearPi/OCR_Chinese

COCO-Text: Dataset and Benchmark for Text Detection and Recognition in Natural Images

https://github.com/Liumihan/CRNN_kreas

An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition

https://github.com/Liumihan/CRNN_pytorch

An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition

https://github.com/LukasErlenbach/active_learning_bnn

Deeper Connections between Neural Networks and Gaussian Processes Speed-up Active Learning

https://github.com/LuxxxLucy/Active-Decision-Set-Induction

An Active Approach for Model Interpretation

https://github.com/MMMU-Benchmark/MMMU

MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark

https://github.com/MS-Mind/MS-Code-06/tree/main/psenet

Shape Robust Text Detection with Progressive Scale Expansion Network

https://github.com/MS-P3/code4/tree/main/wukong

Wukong-Reader: Multi-modal Pre-training for Fine-grained Visual Document Understanding

https://github.com/Mael-zys/PSENet

Shape Robust Text Detection with Progressive Scale Expansion Network

https://github.com/MaybeShewill-CV/CRNN_Tensorflow

An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.