<?xml version="1.0" encoding="utf-8"?>
<feed xmlns="http://www.w3.org/2005/Atom"><title>Michael Jay Lissner</title><link href="https://michaeljaylissner.com/" rel="alternate"></link><link href="https://michaeljaylissner.com/feeds/tag/typography" rel="self"></link><id>https://michaeljaylissner.com/</id><updated>2012-01-27T22:15:58-08:00</updated><entry><title>The Winning Font in Court Opinions</title><link href="https://michaeljaylissner.com/posts/2012/01/27/and-the-winning-font-in-court-documents-is/" rel="alternate"></link><updated>2012-01-27T22:15:58-08:00</updated><author><name>Mike Lissner</name></author><id>tag:michaeljaylissner.com,2012-01-27:posts/2012/01/27/and-the-winning-font-in-court-documents-is/</id><summary type="html">&lt;p&gt;At CourtListener, we&amp;#8217;re developing a new system to convert scanned court 
documents to text. As part of our development we&amp;#8217;ve analyzed more than 1,000 
court opinions to determine what fonts courts are&amp;nbsp;using. &lt;/p&gt;
&lt;p&gt;Now that we have this information, our next step is to create training data 
for &lt;a href="http://code.google.com/p/tesseract-ocr/"&gt;our &lt;span class="caps"&gt;OCR&lt;/span&gt; system&lt;/a&gt; so that it specializes in these fonts, 
but for now we&amp;#8217;ve attached &lt;a href="https://michaeljaylissner.com/archive/court-font-analysis/font-analysis.ods"&gt;a spreadsheet&lt;/a&gt; with our findings, 
and &lt;a href="https://michaeljaylissner.com/archive/court-font-analysis/extract_font_metadata_from_files.py"&gt;a script that can be used by others&lt;/a&gt; to extract font metadata 
from&amp;nbsp;PDFs.&lt;/p&gt;
&lt;p&gt;Unsurprisingly, the top font &amp;mdash; drumroll please &amp;mdash; is Times New&amp;nbsp;Roman. &lt;/p&gt;
&lt;table&gt;
    &lt;tr&gt;
        &lt;th&gt;Font&lt;/td&gt;
        &lt;th&gt;Regular&lt;/td&gt;
        &lt;th&gt;Bold
        &lt;th&gt;Italic
        &lt;th&gt;Bold Italic
        &lt;th&gt;Total
    &lt;/tr&gt;
    &lt;tr&gt;
        &lt;td&gt;Times
        &lt;td&gt;1454
        &lt;td&gt;953
        &lt;td&gt;867
        &lt;td&gt;47
        &lt;td&gt;&lt;strong&gt;3321&lt;/strong&gt;
    &lt;/tr&gt;
    &lt;tr&gt;
        &lt;td&gt;Courier
        &lt;td&gt;369
        &lt;td&gt;333
        &lt;td&gt;209
        &lt;td&gt;131
        &lt;td&gt;&lt;strong&gt;1042&lt;/strong&gt;
    &lt;/tr&gt;
    &lt;tr&gt;
        &lt;td&gt;Arial
        &lt;td&gt;364
        &lt;td&gt;39
        &lt;td&gt;11
        &lt;td&gt;41
        &lt;td&gt;&lt;strong&gt;455&lt;/strong&gt;
    &lt;/tr&gt;
    &lt;tr&gt;
        &lt;td&gt;Symbol
        &lt;td&gt;212
        &lt;td&gt;0
        &lt;td&gt;0
        &lt;td&gt;0
        &lt;td&gt;&lt;strong&gt;212&lt;/strong&gt;
    &lt;/tr&gt;
    &lt;tr&gt;
        &lt;td&gt;Helvetica
        &lt;td&gt;24
        &lt;td&gt;161
        &lt;td&gt;2
        &lt;td&gt;2
        &lt;td&gt;&lt;strong&gt;189&lt;/strong&gt;
    &lt;/tr&gt;
    &lt;tr&gt;
        &lt;td&gt;Century Schoolbook
        &lt;td&gt;58
        &lt;td&gt;54
        &lt;td&gt;52
        &lt;td&gt;9
        &lt;td&gt;&lt;strong&gt;173&lt;/strong&gt;
    &lt;/tr&gt;
    &lt;tr&gt;
        &lt;td&gt;Garamond
        &lt;td&gt;44
        &lt;td&gt;42
        &lt;td&gt;41
        &lt;td&gt;0
        &lt;td&gt;&lt;strong&gt;127&lt;/strong&gt;
    &lt;/tr&gt;
    &lt;tr&gt;
        &lt;td&gt;Palatino Linotype
        &lt;td&gt;36
        &lt;td&gt;24
        &lt;td&gt;24
        &lt;td&gt;1
        &lt;td&gt;&lt;strong&gt;85&lt;/strong&gt;
    &lt;/tr&gt;
    &lt;tr&gt;
        &lt;td&gt;Old English
        &lt;td&gt;42
        &lt;td&gt;0
        &lt;td&gt;0
        &lt;td&gt;0
        &lt;td&gt;&lt;strong&gt;42&lt;/strong&gt;
    &lt;/tr&gt;
    &lt;tr&gt;
        &lt;td&gt;Lincoln
        &lt;td&gt;27
        &lt;td&gt;0
        &lt;td&gt;0
        &lt;td&gt;0
        &lt;td&gt;&lt;strong&gt;27&lt;/strong&gt;
    &lt;/tr&gt;
&lt;/table&gt;</summary><category term="typography"></category><category term="tesseract"></category><category term="Python"></category><category term="ocr"></category><category term="font"></category><category term="CourtListener"></category></entry></feed>