<!DOCTYPE html>
<html lang="en" data-content_root="./" >
<head>
<meta charset="utf-8" />
<meta name="viewport" content="width=device-width, initial-scale=1.0" /><meta name="viewport" content="width=device-width, initial-scale=1" />
<title>cv-analysis - Visual (CV-Based) Document Parsing — CV Analysis Service 2.5.2 documentation</title>
<script data-cfasync="false">
document.documentElement.dataset.mode = localStorage.getItem("mode") || "";
document.documentElement.dataset.theme = localStorage.getItem("theme") || "light";
</script>
<!-- Loaded before other Sphinx assets -->
<link href="_static/styles/theme.css?digest=8d27b9dea8ad943066ae" rel="stylesheet" />
<link href="_static/styles/bootstrap.css?digest=8d27b9dea8ad943066ae" rel="stylesheet" />
<link href="_static/styles/pydata-sphinx-theme.css?digest=8d27b9dea8ad943066ae" rel="stylesheet" />
<link href="_static/vendor/fontawesome/6.5.1/css/all.min.css?digest=8d27b9dea8ad943066ae" rel="stylesheet" />
<link rel="preload" as="font" type="font/woff2" crossorigin href="_static/vendor/fontawesome/6.5.1/webfonts/fa-solid-900.woff2" />
<link rel="preload" as="font" type="font/woff2" crossorigin href="_static/vendor/fontawesome/6.5.1/webfonts/fa-brands-400.woff2" />
<link rel="preload" as="font" type="font/woff2" crossorigin href="_static/vendor/fontawesome/6.5.1/webfonts/fa-regular-400.woff2" />
<link rel="stylesheet" type="text/css" href="_static/pygments.css?v=a746c00c" />
<link rel="stylesheet" type="text/css" href="https://assets.readthedocs.org/static/css/badge_only.css" />
<!-- Pre-loaded scripts that we'll load fully later -->
<link rel="preload" as="script" href="_static/scripts/bootstrap.js?digest=8d27b9dea8ad943066ae" />
<link rel="preload" as="script" href="_static/scripts/pydata-sphinx-theme.js?digest=8d27b9dea8ad943066ae" />
<script src="_static/vendor/fontawesome/6.5.1/js/all.min.js?digest=8d27b9dea8ad943066ae"></script>
<script src="_static/documentation_options.js?v=afc61bbc"></script>
<script src="_static/doctools.js?v=9a2dae69"></script>
<script src="_static/sphinx_highlight.js?v=dc90522c"></script>
<script>DOCUMENTATION_OPTIONS.pagename = 'README';</script>
<script async="async" src="https://assets.readthedocs.org/static/javascript/readthedocs-doc-embed.js"></script>
<link rel="index" title="Index" href="genindex.html" />
<link rel="search" title="Search" href="search.html" />
<link rel="next" title="cv_analysis package" href="modules/cv_analysis.html" />
<link rel="prev" title="Welcome to CV Analysis Service documentation!" href="index.html" />
<meta name="viewport" content="width=device-width, initial-scale=1"/>
<meta name="docsearch:language" content="en"/>
<!-- RTD Extra Head -->
<link rel="stylesheet" href="https://assets.readthedocs.org/static/css/readthedocs-doc-embed.css" type="text/css" />
<script type="application/json" id="READTHEDOCS_DATA">{"ad_free": "", "api_host": "", "builder": "sphinx", "canonical_url": "", "docroot": "", "features": {"docsearch_disabled": false}, "global_analytics_code": null, "language": "", "page": "README", "programming_language": "", "project": "", "source_suffix": ".md", "subprojects": {}, "theme": "", "user_analytics_code": null, "version": ""}</script>
<!--
Using this variable directly instead of using `JSON.parse` is deprecated.
The READTHEDOCS_DATA global variable will be removed in the future.
