forked from docs/doc-exports
Su, Xiaomeng
2d6f6839ae
Reviewed-by: Pruthi, Vineet <vineet.pruthi@t-systems.com> Co-authored-by: Su, Xiaomeng <suxiaomeng1@huawei.com> Co-committed-by: Su, Xiaomeng <suxiaomeng1@huawei.com>
13 lines
3.9 KiB
HTML
13 lines
3.9 KiB
HTML
<a name="ocr_01_0006"></a><a name="ocr_01_0006"></a>
|
|
|
|
<h1 class="topictitle1">Notes and Constraints</h1>
|
|
<div id="body0000001751918129"><p id="ocr_01_0006__p552814518411">There are various factors, such as technology and cost, that limit the performance of OCR services. There are system-wide constraints that affect all services, as well as service-level constraints that affect individual services only.</p>
|
|
<div class="section" id="ocr_01_0006__section1835213451444"><h4 class="sectiontitle">General Table OCR</h4><ul id="ocr_01_0006__ul45289459414"><li id="ocr_01_0006__li15528124513413">Only images in PNG, JPG, JPEG, BMP, or TIFF format can be recognized.</li><li id="ocr_01_0006__li052816457413">No side of the image can be smaller than 15 or larger than 8,192 pixels.</li><li id="ocr_01_0006__li252864513412">The area to be recognized must occupy more than 80% of the image. When scanning a table, ensure that the entire table and its surrounding area are included in the image.</li><li id="ocr_01_0006__li1052816459412">An image can be rotated to any angle.</li><li id="ocr_01_0006__li25285450419">Text in images with complex backgrounds (such as outdoor scenery or anti-counterfeit watermarks) or distorted table lines cannot be recognized.</li><li id="ocr_01_0006__li75282452041">English and Chinese are both supported, but the support for traditional Chinese characters is limited.</li></ul>
|
|
</div>
|
|
<div class="section" id="ocr_01_0006__section1735714458418"><h4 class="sectiontitle">General Text OCR</h4><ul id="ocr_01_0006__ul1352874516418"><li id="ocr_01_0006__li352815456411">Only images in PNG, JPG, JPEG, BMP, GIF, TIFF, WebP, PCX, ICO, PSD, or PDF format can be recognized.</li><li id="ocr_01_0006__li17528164515418">No side of the image can be smaller than 15 or larger than 8,192 pixels.</li><li id="ocr_01_0006__li352814451247">The area to be recognized must occupy more than 80% of the image. When scanning a table, ensure that all text and its surrounding area are included in the image.</li><li id="ocr_01_0006__li452812456417">An image can be rotated to any angle.</li><li id="ocr_01_0006__li185284451744">Text in images with complex backgrounds (such as outdoor scenery or anti-counterfeit watermarks) or distorted text cannot be recognized.</li><li id="ocr_01_0006__li175288454412">Supported languages: Chinese, English, some traditional Chinese, Malay, Ukrainian, Hindi, Russian, Vietnamese, Indonesian, Thai, Arabic, German, Latin, French, Italian, Spanish, Portuguese, Romanian, Polish Amharic, Japanese, Korean, Turkish, Norwegian, Danish, Swedish, Khmer, and Hebrew.</li></ul>
|
|
</div>
|
|
<div class="section" id="ocr_01_0006__section12870144482912"><h4 class="sectiontitle">Smart Document Recognizer</h4><ul id="ocr_01_0006__ul7622153124420"><li id="ocr_01_0006__li86221318446">English and Chinese are both supported, but the support for traditional Chinese characters is limited.</li><li id="ocr_01_0006__li136239319446">Only images in PNG, JPG, JPEG, BMP, GIF, TIFF, WebP, PCX, ICO or PSD format and PDF files can be recognized. PDF files can only be recognized one page at a time, but you can use the <strong id="ocr_01_0006__b154021851778">pdf_page_number</strong> parameter to specify which page you want to recognize.</li><li id="ocr_01_0006__li11623193134410">No side of the image can be smaller than 15 or larger than 8,192 pixels.</li><li id="ocr_01_0006__li1362313104411">The area to be recognized must occupy more than 80% of the image. When scanning a table, ensure that all text and its surrounding area are included in the image.</li><li id="ocr_01_0006__li15623133117442">An image can be rotated to any angle.</li><li id="ocr_01_0006__li1862313316443">For more accurate recognition results, the number of characters on a single page must be limited to 1,800 or less.</li><li id="ocr_01_0006__li46238319446">Text in images with complex backgrounds (such as outdoor scenery or anti-counterfeit watermarks) or distorted text cannot be analyzed.</li></ul>
|
|
</div>
|
|
</div>
|
|
|