Built site for gh-pages

.nojekyll

@@ -1 +1 @@
-b7306875
+2914ac2e

search.json

@@ -92,7 +92,7 @@
     "href": "software.html#open-source",
     "title": "4  HTR/OCR software and data",
     "section": "4.2 Open source",
-    "text": "4.2 Open source\n\n4.2.1 eScriptorium\neScriptorium is a software platform created to make text layout analysis and recognition easy. The underlying text recognition is based on the Kraken framework, for which it serves as an interface. The interface allows for the user to annotate and train custom models, with no coding required, similar to Transkribus. Despite providing much the same features as Transkribus, eScriptorium is not program as such, but a service to be run on a server or in a docker image. This does require knowledge on how to setup and manage docker instances, or do a full server install. Good introductions to the use eScriptorium are provided through the standard documentation and a course by the University of Mannheim.\n\n\n\nPro:\nCon:\n\n\n\n\nuser friendly\ncomplex installation for novices\n\n\nOK documentation\n\n\n\nfull workflow control\n\n\n\ninteroperability\n\n\n\nshared models\n\n\n\n\n\n4.2.1.1 Installation & Use\nA basic docker install is provided on the project code pages.\n\n\n\n4.2.2 OCR4all\nOCR4all is an OCR platform built around the Calamari text recognition engine and the LAREX layout analysis tool. Similar to eScriptorium and Transkribus it aims at making the transcription of documents easy, without the need for coding. Similar to eScriptorium the setup is not program as such, but a service to be run on a server or in a docker image.\n\n\n\nPro:\nCon:\n\n\n\n\nuser friendly\ncomplex installation for novices\n\n\nOK documentation\n\n\n\nfull workflow control\n\n\n\ninteroperability\n\n\n\nshared models\n\n\n\n\n\n4.2.2.1 Installation & Use\nThe software runs as a docker service and can be installed using the following command:\nsudo docker run -p 1476:8080 \\\n    -u `id -u root`:`id -g $USER` \\\n    --name ocr4all \\\n    -v $PWD/data:/var/ocr4all/data \\\n    -v $PWD/models:/var/ocr4all/models/custom \\\n    -it uniwuezpd/ocr4all\n\n\n\n4.2.3 Tesseract\nTesseract is a popular open-source OCR program, originally created by Google but now maintained by the open-source community. Out of the box Tesseract does not allow for handwritten text recognition as the included models are not trained on handwritten data.\nHowever, the software does allow for the retraining of models. Having been a mainstay in OCR work in the open source community a zoo of third party software providing interfaces and additional functionality exists, as well as a python interface (pytesseract) to make data processing easier.\n\n\n4.2.4 Custom pipelines and libraries\nMost of the above mentioned software options are mature and require limited coding knowledge to operate. However, I would be amiss to not mention the underlying HTR/OCR programming libraries. Depending on the use case one could benefit from using low level libraries, rather than more user friendly platforms (built around them). Most prominent python libraries for HTR/OCR work are Kraken as used by eScriptorium, PyLaia used by Transkribus, EasyOCR and PaddleOCR.\nAll these libraries provide machine learning setups to train handwritten text recognition models of the CNN + LSTM/RNN + CTC kind. In addition, Kraken and PaddleOCR provide document layout analysis (segmentation) options.\n\n\n\nPro:\nCon:\n\n\n\n\nflexible\ncomplex installation\n\n\nfull workflow control\ncoding required",