-->
<script type="text/javascript">
READTHEDOCS_DATA = JSON.parse(document.getElementById('READTHEDOCS_DATA').innerHTML);
</script>
<script type="text/javascript" src="https://assets.readthedocs.org/static/javascript/readthedocs-analytics.js" async="async"></script>
<!-- end RTD <extrahead> -->
</head>
<body data-bs-spy="scroll" data-bs-target=".bd-toc-nav" data-offset="180" data-bs-root-margin="0px 0px -60%" data-default-mode="">
<a id="pst-skip-link" class="skip-link" href="#main-content">Skip to main content</a>
<div id="pst-scroll-pixel-helper"></div>
<button type="button" class="btn rounded-pill" id="pst-back-to-top">
<i class="fa-solid fa-arrow-up"></i>
Back to top
</button>
<input type="checkbox"
class="sidebar-toggle"
name="__primary"
id="__primary"/>
<label class="overlay overlay-primary" for="__primary"></label>
<input type="checkbox"
class="sidebar-toggle"
name="__secondary"
id="__secondary"/>
<label class="overlay overlay-secondary" for="__secondary"></label>
<div class="search-button__wrapper">
<div class="search-button__overlay"></div>
<div class="search-button__search-container">
<form class="bd-search d-flex align-items-center"
action="search.html"
method="get">
<i class="fa-solid fa-magnifying-glass"></i>
<input type="search"
class="form-control"
name="q"
id="search-input"
placeholder="Search the docs ..."
aria-label="Search the docs ..."
autocomplete="off"
autocorrect="off"
autocapitalize="off"
spellcheck="false"/>
<span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd>K</kbd></span>
</form></div>
</div>
<header class="bd-header navbar navbar-expand-lg bd-navbar">
<div class="bd-header__inner bd-page-width">
<label class="sidebar-toggle primary-toggle" for="__primary">
<span class="fa-solid fa-bars"></span>
</label>
<div class="col-lg-3 navbar-header-items__start">
<div class="navbar-item">
<a class="navbar-brand logo" href="index.html">
<img src="_static/logo.png" class="logo__image only-light" alt="CV Analysis Service 2.5.2 documentation - Home"/>
<script>document.write(`<img src="_static/logo.png" class="logo__image only-dark" alt="CV Analysis Service 2.5.2 documentation - Home"/>`);</script>
</a></div>
</div>
<div class="col-lg-9 navbar-header-items">
<div class="me-auto navbar-header-items__center">
<div class="navbar-item">
<nav class="navbar-nav">
<ul class="bd-navbar-elements navbar-nav">
<li class="nav-item current active">
<a class="nav-link nav-internal" href="#">
cv-analysis - Visual (CV-Based) Document Parsing
</a>
</li>
<li class="nav-item">
<a class="nav-link nav-internal" href="modules/cv_analysis.html">
cv_analysis package
</a>
</li>
<li class="nav-item">
<a class="nav-link nav-internal" href="modules/serve.html">
serve module
</a>
</li>
</ul>
</nav></div>
</div>
<div class="navbar-header-items__end">
<div class="navbar-item navbar-persistent--container">
<script>
document.write(`
<button class="btn navbar-btn search-button-field search-button__button" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip">
<i class="fa-solid fa-magnifying-glass"></i>
<span class="search-button__default-text">Search</span>
<span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd class="kbd-shortcut__modifier">K</kbd></span>
</button>
`);
</script>
</div>
<div class="navbar-item">
<script>
document.write(`
<button class="btn btn-sm navbar-btn theme-switch-button" title="light/dark" aria-label="light/dark" data-bs-placement="bottom" data-bs-toggle="tooltip">
<span class="theme-switch nav-link" data-mode="light"><i class="fa-solid fa-sun fa-lg"></i></span>
<span class="theme-switch nav-link" data-mode="dark"><i class="fa-solid fa-moon fa-lg"></i></span>
<span class="theme-switch nav-link" data-mode="auto"><i class="fa-solid fa-circle-half-stroke fa-lg"></i></span>
</button>
`);
</script></div>
</div>
</div>
<div class="navbar-persistent--mobile">
<script>
document.write(`
<button class="btn navbar-btn search-button-field search-button__button" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip">
