Optical Character Recognition

114 papers with code • 1 benchmarks • 23 datasets

This task has no description! Would you like to contribute one?

Greatest papers with code

Attention-based Extraction of Structured Information from Street View Imagery

tensorflow/models 11 Apr 2017

We present a neural network model - based on CNNs, RNNs and a novel attention mechanism - which achieves 84. 2% accuracy on the challenging French Street Name Signs (FSNS) dataset, significantly outperforming the previous state of the art (Smith'16), which achieved 72. 46%.

Optical Character Recognition

Adapting the Tesseract Open Source OCR Engine for Multilingual OCR

tesseract-ocr/tesseract ACM 2009

We describe efforts to adapt the Tesseract open source OCR engine for multiple scripts and languages.

Optical Character Recognition

PP-OCR: A Practical Ultra Lightweight OCR System

PaddlePaddle/PaddleOCR 21 Sep 2020

Meanwhile, several pre-trained models for the Chinese and English recognition are released, including a text detector (97K images are used), a direction classifier (600K images are used) as well as a text recognizer (17. 9M images are used).

Optical Character Recognition

Learning Transferable Visual Models From Natural Language Supervision

openai/CLIP 26 Feb 2021

State-of-the-art computer vision systems are trained to predict a fixed set of predetermined object categories.

Action Recognition Action Recognition In Videos +4

Chinese Text in the Wild

xiaofengShi/CHINESE-OCR 28 Feb 2018

[python3. 6] 运用tf实现自然场景文字检测, keras/pytorch实现ctpn+crnn+ctc实现不定长场景文字OCR识别

Optical Character Recognition

End-to-End Interpretation of the French Street Name Signs Dataset

xiaofengShi/CHINESE-OCR 13 Feb 2017

We introduce the French Street Name Signs (FSNS) Dataset consisting of more than a million images of street name signs cropped from Google Street View images of France.

Optical Character Recognition

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

xiaofengShi/CHINESE-OCR 26 Jan 2016

The goal of COCO-Text is to advance state-of-the-art in text detection and recognition in natural images.

General Classification Object Recognition +4

Segmentation Transformer: Object-Contextual Representations for Semantic Segmentation

HRNet/HRNet-Semantic-Segmentation ECCV 2020

We empirically demonstrate that the proposed approach achieves competitive performance on various challenging semantic segmentation benchmarks: Cityscapes, ADE20K, LIP, PASCAL-Context, and COCO-Stuff.

Optical Character Recognition Semantic Segmentation

License Plate Detection and Recognition in Unconstrained Scenarios

sergiomsilva/alpr-unconstrained ECCV 2018

Despite the large number of both commercial and academic methods for Automatic License Plate Recognition (ALPR), most existing approaches are focused on a specific license plate (LP) region (e. g. European, US, Brazilian, Taiwanese, etc.

License Plate Detection License Plate Recognition +1

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

da03/Attention-OCR ICML 2017

We present a neural encoder-decoder model to convert images into presentational markup based on a scalable coarse-to-fine attention mechanism.

Optical Character Recognition