cv-analysis-service/docs/build/html/modules/cv_analysis.figure_detection.text.html
2024-05-06 15:31:45 +02:00

560 lines
24 KiB
HTML
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

<!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.figure_detection.text module &#8212; 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 = 'modules/cv_analysis.figure_detection.text';</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.server package" href="cv_analysis.server.html" />
<link rel="prev" title="cv_analysis.figure_detection.figures module" href="cv_analysis.figure_detection.figures.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": "modules/cv_analysis.figure_detection.text", "programming_language": "", "project": "", "source_suffix": ".rst", "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">
<a class="nav-link nav-internal" href="../README.html">
cv-analysis - Visual (CV-Based) Document Parsing
</a>
</li>
<li class="nav-item current active">
<a class="nav-link nav-internal" href="cv_analysis.html">
cv_analysis package
</a>
</li>
<li class="nav-item">
<a class="nav-link nav-internal" href="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">
<a class="nav-link nav-internal" href="../README.html">
cv-analysis - Visual (CV-Based) Document Parsing
</a>
</li>
<li class="nav-item current active">
<a class="nav-link nav-internal" href="cv_analysis.html">
cv_analysis package
</a>
</li>
<li class="nav-item">
<a class="nav-link nav-internal" href="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"><ul class="current nav bd-sidenav">
<li class="toctree-l1 current active has-children"><a class="reference internal" href="cv_analysis.figure_detection.html">cv_analysis.figure_detection package</a><input checked="" class="toctree-checkbox" id="toctree-checkbox-1" name="toctree-checkbox-1" type="checkbox"/><label class="toctree-toggle" for="toctree-checkbox-1"><i class="fa-solid fa-chevron-down"></i></label><ul class="current">
<li class="toctree-l2"><a class="reference internal" href="cv_analysis.figure_detection.figure_detection.html">cv_analysis.figure_detection.figure_detection module</a></li>
<li class="toctree-l2"><a class="reference internal" href="cv_analysis.figure_detection.figures.html">cv_analysis.figure_detection.figures module</a></li>
<li class="toctree-l2 current active"><a class="current reference internal" href="#">cv_analysis.figure_detection.text module</a></li>
</ul>
</li>
<li class="toctree-l1 has-children"><a class="reference internal" href="cv_analysis.server.html">cv_analysis.server package</a><input class="toctree-checkbox" id="toctree-checkbox-2" name="toctree-checkbox-2" type="checkbox"/><label class="toctree-toggle" for="toctree-checkbox-2"><i class="fa-solid fa-chevron-down"></i></label><ul>
<li class="toctree-l2"><a class="reference internal" href="cv_analysis.server.pipeline.html">cv_analysis.server.pipeline module</a></li>
</ul>
</li>
<li class="toctree-l1 has-children"><a class="reference internal" href="cv_analysis.utils.html">cv_analysis.utils package</a><input class="toctree-checkbox" id="toctree-checkbox-3" name="toctree-checkbox-3" type="checkbox"/><label class="toctree-toggle" for="toctree-checkbox-3"><i class="fa-solid fa-chevron-down"></i></label><ul>
<li class="toctree-l2"><a class="reference internal" href="cv_analysis.utils.annotate.html">cv_analysis.utils.annotate module</a></li>
<li class="toctree-l2"><a class="reference internal" href="cv_analysis.utils.banner.html">cv_analysis.utils.banner module</a></li>
<li class="toctree-l2"><a class="reference internal" href="cv_analysis.utils.connect_rects.html">cv_analysis.utils.connect_rects module</a></li>
<li class="toctree-l2"><a class="reference internal" href="cv_analysis.utils.display.html">cv_analysis.utils.display module</a></li>
<li class="toctree-l2"><a class="reference internal" href="cv_analysis.utils.draw.html">cv_analysis.utils.draw module</a></li>
<li class="toctree-l2"><a class="reference internal" href="cv_analysis.utils.filters.html">cv_analysis.utils.filters module</a></li>
<li class="toctree-l2"><a class="reference internal" href="cv_analysis.utils.image_extraction.html">cv_analysis.utils.image_extraction module</a></li>
<li class="toctree-l2"><a class="reference internal" href="cv_analysis.utils.open_pdf.html">cv_analysis.utils.open_pdf module</a></li>
<li class="toctree-l2"><a class="reference internal" href="cv_analysis.utils.postprocessing.html">cv_analysis.utils.postprocessing module</a></li>
<li class="toctree-l2"><a class="reference internal" href="cv_analysis.utils.preprocessing.html">cv_analysis.utils.preprocessing module</a></li>
<li class="toctree-l2"><a class="reference internal" href="cv_analysis.utils.structures.html">cv_analysis.utils.structures module</a></li>
<li class="toctree-l2"><a class="reference internal" href="cv_analysis.utils.test_metrics.html">cv_analysis.utils.test_metrics module</a></li>
<li class="toctree-l2"><a class="reference internal" href="cv_analysis.utils.utils.html">cv_analysis.utils.utils module</a></li>
<li class="toctree-l2"><a class="reference internal" href="cv_analysis.utils.visual_logging.html">cv_analysis.utils.visual_logging module</a></li>
</ul>
</li>
</ul>
<ul class="nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="cv_analysis.config.html">cv_analysis.config module</a></li>
<li class="toctree-l1"><a class="reference internal" href="cv_analysis.layout_parsing.html">cv_analysis.layout_parsing module</a></li>
