<span class="typ">Page</span><span class="pln"> segmentation modes</span><span class="pun">:</span>
<span class="lit">0</span> <span class="typ">Orientation</span> <span class="kwd">and</span><span class="pln"> script detection </span><span class="pun">(</span><span class="pln">OSD</span><span class="pun">)</span><span class="pln"> only</span><span class="pun">.</span>
<span class="lit">1</span> <span class="typ">Automatic</span><span class="pln"> page segmentation </span><span class="kwd">with</span><span class="pln"> OSD</span><span class="pun">.</span>
<span class="lit">2</span> <span class="typ">Automatic</span><span class="pln"> page segmentation</span><span class="pun">,</span><span class="pln"> but no OSD</span><span class="pun">,</span> <span class="kwd">or</span><span class="pln"> OCR</span><span class="pun">.</span>
<span class="lit">3</span> <span class="typ">Fully</span><span class="pln"> automatic page segmentation</span><span class="pun">,</span><span class="pln"> but no OSD</span><span class="pun">.</span> <span class="pun">(</span><span class="typ">Default</span><span class="pun">)</span>
<span class="lit">4</span> <span class="typ">Assume</span><span class="pln"> a single column of text of variable sizes</span><span class="pun">.</span>
<span class="lit">5</span> <span class="typ">Assume</span><span class="pln"> a single uniform block of vertically aligned text</span><span class="pun">.</span>
<span class="lit">6</span> <span class="typ">Assume</span><span class="pln"> a single uniform block of text</span><span class="pun">.</span>
<span class="lit">7</span> <span class="typ">Treat</span><span class="pln"> the image </span><span class="kwd">as</span><span class="pln"> a single text line</span><span class="pun">.</span>
<span class="lit">8</span> <span class="typ">Treat</span><span class="pln"> the image </span><span class="kwd">as</span><span class="pln"> a single word</span><span class="pun">.</span>
<span class="lit">9</span> <span class="typ">Treat</span><span class="pln"> the image </span><span class="kwd">as</span><span class="pln"> a single word </span><span class="kwd">in</span><span class="pln"> a circle</span><span class="pun">.</span>
<span class="lit">10</span> <span class="typ">Treat</span><span class="pln"> the image </span><span class="kwd">as</span><span class="pln"> a single character</span><span class="pun">.</span>
<span class="lit">11</span> <span class="typ">Sparse</span><span class="pln"> text</span><span class="pun">.</span> <span class="typ">Find</span> <span class="kwd">as</span><span class="pln"> much text </span><span class="kwd">as</span><span class="pln"> possible </span><span class="kwd">in</span><span class="pln"> no particular order</span><span class="pun">.</span>
<span class="lit">12</span> <span class="typ">Sparse</span><span class="pln"> text </span><span class="kwd">with</span><span class="pln"> OSD</span><span class="pun">.</span>
<span class="lit">13</span> <span class="typ">Raw</span><span class="pln"> line</span><span class="pun">.</span> <span class="typ">Treat</span><span class="pln"> the image </span><span class="kwd">as</span><span class="pln"> a single text line</span><span class="pun">,</span><span class="pln">
bypassing hacks that are </span><span class="typ">Tesseract</span><span class="pun">-</span><span class="pln">specific</span><span class="pun">.</span>
References
https://stackoverflow.com/questions/44619077/pytesseract-ocr-multiple-config-options