---
# System prepended metadata

title: Implementation Project OCR-D / Kitodo
tags: [OCR-D, ' OCR', ' Kitodo']

---

---
title: Implementation Project OCR-D / Kitodo
tags: OCR-D, OCR, Kitodo
description: 1st OCR-D developer workshop, 29 Nov 2021
slideOptions:
  theme: white
  slideNumber: true
---

<style>
/* reduce from default 48px: */
.reveal {
  font-size: 24px;
  text-align: left;
}
.reveal .slides {
  text-align: left;
}
/* change from default gray-on-black: */
.hljs {
  color: #005;
  background: #fff;
}
/* prevent invisible fragments from occupying space: */
.fragment.visible:not(.current-fragment) {
    display: none;
    height:0px;
    line-height: 0px;
    font-size: 0px;
}
/* increase font size in diagrams: */
.label {
    font-size: 24px;
    font-weight: bold;
}
/* increase maximum width of code blocks: */
.reveal pre code {
    max-width: 1000px;
    max-height: 1000px;
}
/* remove black border from images: */
.reveal section img {
    border: 0;
}
.reveal pre.mermaid {
    width: 100% !important;
}

.reveal svg {
    max-height: 600px;
}

.reveal .scaled-flowchart-td pre.mermaid {
    width: 100% !important;
    /* why? float: left; */
}

.reveal .scaled-flowchart-td svg {
    max-width: 100% !important;
}

.reveal .scaled-flowchart-td svg g.node,
.reveal .scaled-flowchart-td svg g.label,
.reveal .scaled-flowchart-td svg foreignObject {
    width: 100% !important;
}

.reveal .scaled-flowchart-td p {
    clear:both;
}


.reveal .centered {
    text-align: center
}
.reveal .width75 {
    max-width: 75%;
}
/* remove black border from images: */
.reveal section img {
    border: 0;
    box-shadow: none;
}


</style>

# Implementation Project<br>OCR‑D / Kitodo

## Erik Sommer        &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;![slub-logo](https://www.slub-dresden.de/typo3conf/ext/slub_template/Resources/Public/Images/slublogo.svg =200x)
## Robert Sachunsky  &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;![slub-logo](https://www.slub-dresden.de/typo3conf/ext/slub_template/Resources/Public/Images/slublogo.svg =200x)
## Katya Rykhlinskaya &nbsp;&nbsp;![tub-logo](https://www.tu-braunschweig.de/typo3conf/ext/tu_braunschweig/Resources/Public/Images/Logos/tu_braunschweig_logo.svg)


_1st OCR-D<sup>III</sup> developer workshop, 29 Nov 2021_

: https://hackmd.io/@bertsky/ocrd-workshop1-kitodo

---

1. Status and Planning
2. Development
3. Kitodo User Survey

---

## 0 Quick Recap

→ We want to bring OCR-D into mass digitization.

- Project goals:
  - scalabe and robust OCR-D Web Service
  - improved Quality Metrics
  - integration with Kitodo (   .Production    /   .Presentation )
      - aligned to the requirements of the Community

---

## 1 Status

- Commenced 01 Oct, staged entry of core team members:
  1. Katya Rykhlinskaya (Community Outreach): Oct 2021
  2. Robert Sachunsky (DEV OCR-D): Nov 2021
  3. Sven Marcus (DEV Web Service): ~Dec 2021
  4. Markus Weigelt (DEV Kitodo.Production): ~Jan 2022
  5. H. Sidiropoulos (DEV Kitodo.Presentation): ~mid Jan 2022

---

## 1 Planning

- First Phase – independent Tiers:
  - Assess User Requirements
  - Network Implementation (coordinated)
  - Scaling + robustness (coordinated)
  - Quality/Error interfaces, Quality Metrics
  - Fill technological gaps (GT, OLR, Backlog, New Wrappers)
- Second Phase – additional, dependent tiers:
  - UI for Control and Visualization
  - Kitodo.Production Module
  - Kitodo.Presentation Interfaces
  - Experiments on Workflow Optimization

---

## 2 Development

- core issues/pulls
  - [repairing typical PAGE defects](https://github.com/OCR-D/core/issues/740)
  - [bashlib in/output-file-grp checking](https://github.com/OCR-D/core/pull/743)
  - [`//mets:agent/mets:note` for workflow provenance](https://github.com/OCR-D/core/pull/747)
  - [`ocrd workspace find --download --wait`](https://github.com/OCR-D/core/pull/747)
- [ocrd-segment-evaluate](https://github.com/OCR-D/ocrd_segment/blob/master/ocrd_segment/evaluate.py) :construction_worker: 
- [ocrd_doxa](https://github.com/bertsky/ocrd_doxa) binarization :construction_worker: 
- [ocrd_origami](https://github.com/bertsky/ocrd_origami) segmentation :construction_worker: 
- [ocrd_wrap](https://github.com/bertsky/ocrd_wrap) with [DeslantImg](https://github.com/githubharald/DeslantImg) (for handwriting)
- experiments on OCR/HTR training :construction_worker: 


---

## 3 User survey
### General data

- workshop for Kitodo user community
- open [survey](https://limesurvey.rz.tu-bs.de/index.php/444955) to understand the needs concerning OCR-D integration
- 33 detailed questions regarding:
  - type/quantity/quality of data
  - technical constraints on software
  - Kitodo versions/migration and servicing
  - preferences regarding service model
  - previous/other OCR experience
  - preferences regarding workflow and monitoring UI
  - preferences regarding quality vs. speed
  - required output formats and interface for manual correction
  - demand for OCR-on-demand functions
- 24 participants (so far!)

---


## 3 User survey
### Preliminary results (example)

- questions regarding kind of materials to be digitalized, format and language  
  
  → broad spectrum of materials to process (including newspapers and magazines), fonts and languages 
  ![](https://i.imgur.com/3025WBM.png)

---

## 3 User survey
### Preliminary results (example)

- questions regarding expected characteristics of OCR process  

  → need for both options "quality first" and "quantity first"
 
![](https://i.imgur.com/mNGV88x.png)

---

## 3 User survey
### Summary

- survey still active → results not fully analysed yet

- information will guide Kitodo/OCR-D design and implementation

- everyone welcome to [participate](https://limesurvey.rz.tu-bs.de/index.php/444955)