+    "text": "4.2 Open source\n\n4.2.1 eScriptorium\neScriptorium is a software platform created to make text layout analysis and recognition easy. The underlying text recognition is based on the Kraken framework, for which it serves as an interface. The interface allows for the user to annotate and train custom models, with no coding required, similar to Transkribus. Despite providing much the same features as Transkribus, eScriptorium is not program as such, but a service to be run on a server or in a docker image. This does require knowledge on how to setup and manage docker instances, or do a full server install. Good introductions to the use eScriptorium are provided through the standard documentation and a course by the University of Mannheim.\n\n\n\nPro:\nCon:\n\n\n\n\nuser friendly\ncomplex installation for novices\n\n\nOK documentation\n\n\n\nfull workflow control\n\n\n\ninteroperability\n\n\n\nshared models\n\n\n\n\n\n4.2.1.1 Installation & Use\nA basic docker install is provided on the project code pages.\n\n\n\n4.2.2 ArkIndex\nArkIndex is a document processing platform similar to Transkribus. More so, the this open-source platform is made by the company, Teklia, behind the PyLaia library underpinning most of Transkribus. In therefore offers the same functionality with a different interface.\n\n4.2.2.1 Installation & Use\nA basic docker install is provided on the project documentation pages.\n\n\n\n4.2.3 OCR4all\nOCR4all is an OCR platform built around the Calamari text recognition engine and the LAREX layout analysis tool. Similar to eScriptorium and Transkribus it aims at making the transcription of documents easy, without the need for coding. Similar to eScriptorium the setup is not program as such, but a service to be run on a server or in a docker image.\n\n\n\nPro:\nCon:\n\n\n\n\nuser friendly\ncomplex installation for novices\n\n\nOK documentation\n\n\n\nfull workflow control\n\n\n\ninteroperability\n\n\n\nshared models\n\n\n\n\n\n4.2.3.1 Installation & Use\nThe software runs as a docker service and can be installed using the following command:\nsudo docker run -p 1476:8080 \\\n    -u `id -u root`:`id -g $USER` \\\n    --name ocr4all \\\n    -v $PWD/data:/var/ocr4all/data \\\n    -v $PWD/models:/var/ocr4all/models/custom \\\n    -it uniwuezpd/ocr4all\n\n\n\n4.2.4 Tesseract\nTesseract is a popular open-source OCR program, originally created by Google but now maintained by the open-source community. Out of the box Tesseract does not allow for handwritten text recognition as the included models are not trained on handwritten data.\nHowever, the software does allow for the retraining of models. Having been a mainstay in OCR work in the open source community a zoo of third party software providing interfaces and additional functionality exists, as well as a python interface (pytesseract) to make data processing easier.\n\n\n4.2.5 Custom pipelines and libraries\nMost of the above mentioned software options are mature and require limited coding knowledge to operate. However, I would be amiss to not mention the underlying HTR/OCR programming libraries. Depending on the use case one could benefit from using low level libraries, rather than more user friendly platforms (built around them). Most prominent python libraries for HTR/OCR work are Kraken as used by eScriptorium, PyLaia used by Transkribus, EasyOCR and PaddleOCR. Other software libraries to mention are YOLO and doc-UFCN which both cover layout and text detection needs.\nAll these libraries provide machine learning setups to train handwritten text recognition models of the CNN + LSTM/RNN + CTC kind. In addition, Kraken and PaddleOCR provide document layout analysis (segmentation) options.\n\n\n\nPro:\nCon:\n\n\n\n\nflexible\ncomplex installation\n\n\nfull workflow control\ncoding required",
     "crumbs": [
       "Home",
       "<span class='chapter-number'>4</span>  <span class='chapter-title'>HTR/OCR software and data</span>"

software.html

@@ -244,9 +244,10 @@ <h2 id="toc-title">Table of contents</h2>
   <li><a href="#open-source" id="toc-open-source" class="nav-link" data-scroll-target="#open-source"><span class="header-section-number">4.2</span> Open source</a>
   <ul class="collapse">
   <li><a href="#escriptorium" id="toc-escriptorium" class="nav-link" data-scroll-target="#escriptorium"><span class="header-section-number">4.2.1</span> eScriptorium</a></li>
-  <li><a href="#ocr4all" id="toc-ocr4all" class="nav-link" data-scroll-target="#ocr4all"><span class="header-section-number">4.2.2</span> OCR4all</a></li>
-  <li><a href="#tesseract" id="toc-tesseract" class="nav-link" data-scroll-target="#tesseract"><span class="header-section-number">4.2.3</span> Tesseract</a></li>
