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.
+
General Table OCR
- Only images in PNG, JPG, JPEG, BMP, or TIFF format can be recognized.
- No side of the image can be smaller than 15 or larger than 8,192 pixels.
- 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.
- An image can be rotated to any angle.
- Text in images with complex backgrounds (such as outdoor scenery or anti-counterfeit watermarks) or distorted table lines cannot be recognized.
- English and Chinese are both supported, but the support for traditional Chinese characters is limited.
-
General Text OCR
- Only images in PNG, JPG, JPEG, BMP, GIF, TIFF, WebP, PCX, ICO, or PSD format can be recognized.
- No side of the image can be smaller than 15 or larger than 8,192 pixels.
- 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.
- An image can be rotated to any angle.
- Text in images with complex backgrounds (such as outdoor scenery or anti-counterfeit watermarks) or distorted text cannot be recognized.
- 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, and Swedish.
+
General Text OCR
- Only images in PNG, JPG, JPEG, BMP, GIF, TIFF, WebP, PCX, ICO, PSD, or PDF format can be recognized.
- No side of the image can be smaller than 15 or larger than 8,192 pixels.
- 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.
- An image can be rotated to any angle.
- Text in images with complex backgrounds (such as outdoor scenery or anti-counterfeit watermarks) or distorted text cannot be recognized.
- 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.
+
+
Smart Document Recognizer
- English and Chinese are both supported, but the support for traditional Chinese characters is limited.
- 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 pdf_page_number parameter to specify which page you want to recognize.
- No side of the image can be smaller than 15 or larger than 8,192 pixels.
- 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.
- An image can be rotated to any angle.
- For more accurate recognition results, the number of characters on a single page must be limited to 1,800 or less.
- Text in images with complex backgrounds (such as outdoor scenery or anti-counterfeit watermarks) or distorted text cannot be analyzed.
diff --git a/docs/ocr/umn/ocr_01_0028.html b/docs/ocr/umn/ocr_01_0028.html
index eabdee5d5..b9766d86a 100644
--- a/docs/ocr/umn/ocr_01_0028.html
+++ b/docs/ocr/umn/ocr_01_0028.html
@@ -3,9 +3,12 @@
Functions
Function Description
- General Table
Detects and extracts text and their row and column locations from images of tables in various formats, as well as the text areas outside tables. It is used to store information on documents and reports as structured data.
- General Text
Detects and extracts text and their locations from images and converts them into structured data.
+ - Smart Document Recognizer
Recognizes text, analyzes layout, extracts key-value pairs, identifies tables in various formatted documents such as certificates, receipts, and forms, and converts the results into a structured JSON format.
Use Cases
- Digitalizing paper documents
Automatically detects and extracts text, signatures, and seals from document images and converts them into structured data for faster review.
+ Expense review
+Automatically recognizes and digitally inputs employees' invoices, reducing labor costs and enhancing efficiency.
diff --git a/docs/ocr/umn/ocr_01_0078.html b/docs/ocr/umn/ocr_01_0078.html
index 3722ee9c7..c03dba690 100644
--- a/docs/ocr/umn/ocr_01_0078.html
+++ b/docs/ocr/umn/ocr_01_0078.html
@@ -2,7 +2,7 @@
Is It Possible to Call the OCR Service From a Different Region Than OBS Resources?
Cross-region OBS is not supported, and the OBS region must match the region of the service being called.
-
For OBS resources with public read authorization, they can be accessed over the Internet and can support cross-region calls. Although this is convenient, there is a risk of sensitive information leakage, such as personal private data. It is recommended that you use OCR and OBS services in the same region to avoid this risk.
+
For OBS resources with public read authorization, they can be accessed over the Internet and can support cross-region calls. Although this is convenient, there is a risk of sensitive information leakage, such as personal private data. It is recommended that you use OCR and OBS services in the same region to avoid this risk.
diff --git a/docs/ocr/umn/ocr_01_0089.html b/docs/ocr/umn/ocr_01_0089.html
index 4b2d67c8b..9beed9d2b 100644
--- a/docs/ocr/umn/ocr_01_0089.html
+++ b/docs/ocr/umn/ocr_01_0089.html
@@ -3,7 +3,7 @@
How Do I Handle the Error APIG.0307?
If error message "The token must be updated." and error code "APIG.0307" are displayed when you call an OCR API, the token has expired and needs to be updated.
Perform the following steps to rectify the fault:
-
- The validity period of a token is 24 hours. Obtain the token again to call the API.
- Check whether the endpoint in the API URL is correct. Services deployed in different regions cannot be called across regions. If APIs in different regions are called, the token is invalid and error code APIG.0307 is displayed.
+
- The validity period of a token is 24 hours. Obtain the token again to call the API.
- Check whether the endpoint in the API URL is correct. Services deployed in different regions cannot be called across regions. If APIs in different regions are called, the token is invalid and error code APIG.0307 is displayed.
diff --git a/docs/ocr/umn/ocr_01_0153.html b/docs/ocr/umn/ocr_01_0153.html
index 651375fa8..e47ef4fdc 100644
--- a/docs/ocr/umn/ocr_01_0153.html
+++ b/docs/ocr/umn/ocr_01_0153.html
@@ -7,7 +7,7 @@
Step 2: Configuring the Environment
Step 3: Using a Token for Authentication
Step 4: Calling the Service
-
Step 1: Subscribing to a Service
- Log in to the OCR management console.
Select a region based on service requirements. For details about the region where each service is deployed, see Regions and Endpoints.
+Step 1: Subscribing to a Service
- Log in to the OCR management console.
Select a region based on service requirements. For details about the region where each service is deployed, see Regions and Endpoints.
- On the page displayed, select and subscribe to your desired APIs.
For this example, subscribe to the General Text OCR API.