<i class="fa-solid fa-magnifying-glass"></i>
<span class="search-button__default-text">Search</span>
<span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd class="kbd-shortcut__modifier">K</kbd></span>
</button>
`);
</script>
</div>
<label class="sidebar-toggle secondary-toggle" for="__secondary" tabindex="0">
<span class="fa-solid fa-outdent"></span>
</label>
</div>
</header>
<div class="bd-container">
<div class="bd-container__inner bd-page-width">
<div class="bd-sidebar-primary bd-sidebar">
<div class="sidebar-header-items sidebar-primary__section">
<div class="sidebar-header-items__center">
<div class="navbar-item">
<nav class="navbar-nav">
<ul class="bd-navbar-elements navbar-nav">
<li class="nav-item current active">
<a class="nav-link nav-internal" href="#">
cv-analysis - Visual (CV-Based) Document Parsing
</a>
</li>
<li class="nav-item">
<a class="nav-link nav-internal" href="modules/cv_analysis.html">
cv_analysis package
</a>
</li>
<li class="nav-item">
<a class="nav-link nav-internal" href="modules/serve.html">
serve module
</a>
</li>
</ul>
</nav></div>
</div>
<div class="sidebar-header-items__end">
<div class="navbar-item">
<script>
document.write(`
<button class="btn btn-sm navbar-btn theme-switch-button" title="light/dark" aria-label="light/dark" data-bs-placement="bottom" data-bs-toggle="tooltip">
<span class="theme-switch nav-link" data-mode="light"><i class="fa-solid fa-sun fa-lg"></i></span>
<span class="theme-switch nav-link" data-mode="dark"><i class="fa-solid fa-moon fa-lg"></i></span>
<span class="theme-switch nav-link" data-mode="auto"><i class="fa-solid fa-circle-half-stroke fa-lg"></i></span>
</button>
`);
</script></div>
</div>
</div>
<div class="sidebar-primary-items__start sidebar-primary__section">
<div class="sidebar-primary-item">
<nav class="bd-docs-nav bd-links"
aria-label="Section Navigation">
<p class="bd-links__title" role="heading" aria-level="1">Section Navigation</p>
<div class="bd-toc-item navbar-nav"></div>
</nav></div>
</div>
<div class="sidebar-primary-items__end sidebar-primary__section">
</div>
<div id="rtd-footer-container"></div>
</div>
<main id="main-content" class="bd-main">
<div class="bd-content">
<div class="bd-article-container">
<div class="bd-header-article">
<div class="header-article-items header-article__inner">
<div class="header-article-items__start">
<div class="header-article-item">
<nav aria-label="Breadcrumb">
<ul class="bd-breadcrumbs">
<li class="breadcrumb-item breadcrumb-home">
<a href="index.html" class="nav-link" aria-label="Home">
<i class="fa-solid fa-home"></i>
</a>
</li>
<li class="breadcrumb-item active" aria-current="page">cv-analysis...</li>
</ul>
</nav>
</div>
</div>
</div>
</div>
<div id="searchbox"></div>
<article class="bd-article">
<section id="cv-analysis-visual-cv-based-document-parsing">
<h1>cv-analysis - Visual (CV-Based) Document Parsing<a class="headerlink" href="#cv-analysis-visual-cv-based-document-parsing" title="Link to this heading">#</a></h1>
<p>parse_pdf()
This repository implements computer vision based approaches for detecting and parsing visual features such as tables or
previous redactions in documents.</p>
<section id="api">
<h2>API<a class="headerlink" href="#api" title="Link to this heading">#</a></h2>
<p>Input message:</p>
<div class="highlight-json notranslate"><div class="highlight"><pre><span></span><span class="p">{</span>
<span class="w"> </span><span class="nt">"targetFilePath"</span><span class="p">:</span><span class="w"> </span><span class="p">{</span>
<span class="w"> </span><span class="nt">"pdf"</span><span class="p">:</span><span class="w"> </span><span class="s2">"absolute file path"</span><span class="p">,</span>
<span class="w"> </span><span class="nt">"vlp_output"</span><span class="p">:</span><span class="w"> </span><span class="s2">"absolute file path"</span>
<span class="w"> </span><span class="p">},</span>