-  <li><a href="#custom-pipelines-and-libraries" id="toc-custom-pipelines-and-libraries" class="nav-link" data-scroll-target="#custom-pipelines-and-libraries"><span class="header-section-number">4.2.4</span> Custom pipelines and libraries</a></li>
+  <li><a href="#arkindex" id="toc-arkindex" class="nav-link" data-scroll-target="#arkindex"><span class="header-section-number">4.2.2</span> ArkIndex</a></li>
+  <li><a href="#ocr4all" id="toc-ocr4all" class="nav-link" data-scroll-target="#ocr4all"><span class="header-section-number">4.2.3</span> OCR4all</a></li>
+  <li><a href="#tesseract" id="toc-tesseract" class="nav-link" data-scroll-target="#tesseract"><span class="header-section-number">4.2.4</span> Tesseract</a></li>
+  <li><a href="#custom-pipelines-and-libraries" id="toc-custom-pipelines-and-libraries" class="nav-link" data-scroll-target="#custom-pipelines-and-libraries"><span class="header-section-number">4.2.5</span> Custom pipelines and libraries</a></li>
   </ul></li>
   <li><a href="#data" id="toc-data" class="nav-link" data-scroll-target="#data"><span class="header-section-number">4.3</span> Data</a></li>
   </ul>
@@ -385,8 +386,16 @@ <h4 data-number="4.2.1.1" class="anchored" data-anchor-id="installation-use"><sp
 <p>A basic docker install is provided on <a href="https://gitlab.com/scripta/escriptorium/-/wikis/docker-install">the project code pages</a>.</p>
 </section>
 </section>
-<section id="ocr4all" class="level3" data-number="4.2.2">
-<h3 data-number="4.2.2" class="anchored" data-anchor-id="ocr4all"><span class="header-section-number">4.2.2</span> <a href="https://www.ocr4all.org/">OCR4all</a></h3>
+<section id="arkindex" class="level3" data-number="4.2.2">
+<h3 data-number="4.2.2" class="anchored" data-anchor-id="arkindex"><span class="header-section-number">4.2.2</span> <a href="https://demo.arkindex.org/">ArkIndex</a></h3>
+<p>ArkIndex is a document processing platform similar to Transkribus. More so, the this open-source platform is made by the company, Teklia, behind the PyLaia library underpinning most of Transkribus. In therefore offers the same functionality with a different interface.</p>
+<section id="installation-use-1" class="level4" data-number="4.2.2.1">
+<h4 data-number="4.2.2.1" class="anchored" data-anchor-id="installation-use-1"><span class="header-section-number">4.2.2.1</span> Installation &amp; Use</h4>
+<p>A basic docker install is provided on <a href="https://doc.arkindex.org/deployment/setup/">the project documentation pages</a>.</p>
+</section>
+</section>
+<section id="ocr4all" class="level3" data-number="4.2.3">
+<h3 data-number="4.2.3" class="anchored" data-anchor-id="ocr4all"><span class="header-section-number">4.2.3</span> <a href="https://www.ocr4all.org/">OCR4all</a></h3>
 <p>OCR4all is an OCR platform built around the Calamari text recognition engine and the LAREX layout analysis tool. Similar to eScriptorium and Transkribus it aims at making the transcription of documents easy, without the need for coding. Similar to eScriptorium the setup is not program as such, but a service to be run on a server or in a docker image.</p>
 <table class="caption-top table">
 <thead>
@@ -418,8 +427,8 @@ <h3 data-number="4.2.2" class="anchored" data-anchor-id="ocr4all"><span class="h
 </tr>
 </tbody>
 </table>
-<section id="installation-use-1" class="level4" data-number="4.2.2.1">
-<h4 data-number="4.2.2.1" class="anchored" data-anchor-id="installation-use-1"><span class="header-section-number">4.2.2.1</span> Installation &amp; Use</h4>
+<section id="installation-use-2" class="level4" data-number="4.2.3.1">
+<h4 data-number="4.2.3.1" class="anchored" data-anchor-id="installation-use-2"><span class="header-section-number">4.2.3.1</span> Installation &amp; Use</h4>
 <p>The software runs as a docker service and can be installed using the following command:</p>
 <div class="sourceCode" id="cb1"><pre class="sourceCode bash code-with-copy"><code class="sourceCode bash"><span id="cb1-1"><a href="#cb1-1" aria-hidden="true" tabindex="-1"></a><span class="fu">sudo</span> docker run <span class="at">-p</span> 1476:8080 <span class="dt">\</span></span>
