Ctrl K

.css-1e132ge{font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,'Helvetica Neue',Arial,sans-serif,'Apple Color Emoji','Segoe UI Emoji','Segoe UI Symbol';font-weight:400;font-size:0.875rem;line-height:1.43;background-color:transparent;display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;padding:6px 16px;color:rgb(96, 54, 20);background-color:rgb(253, 243, 234);width:100vw;-webkit-box-pack:center;-ms-flex-pack:center;-webkit-justify-content:center;justify-content:center;margin-top:1rem;z-index:9;}.css-1e132ge .MuiAlert-icon{color:#ed6c02;}.css-1pl9tfm{background-color:#fff;color:rgba(34,36,37,1);-webkit-transition:box-shadow 300ms cubic-bezier(0.4, 0, 0.2, 1) 0ms;transition:box-shadow 300ms cubic-bezier(0.4, 0, 0.2, 1) 0ms;border-radius:2px;box-shadow:var(--Paper-shadow);background-image:var(--Paper-overlay);overflow:auto;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,'Helvetica Neue',Arial,sans-serif,'Apple Color Emoji','Segoe UI Emoji','Segoe UI Symbol';font-weight:400;font-size:0.875rem;line-height:1.43;background-color:transparent;display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;padding:6px 16px;color:rgb(96, 54, 20);background-color:rgb(253, 243, 234);width:100vw;-webkit-box-pack:center;-ms-flex-pack:center;-webkit-justify-content:center;justify-content:center;margin-top:1rem;z-index:9;}.css-1pl9tfm .MuiAlert-icon{color:#ed6c02;}

Limited functionality: Your browser does not support JavaScript.

kraken

kraken is an open-source, turn-key automatic text recognition (ATR) system optimized for historical and non-Latin script writing. Designed as a universal text recognizer for the humanities, it directly addresses the unique challenges of digitizing historical documents.

contributor

Get started

2258 commitsLast commit ≈ 6 days ago1064 stars174 forks

Description

Kraken is a turn-key OCR system optimized for historical and non-Latin script material.

Kraken's main features are:

Fully trainable layout analysis and character recognition
Right-to-Left, BiDi, and Top-to-Bottom script support
ALTO, PageXML, abbyyXML, and hOCR output
Word bounding boxes and character cuts
Multi-script recognition support
Public repository of model files
Variable recognition network architecture

Keywords

alto xml

Alto-XML

Handwritten Text Recognition

Optical Character Recognition

page xml

Page-XML

Programming language

Python 100%

License

Apache-2.0

</>Source code

Contributors

Benjamin Kiessling

Related software

eScriptorium

eScriptorium is a program used for the automatic or manuell segmentation of printed or handwritten historic documents. It is OpenSource and not a web-application.

Updated 17 months ago

This local instance of Research Software Directory (RSD) is only used to register tools and software in the scientific field of digital scholarly editions. You can access the main instance of RSD at https://research-software-directory.org/.