<span class="w"> </span><span class="nt">"responseFilePath"</span><span class="p">:</span><span class="w"> </span><span class="s2">"absolute file path"</span><span class="p">,</span>
<span class="w"> </span><span class="nt">"operation"</span><span class="p">:</span><span class="w"> </span><span class="s2">"table_image_inference"</span>
<span class="p">}</span>
</pre></div>
</div>
<p>Response is uploaded to the storage as specified in the <code class="docutils literal notranslate"><span class="pre">responseFilePath</span></code> field. The structure is as follows:</p>
<div class="highlight-json notranslate"><div class="highlight"><pre><span></span><span class="p">{</span>
<span class="w"> </span><span class="err">...</span><span class="p">,</span>
<span class="w"> </span><span class="nt">"data"</span><span class="p">:</span><span class="w"> </span><span class="p">[</span>
<span class="w"> </span><span class="p">{</span>
<span class="w"> </span><span class="err">'pageNum'</span><span class="p">:</span><span class="w"> </span><span class="mi">0</span><span class="p">,</span>
<span class="w"> </span><span class="err">'bbox'</span><span class="p">:</span><span class="w"> </span><span class="p">{</span>
<span class="w"> </span><span class="err">'x</span><span class="mi">1</span><span class="err">'</span><span class="p">:</span><span class="w"> </span><span class="mf">55.3407</span><span class="p">,</span>
<span class="w"> </span><span class="err">'y</span><span class="mi">1</span><span class="err">'</span><span class="p">:</span><span class="w"> </span><span class="mf">247.0246</span><span class="p">,</span>
<span class="w"> </span><span class="err">'x</span><span class="mi">2</span><span class="err">'</span><span class="p">:</span><span class="w"> </span><span class="mf">558.5602</span><span class="p">,</span>
<span class="w"> </span><span class="err">'y</span><span class="mi">2</span><span class="err">'</span><span class="p">:</span><span class="w"> </span><span class="mf">598.0585</span>
<span class="w"> </span><span class="p">},</span>
<span class="w"> </span><span class="err">'uuid'</span><span class="p">:</span><span class="w"> </span><span class="err">'</span><span class="mi">2</span><span class="err">b</span><span class="mi">10</span><span class="err">c</span><span class="mi">1</span><span class="err">a</span><span class="mi">2-393</span><span class="err">c</span><span class="mi">-4</span><span class="kc">f</span><span class="err">ca</span><span class="mi">-</span><span class="err">b</span><span class="mf">9e3-0</span><span class="err">ad</span><span class="mi">5</span><span class="err">b</span><span class="mi">774</span><span class="err">ac</span><span class="mi">84</span><span class="err">'</span><span class="p">,</span>
<span class="w"> </span><span class="err">'label'</span><span class="p">:</span><span class="w"> </span><span class="err">'</span><span class="kc">ta</span><span class="err">ble'</span><span class="p">,</span>
<span class="w"> </span><span class="err">'</span><span class="kc">ta</span><span class="err">bleLi</span><span class="kc">nes</span><span class="err">'</span><span class="p">:</span><span class="w"> </span><span class="p">[</span>
<span class="w"> </span><span class="p">{</span>
<span class="w"> </span><span class="err">'x</span><span class="mi">1</span><span class="err">'</span><span class="p">:</span><span class="w"> </span><span class="mi">0</span><span class="p">,</span>
<span class="w"> </span><span class="err">'y</span><span class="mi">1</span><span class="err">'</span><span class="p">:</span><span class="w"> </span><span class="mi">16</span><span class="p">,</span>
<span class="w"> </span><span class="err">'x</span><span class="mi">2</span><span class="err">'</span><span class="p">:</span><span class="w"> </span><span class="mi">1399</span><span class="p">,</span>
<span class="w"> </span><span class="err">'y</span><span class="mi">2</span><span class="err">'</span><span class="p">:</span><span class="w"> </span><span class="mi">16</span>
