View a markdown version of this page

Set Quotas in Amazon Textract - Amazon Textract

Set Quotas in Amazon Textract

The following is a list of set quotas in Amazon Textract, which cannot be changed. For information about limitations in default quotas you can change, see the section Default Quotas in Amazon Textract.

Limit Description

Accepted File Formats

Operations support JPEG, PNG, PDF, and TIFF files. (JPEG 2000-encoded images within PDFs are supported). Textract does not support XFA based PDFs.

File Size and Page Count Limits

For synchronous operations, JPEG, PNG, PDF, and TIFF files have a limit of 10 MB in memory. PDF and TIFF files also have a limit of 1 page. For asynchronous operations, JPEG and PNG files have a limit of 10 MB in memory. PDF and TIFF files have a limit of 500 MB in memory and a limit of 3,000 pages.

PDF Specific Limits

The maximum height and width is 40 inches and 9000 points. PDFs cannot be password protected. PDFs can contain JPEG 2000 formatted images.

Document Rotation and Image Size

Amazon Textract supports all in-plane document rotations, for example 45-degree in-plane rotation.

Amazon Textract supports images with a resolution less than or equal to 10000 pixels on all sides.

Query Specific Limits

Amazon Textract supports up to 15 queries per page for synchronous operations and up to 30 queries per page for asynchronous operations.

Text Alignment

Text can be text aligned horizontally within the document. Horizontally arrayed text can be read regardless of the degree of rotation of a document.

Languages

Amazon Textract supports more than 40 languages including: Albanian, Arabic, Basque, Belarusian, Bosnian, Bulgarian, Chinese (Simplified and Traditional), Croatian, Czech, Danish, Dutch, English, Estonian, Finnish, French, German, Hebrew, Hindi, Hungarian, Icelandic, Italian, Japanese, Korean, Latvian, Lithuanian, Luxembourgish, Norwegian, Polish, Portuguese, Romanian, Russian, Serbian Cyrillic, Serbian Latin, Slovak, Slovenian, Spanish, Swedish, Turkish, Turkmen, and Ukrainian.

StartDocumentAnalysis (Table, Signatures, Layout), AnalyzeDocument (Table, Signatures, Layout), StartDocumentTextDetection, and GetDocumentTextDetection APIs support all languages. AnalyzeDocument (Forms), StartDocumentAnalysis (Forms), and GetDocumentAnalysis APIs are limited to English, Spanish, Italian, Portuguese, French, and German. All other APIs are limited to English.

Character Size

The minimum height for text to be detected is 15 pixels. At 150 DPI, this would be the same as 8 point font.

Character Type

Amazon Textract supports both handwritten and printed character recognition. Handwritten character recognition is only supported in English.

Characters

Amazon Textract detects the following characters:

  • a-z

  • A-Z

  • 0-9

  • ä Ä ö Ö ü Ü ç Ç é É â Â ê Ê î Î ô Ô û Û à À è È ù Ù ë Ë ï Ï ü Ü á Á é É í Í ó Ó ú Ú ü Ü ñ Ñ ì Ì ò Ò ã Ã õ Õ

  • ! " # $ % ' & ( ) * + , - . / : ; = ? @ [ \ ] ^ _ ` { | } ~ > < ° € £ ¥ ₹ ß ẞ ¿ ¡ € £ ¥ ₹ ø Ø œ Œ © ® ™ § ¹ ² ³ '
AnalyzeID Specific Limits AnalyzeID only supports US passports, and US driver's licenses.
Adapter Specific Limits

  • Accepted dataset configuration for adapter training - Training: 5-2500, Test: 5-1000,

  • Training/testing file format and size: JPG, PNG, PDF, TIFF.

  • Maximum size of training/testing file is 10MB.

  • Maximum size of annotation/pre-labeling file is 25MB.

  • Maximum length of pre-labeling file array is 15.

  • Max query response length - 128 characters

  • Max number of queries per page - 30