 <span id="cb1-2"><a href="#cb1-2" aria-hidden="true" tabindex="-1"></a>    <span class="at">-u</span> <span class="kw">`</span><span class="fu">id</span> <span class="at">-u</span> root<span class="kw">`</span>:<span class="kw">`</span><span class="fu">id</span> <span class="at">-g</span> <span class="va">$USER</span><span class="kw">`</span> <span class="dt">\</span></span>
@@ -429,14 +438,14 @@ <h4 data-number="4.2.2.1" class="anchored" data-anchor-id="installation-use-1"><
 <span id="cb1-6"><a href="#cb1-6" aria-hidden="true" tabindex="-1"></a>    <span class="at">-it</span> uniwuezpd/ocr4all</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
 </section>
 </section>
-<section id="tesseract" class="level3" data-number="4.2.3">
-<h3 data-number="4.2.3" class="anchored" data-anchor-id="tesseract"><span class="header-section-number">4.2.3</span> <a href="https://tesseract-ocr.github.io/tessdoc/">Tesseract</a></h3>
+<section id="tesseract" class="level3" data-number="4.2.4">
+<h3 data-number="4.2.4" class="anchored" data-anchor-id="tesseract"><span class="header-section-number">4.2.4</span> <a href="https://tesseract-ocr.github.io/tessdoc/">Tesseract</a></h3>
 <p>Tesseract is a popular open-source OCR program, originally created by Google but now maintained by the open-source community. Out of the box Tesseract does not allow for handwritten text recognition as the included models are not trained on handwritten data.</p>
 <p>However, the software does allow for the retraining of models. Having been a mainstay in OCR work in the open source community <a href="https://tesseract-ocr.github.io/tessdoc/User-Projects-%E2%80%93-3rdParty.html">a zoo of third party software</a> providing interfaces and additional functionality exists, as well as a <a href="https://github.com/madmaze/pytesseract">python interface (pytesseract)</a> to make data processing easier.</p>
 </section>
-<section id="custom-pipelines-and-libraries" class="level3" data-number="4.2.4">
-<h3 data-number="4.2.4" class="anchored" data-anchor-id="custom-pipelines-and-libraries"><span class="header-section-number">4.2.4</span> Custom pipelines and libraries</h3>
-<p>Most of the above mentioned software options are mature and require limited coding knowledge to operate. However, I would be amiss to not mention the underlying HTR/OCR programming libraries. Depending on the use case one could benefit from using low level libraries, rather than more user friendly platforms (built around them). Most prominent python libraries for HTR/OCR work are <a href="https://kraken.re/main/index.html">Kraken</a> as used by eScriptorium, <a href="https://gitlab.teklia.com/atr/pylaia">PyLaia</a> used by Transkribus, <a href="https://github.com/JaidedAI/EasyOCR">EasyOCR</a> and <a href="https://github.com/PaddlePaddle/PaddleOCR/blob/main/README_en.md">PaddleOCR</a>.</p>
+<section id="custom-pipelines-and-libraries" class="level3" data-number="4.2.5">
+<h3 data-number="4.2.5" class="anchored" data-anchor-id="custom-pipelines-and-libraries"><span class="header-section-number">4.2.5</span> Custom pipelines and libraries</h3>
+<p>Most of the above mentioned software options are mature and require limited coding knowledge to operate. However, I would be amiss to not mention the underlying HTR/OCR programming libraries. Depending on the use case one could benefit from using low level libraries, rather than more user friendly platforms (built around them). Most prominent python libraries for HTR/OCR work are <a href="https://kraken.re/main/index.html">Kraken</a> as used by eScriptorium, <a href="https://gitlab.teklia.com/atr/pylaia">PyLaia</a> used by Transkribus, <a href="https://github.com/JaidedAI/EasyOCR">EasyOCR</a> and <a href="https://github.com/PaddlePaddle/PaddleOCR/blob/main/README_en.md">PaddleOCR</a>. Other software libraries to mention are <a href="">YOLO</a> and <a href="https://pypi.org/project/doc-ufcn/">doc-UFCN</a> which both cover layout and text detection needs.</p>
 <p>All these libraries provide machine learning setups to train handwritten text recognition models of the CNN + LSTM/RNN + CTC kind. In addition, Kraken and PaddleOCR provide document layout analysis (segmentation) options.</p>
 <table class="caption-top table">
 <thead>