<span class="w"> </span><span class="p">},</span>
<span class="w"> </span><span class="err">...</span>
<span class="w"> </span><span class="p">],</span>
<span class="w"> </span><span class="err">'imageI</span><span class="kc">nf</span><span class="err">o'</span><span class="p">:</span><span class="w"> </span><span class="p">{</span>
<span class="w"> </span><span class="err">'heigh</span><span class="kc">t</span><span class="err">'</span><span class="p">:</span><span class="w"> </span><span class="mi">693</span><span class="p">,</span>
<span class="w"> </span><span class="err">'wid</span><span class="kc">t</span><span class="err">h'</span><span class="p">:</span><span class="w"> </span><span class="mi">1414</span>
<span class="w"> </span><span class="p">}</span>
<span class="w"> </span><span class="p">},</span>
<span class="w"> </span><span class="err">...</span>
<span class="w"> </span><span class="p">]</span>
<span class="p">}</span>
</pre></div>
</div>
</section>
<section id="installation">
<h2>Installation<a class="headerlink" href="#installation" title="Link to this heading">#</a></h2>
<div class="highlight-bash notranslate"><div class="highlight"><pre><span></span>git<span class="w"> </span>clone<span class="w"> </span>ssh://git@git.iqser.com:2222/rr/cv-analysis.git
<span class="nb">cd</span><span class="w"> </span>cv-analysis
python<span class="w"> </span>-m<span class="w"> </span>venv<span class="w"> </span>env
<span class="nb">source</span><span class="w"> </span>env/bin/activate
pip<span class="w"> </span>install<span class="w"> </span>-e<span class="w"> </span>.
pip<span class="w"> </span>install<span class="w"> </span>-r<span class="w"> </span>requirements.txt
dvc<span class="w"> </span>pull
</pre></div>
</div>
</section>
<section id="usage">
<h2>Usage<a class="headerlink" href="#usage" title="Link to this heading">#</a></h2>
<section id="as-an-api">
<h3>As an API<a class="headerlink" href="#as-an-api" title="Link to this heading">#</a></h3>
<p>The module provided functions for the individual tasks that all return some kind of collection of points, depending on
the specific task.</p>
<section id="redaction-detection-api">
<h4>Redaction Detection (API)<a class="headerlink" href="#redaction-detection-api" title="Link to this heading">#</a></h4>
<p>The below snippet shows hot to find the outlines of previous redactions.</p>
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="kn">from</span> <span class="nn">cv_analysis.redaction_detection</span> <span class="kn">import</span> <span class="n">find_redactions</span>
<span class="kn">import</span> <span class="nn">pdf2image</span>
<span class="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span>
<span class="n">pdf_path</span> <span class="o">=</span> <span class="o">...</span>
<span class="n">page_index</span> <span class="o">=</span> <span class="o">...</span>
<span class="n">page</span> <span class="o">=</span> <span class="n">pdf2image</span><span class="o">.</span><span class="n">convert_from_path</span><span class="p">(</span><span class="n">pdf_path</span><span class="p">,</span> <span class="n">first_page</span><span class="o">=</span><span class="n">page_index</span><span class="p">,</span> <span class="n">last_page</span><span class="o">=</span><span class="n">page_index</span><span class="p">)[</span><span class="mi">0</span><span class="p">]</span>
<span class="n">page</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">(</span><span class="n">page</span><span class="p">)</span>
<span class="n">redaction_contours</span> <span class="o">=</span> <span class="n">find_redactions</span><span class="p">(</span><span class="n">page</span><span class="p">)</span>
</pre></div>
</div>
</section>
</section>
</section>
<section id="as-a-cli-tool">
<h2>As a CLI Tool<a class="headerlink" href="#as-a-cli-tool" title="Link to this heading">#</a></h2>
<p>Core API functionalities can be used through a CLI.</p>
<section id="table-parsing">