<li class="toctree-l1"><a class="reference internal" href="cv_analysis.locations.html">cv_analysis.locations module</a></li>
<li class="toctree-l1"><a class="reference internal" href="cv_analysis.redaction_detection.html">cv_analysis.redaction_detection module</a></li>
<li class="toctree-l1"><a class="reference internal" href="cv_analysis.table_inference.html">cv_analysis.table_inference module</a></li>
<li class="toctree-l1"><a class="reference internal" href="cv_analysis.table_parsing.html">cv_analysis.table_parsing module</a></li>
</ul>
</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"><a href="cv_analysis.html" class="nav-link">cv_analysis package</a></li>
<li class="breadcrumb-item"><a href="cv_analysis.figure_detection.html" class="nav-link">cv_analysis.figure_detection package</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="module-cv_analysis.figure_detection.text">
<span id="cv-analysis-figure-detection-text-module"></span><h1>cv_analysis.figure_detection.text module<a class="headerlink" href="#module-cv_analysis.figure_detection.text" title="Link to this heading">#</a></h1>
<dl class="py function">
<dt class="sig sig-object py" id="cv_analysis.figure_detection.text.apply_threshold_to_image">
<span class="sig-prename descclassname"><span class="pre">cv_analysis.figure_detection.text.</span></span><span class="sig-name descname"><span class="pre">apply_threshold_to_image</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">image</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#cv_analysis.figure_detection.text.apply_threshold_to_image" title="Link to this definition">#</a></dt>
<dd><p>Converts an image to black and white.</p>
</dd></dl>
<dl class="py function">
<dt class="sig sig-object py" id="cv_analysis.figure_detection.text.draw_bboxes">
<span class="sig-prename descclassname"><span class="pre">cv_analysis.figure_detection.text.</span></span><span class="sig-name descname"><span class="pre">draw_bboxes</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">image</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bboxes</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#cv_analysis.figure_detection.text.draw_bboxes" title="Link to this definition">#</a></dt>
<dd></dd></dl>
<dl class="py function">
<dt class="sig sig-object py" id="cv_analysis.figure_detection.text.is_likely_primary_text_segment">
<span class="sig-prename descclassname"><span class="pre">cv_analysis.figure_detection.text.</span></span><span class="sig-name descname"><span class="pre">is_likely_primary_text_segment</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">cnt</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#cv_analysis.figure_detection.text.is_likely_primary_text_segment" title="Link to this definition">#</a></dt>
<dd></dd></dl>
<dl class="py function">
<dt class="sig sig-object py" id="cv_analysis.figure_detection.text.remove_primary_text_regions">
<span class="sig-prename descclassname"><span class="pre">cv_analysis.figure_detection.text.</span></span><span class="sig-name descname"><span class="pre">remove_primary_text_regions</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">image</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#cv_analysis.figure_detection.text.remove_primary_text_regions" title="Link to this definition">#</a></dt>
<dd><p>Removes regions of primary text, meaning no figure descriptions for example, but main text body paragraphs.</p>
<dl class="field-list simple">
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
<dd class="field-odd"><p><strong>image</strong> Image to remove primary text from.</p>
</dd>
<dt class="field-even">Returns<span class="colon">:</span></dt>
<dd class="field-even"><p>Image with primary text removed.</p>
</dd>
</dl>
<p class="rubric">References</p>
<p><a class="reference external" href="https://stackoverflow.com/questions/58349726/opencv-how-to-remove-text-from-background">https://stackoverflow.com/questions/58349726/opencv-how-to-remove-text-from-background</a></p>
</dd></dl>
</section>
</article>
<footer class="prev-next-footer">
<div class="prev-next-area">
<a class="left-prev"
href="cv_analysis.figure_detection.figures.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">cv_analysis.figure_detection.figures module</p>
</div>
</a>
<a class="right-next"
href="cv_analysis.server.html"
title="next page">
<div class="prev-next-info">
<p class="prev-next-subtitle">next</p>
<p class="prev-next-title">cv_analysis.server 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="#cv_analysis.figure_detection.text.apply_threshold_to_image"><code class="docutils literal notranslate"><span class="pre">apply_threshold_to_image()</span></code></a></li>
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#cv_analysis.figure_detection.text.draw_bboxes"><code class="docutils literal notranslate"><span class="pre">draw_bboxes()</span></code></a></li>
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#cv_analysis.figure_detection.text.is_likely_primary_text_segment"><code class="docutils literal notranslate"><span class="pre">is_likely_primary_text_segment()</span></code></a></li>
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#cv_analysis.figure_detection.text.remove_primary_text_regions"><code class="docutils literal notranslate"><span class="pre">remove_primary_text_regions()</span></code></a></li>
</ul>
</nav></div>
<div class="sidebar-secondary-item">
<div class="tocsection sourcelink">
<a href="../_sources/modules/cv_analysis.figure_detection.text.rst.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>