<h3>Table Parsing<a class="headerlink" href="#table-parsing" title="Link to this heading">#</a></h3>
<p>The tables parsing utility detects and segments tables into individual cells.</p>
<div class="highlight-bash notranslate"><div class="highlight"><pre><span></span>python<span class="w"> </span>scripts/annotate.py<span class="w"> </span>data/test_pdf.pdf<span class="w"> </span><span class="m">7</span><span class="w"> </span>--type<span class="w"> </span>table
</pre></div>
</div>
<p>The below image shows a parsed table, where each table cell has been detected individually.</p>
<p><img alt="Table Parsing Demonstration" src="_images/table_parsing.png" /></p>
</section>
<section id="redaction-detection-cli">
<h3>Redaction Detection (CLI)<a class="headerlink" href="#redaction-detection-cli" title="Link to this heading">#</a></h3>
<p>The redaction detection utility detects previous redactions in PDFs (filled black rectangles).</p>
<div class="highlight-bash notranslate"><div class="highlight"><pre><span></span>python<span class="w"> </span>scripts/annotate.py<span class="w"> </span>data/test_pdf.pdf<span class="w"> </span><span class="m">2</span><span class="w"> </span>--type<span class="w"> </span>redaction
</pre></div>
</div>
<p>The below image shows the detected redactions with green outlines.</p>
<p><img alt="Redaction Detection Demonstration" src="_images/redaction_detection.png" /></p>
</section>
<section id="layout-parsing">
<h3>Layout Parsing<a class="headerlink" href="#layout-parsing" title="Link to this heading">#</a></h3>
<p>The layout parsing utility detects elements such as paragraphs, tables and figures.</p>
<div class="highlight-bash notranslate"><div class="highlight"><pre><span></span>python<span class="w"> </span>scripts/annotate.py<span class="w"> </span>data/test_pdf.pdf<span class="w"> </span><span class="m">7</span><span class="w"> </span>--type<span class="w"> </span>layout
</pre></div>
</div>
<p>The below image shows the detected layout elements on a page.</p>
<p><img alt="Layout Parsing Demonstration" src="_images/layout_parsing.png" /></p>
</section>
<section id="figure-detection">
<h3>Figure Detection<a class="headerlink" href="#figure-detection" title="Link to this heading">#</a></h3>
<p>The figure detection utility detects figures specifically, which can be missed by the generic layout parsing utility.</p>
<div class="highlight-bash notranslate"><div class="highlight"><pre><span></span>python<span class="w"> </span>scripts/annotate.py<span class="w"> </span>data/test_pdf.pdf<span class="w"> </span><span class="m">3</span><span class="w"> </span>--type<span class="w"> </span>figure
</pre></div>
</div>
<p>The below image shows the detected figure on a page.</p>
<p><img alt="Figure Detection Demonstration" src="_images/figure_detection.png" /></p>
</section>
</section>
<section id="running-as-a-service">
<h2>Running as a service<a class="headerlink" href="#running-as-a-service" title="Link to this heading">#</a></h2>
<section id="building">
<h3>Building<a class="headerlink" href="#building" title="Link to this heading">#</a></h3>
<p>Build base image</p>
<div class="highlight-bash notranslate"><div class="highlight"><pre><span></span>bash<span class="w"> </span>setup/docker.sh
</pre></div>
</div>
<p>Build head image</p>
<div class="highlight-bash notranslate"><div class="highlight"><pre><span></span>docker<span class="w"> </span>build<span class="w"> </span>-f<span class="w"> </span>Dockerfile<span class="w"> </span>-t<span class="w"> </span>cv-analysis<span class="w"> </span>.<span class="w"> </span>--build-arg<span class="w"> </span><span class="nv">BASE_ROOT</span><span class="o">=</span><span class="s2">""</span>
</pre></div>
</div>
</section>
<section id="usage-service">
<h3>Usage (service)<a class="headerlink" href="#usage-service" title="Link to this heading">#</a></h3>
<p>Shell 1</p>
<div class="highlight-bash notranslate"><div class="highlight"><pre><span></span>docker<span class="w"> </span>run<span class="w"> </span>--rm<span class="w"> </span>--net<span class="o">=</span>host<span class="w"> </span>--rm<span class="w"> </span>cv-analysis
</pre></div>
</div>
<p>Shell 2</p>
<div class="highlight-bash notranslate"><div class="highlight"><pre><span></span>python<span class="w"> </span>scripts/client_mock.py<span class="w"> </span>--pdf_path<span class="w"> </span>/path/to/a/pdf
</pre></div>
</div>
</section>
</section>
</section>
</article>
<footer class="prev-next-footer">
<div class="prev-next-area">
<a class="left-prev"
href="index.html"
title="previous page">
<i class="fa-solid fa-angle-left"></i>
<div class="prev-next-info">
<p class="prev-next-subtitle">previous</p>
<p class="prev-next-title">Welcome to CV Analysis Service documentation!</p>
</div>
</a>
<a class="right-next"
href="modules/cv_analysis.html"
title="next page">
<div class="prev-next-info">
<p class="prev-next-subtitle">next</p>
<p class="prev-next-title">cv_analysis package</p>
</div>
<i class="fa-solid fa-angle-right"></i>
</a>
</div>
</footer>
</div>
<div class="bd-sidebar-secondary bd-toc"><div class="sidebar-secondary-items sidebar-secondary__inner">
<div class="sidebar-secondary-item">
<div
id="pst-page-navigation-heading-2"
class="page-toc tocsection onthispage">
<i class="fa-solid fa-list"></i> On this page
</div>
<nav class="bd-toc-nav page-toc" aria-labelledby="pst-page-navigation-heading-2">
<ul class="visible nav section-nav flex-column">
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#api">API</a></li>
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#installation">Installation</a></li>
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#usage">Usage</a><ul class="nav section-nav flex-column">
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#as-an-api">As an API</a><ul class="nav section-nav flex-column">
<li class="toc-h4 nav-item toc-entry"><a class="reference internal nav-link" href="#redaction-detection-api">Redaction Detection (API)</a></li>
</ul>
</li>
</ul>
</li>
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#as-a-cli-tool">As a CLI Tool</a><ul class="nav section-nav flex-column">
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#table-parsing">Table Parsing</a></li>
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#redaction-detection-cli">Redaction Detection (CLI)</a></li>
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#layout-parsing">Layout Parsing</a></li>
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#figure-detection">Figure Detection</a></li>
</ul>
</li>
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#running-as-a-service">Running as a service</a><ul class="nav section-nav flex-column">
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#building">Building</a></li>
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#usage-service">Usage (service)</a></li>
</ul>
</li>
</ul>
</nav></div>
<div class="sidebar-secondary-item">
<div class="tocsection sourcelink">
<a href="_sources/README.md.txt">
<i class="fa-solid fa-file-lines"></i> Show Source
</a>
</div>
</div>
</div></div>
</div>
<footer class="bd-footer-content">
</footer>
</main>
</div>
</div>
<!-- Scripts loaded after <body> so the DOM is not blocked -->
<script src="_static/scripts/bootstrap.js?digest=8d27b9dea8ad943066ae"></script>
<script src="_static/scripts/pydata-sphinx-theme.js?digest=8d27b9dea8ad943066ae"></script>
<footer class="bd-footer">
<div class="bd-footer__inner bd-page-width">
<div class="footer-items__start">
<div class="footer-item">
<p class="copyright">
© Copyright All rights reserved.
<br/>
</p>
</div>
<div class="footer-item">
<p class="sphinx-version">
Created using <a href="https://www.sphinx-doc.org/">Sphinx</a> 7.3.7.
<br/>
</p>
</div>
</div>
<div class="footer-items__end">
<div class="footer-item">
<p class="theme-version">
Built with the <a href="https://pydata-sphinx-theme.readthedocs.io/en/stable/index.html">PyData Sphinx Theme</a> 0.15.2.
</p></div>
</div>
</div>
</footer>
</body>
</html>