From 13aa021d1d3de8ac0833add202f2c7004f68f245 Mon Sep 17 00:00:00 2001 From: "Su, Xiaomeng" Date: Wed, 26 Mar 2025 09:05:18 +0000 Subject: [PATCH] ocr_api_20250311 Reviewed-by: Pruthi, Vineet Co-authored-by: Su, Xiaomeng Co-committed-by: Su, Xiaomeng --- docs/ocr/api-ref/ALL_META.TXT.json | 54 +- docs/ocr/api-ref/CLASS.TXT.json | 40 +- docs/ocr/api-ref/ocr_03_0014.html | 2 + docs/ocr/api-ref/ocr_03_0029.html | 10 + docs/ocr/api-ref/ocr_03_0031.html | 2 +- docs/ocr/api-ref/ocr_03_0042.html | 21 +- docs/ocr/api-ref/ocr_03_0043.html | 2 +- docs/ocr/api-ref/ocr_03_0047.html | 5 + docs/ocr/api-ref/ocr_03_0060.html | 2 +- docs/ocr/api-ref/ocr_03_0062.html | 2 +- docs/ocr/api-ref/ocr_03_0063.html | 6 +- docs/ocr/api-ref/ocr_03_0161.html | 884 +++++++++++++++++++++++++++++ docs/ocr/api-ref/ocr_03_0162.html | 200 +++++++ 13 files changed, 1198 insertions(+), 32 deletions(-) create mode 100644 docs/ocr/api-ref/ocr_03_0161.html create mode 100644 docs/ocr/api-ref/ocr_03_0162.html diff --git a/docs/ocr/api-ref/ALL_META.TXT.json b/docs/ocr/api-ref/ALL_META.TXT.json index dee60c76b..7f05c13fc 100644 --- a/docs/ocr/api-ref/ALL_META.TXT.json +++ b/docs/ocr/api-ref/ALL_META.TXT.json @@ -61,7 +61,7 @@ "node_id":"ocr_03_0062.xml", "product_code":"ocr", "code":"4", - "des":"An endpoint is the request address used to call an API. Different services have different endpoints for different regions. You can query all service endpoints at Regions ", + "des":"An endpoint is the request address for calling an API. Endpoints vary depending on services and regions. For more information, see Regions and Endpoints.", "doc_type":"api", "kw":"Endpoint,Before You Start,API Reference", "search_title":"", @@ -81,7 +81,7 @@ "code":"5", "des":"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 mus", "doc_type":"api", - "kw":"Constraints and Limitations,Before You Start,API Reference", + "kw":"Notes and Constraints,Before You Start,API Reference", "search_title":"", "metedata":[ { @@ -89,7 +89,7 @@ "prodname":"ocr" } ], - "title":"Constraints and Limitations", + "title":"Notes and Constraints", "githuburl":"" }, { @@ -151,7 +151,7 @@ "node_id":"ocr_03_0043.xml", "product_code":"ocr", "code":"9", - "des":"Log in to the OCR management console.Select a region based on your business needs. For details about the regions where services are deployed, see Regions and Endpoints.Se", + "des":"Log in to the OCR management console.Select a region based on service requirements. For details about the regions where services are deployed, see Regions and Endpoints.S", "doc_type":"api", "kw":"Subscribing to an OCR Service,API Calling,API Reference", "search_title":"", @@ -272,11 +272,47 @@ "title":"General Table", "githuburl":"" }, + { + "uri":"ocr_03_0161.html", + "node_id":"ocr_03_0161.xml", + "product_code":"ocr", + "code":"16", + "des":"This API recognizes text, analyzes layout, extracts key-value pairs, identifies tables in various formatted documents such as certificates, receipts, and forms, and conve", + "doc_type":"api", + "kw":"Smart Document Recognizer,API,API Reference", + "search_title":"", + "metedata":[ + { + "documenttype":"api", + "prodname":"ocr" + } + ], + "title":"Smart Document Recognizer", + "githuburl":"" + }, + { + "uri":"ocr_03_0162.html", + "node_id":"ocr_03_0162.xml", + "product_code":"ocr", + "code":"17", + "des":"This section describes how you can use Identity and Access Management (IAM) for fine-grained permissions management of your OCR resources. If your account does not need i", + "doc_type":"api", + "kw":"Permissions Policies and Supported Actions,API Reference", + "search_title":"", + "metedata":[ + { + "documenttype":"api", + "prodname":"ocr" + } + ], + "title":"Permissions Policies and Supported Actions", + "githuburl":"" + }, { "uri":"ocr_03_0048.html", "node_id":"ocr_03_0048.xml", "product_code":"ocr", - "code":"16", + "code":"18", "des":"HUAWEI CLOUD Help Center presents technical documents to help you quickly get started with HUAWEI CLOUD services. The technical documents include Service Overview, Price Details, Purchase Guide, User Guide, API Reference, Best Practices, FAQs, and Videos.", "doc_type":"api", "kw":"Common Parameters", @@ -294,7 +330,7 @@ "uri":"ocr_03_0090.html", "node_id":"ocr_03_0090.xml", "product_code":"ocr", - "code":"17", + "code":"19", "des":"An HTTP status code consists of three digits, which is classified into five categories: 1xx: related information; 2xx: operation successful; 3xx: redirection; 4xx: client", "doc_type":"api", "kw":"Status Codes,Common Parameters,API Reference", @@ -312,7 +348,7 @@ "uri":"ocr_03_0028.html", "node_id":"ocr_03_0028.xml", "product_code":"ocr", - "code":"18", + "code":"20", "des":"No data will be returned if an API fails to be called. You can locate the error cause based on the error code of each API. When an API call fails, HTTPS status code 4xx o", "doc_type":"api", "kw":"Error Codes,Common Parameters,API Reference", @@ -330,7 +366,7 @@ "uri":"ocr_03_0130.html", "node_id":"ocr_03_0130.xml", "product_code":"ocr", - "code":"19", + "code":"21", "des":"A project ID or project name is required in some API requests. You need to obtain the project ID and name before calling an API.Log in to the management console.In the up", "doc_type":"api", "kw":"Obtaining the Project ID,Common Parameters,API Reference", @@ -348,7 +384,7 @@ "uri":"ocr_03_0029.html", "node_id":"ocr_03_0029.xml", "product_code":"ocr", - "code":"20", + "code":"22", "des":"HUAWEI CLOUD Help Center presents technical documents to help you quickly get started with HUAWEI CLOUD services. The technical documents include Service Overview, Price Details, Purchase Guide, User Guide, API Reference, Best Practices, FAQs, and Videos.", "doc_type":"api", "kw":"Change History,API Reference", diff --git a/docs/ocr/api-ref/CLASS.TXT.json b/docs/ocr/api-ref/CLASS.TXT.json index 19e30760a..957d2f681 100644 --- a/docs/ocr/api-ref/CLASS.TXT.json +++ b/docs/ocr/api-ref/CLASS.TXT.json @@ -27,7 +27,7 @@ "code":"3" }, { - "desc":"An endpoint is the request address used to call an API. Different services have different endpoints for different regions. You can query all service endpoints at Regions ", + "desc":"An endpoint is the request address for calling an API. Endpoints vary depending on services and regions. For more information, see Regions and Endpoints.", "product_code":"ocr", "title":"Endpoint", "uri":"ocr_03_0062.html", @@ -38,7 +38,7 @@ { "desc":"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 mus", "product_code":"ocr", - "title":"Constraints and Limitations", + "title":"Notes and Constraints", "uri":"ocr_03_0063.html", "doc_type":"api", "p_code":"1", @@ -72,7 +72,7 @@ "code":"8" }, { - "desc":"Log in to the OCR management console.Select a region based on your business needs. For details about the regions where services are deployed, see Regions and Endpoints.Se", + "desc":"Log in to the OCR management console.Select a region based on service requirements. For details about the regions where services are deployed, see Regions and Endpoints.S", "product_code":"ocr", "title":"Subscribing to an OCR Service", "uri":"ocr_03_0043.html", @@ -134,6 +134,24 @@ "p_code":"13", "code":"15" }, + { + "desc":"This API recognizes text, analyzes layout, extracts key-value pairs, identifies tables in various formatted documents such as certificates, receipts, and forms, and conve", + "product_code":"ocr", + "title":"Smart Document Recognizer", + "uri":"ocr_03_0161.html", + "doc_type":"api", + "p_code":"13", + "code":"16" + }, + { + "desc":"This section describes how you can use Identity and Access Management (IAM) for fine-grained permissions management of your OCR resources. If your account does not need i", + "product_code":"ocr", + "title":"Permissions Policies and Supported Actions", + "uri":"ocr_03_0162.html", + "doc_type":"api", + "p_code":"", + "code":"17" + }, { "desc":"HUAWEI CLOUD Help Center presents technical documents to help you quickly get started with HUAWEI CLOUD services. The technical documents include Service Overview, Price Details, Purchase Guide, User Guide, API Reference, Best Practices, FAQs, and Videos.", "product_code":"ocr", @@ -141,7 +159,7 @@ "uri":"ocr_03_0048.html", "doc_type":"api", "p_code":"", - "code":"16" + "code":"18" }, { "desc":"An HTTP status code consists of three digits, which is classified into five categories: 1xx: related information; 2xx: operation successful; 3xx: redirection; 4xx: client", @@ -149,8 +167,8 @@ "title":"Status Codes", "uri":"ocr_03_0090.html", "doc_type":"api", - "p_code":"16", - "code":"17" + "p_code":"18", + "code":"19" }, { "desc":"No data will be returned if an API fails to be called. You can locate the error cause based on the error code of each API. When an API call fails, HTTPS status code 4xx o", @@ -158,8 +176,8 @@ "title":"Error Codes", "uri":"ocr_03_0028.html", "doc_type":"api", - "p_code":"16", - "code":"18" + "p_code":"18", + "code":"20" }, { "desc":"A project ID or project name is required in some API requests. You need to obtain the project ID and name before calling an API.Log in to the management console.In the up", @@ -167,8 +185,8 @@ "title":"Obtaining the Project ID", "uri":"ocr_03_0130.html", "doc_type":"api", - "p_code":"16", - "code":"19" + "p_code":"18", + "code":"21" }, { "desc":"HUAWEI CLOUD Help Center presents technical documents to help you quickly get started with HUAWEI CLOUD services. The technical documents include Service Overview, Price Details, Purchase Guide, User Guide, API Reference, Best Practices, FAQs, and Videos.", @@ -177,6 +195,6 @@ "uri":"ocr_03_0029.html", "doc_type":"api", "p_code":"", - "code":"20" + "code":"22" } ] \ No newline at end of file diff --git a/docs/ocr/api-ref/ocr_03_0014.html b/docs/ocr/api-ref/ocr_03_0014.html index 84d0b49d1..7805bca0a 100644 --- a/docs/ocr/api-ref/ocr_03_0014.html +++ b/docs/ocr/api-ref/ocr_03_0014.html @@ -8,6 +8,8 @@
  • General Table
    • +
  • Smart Document Recognizer
    +
    • diff --git a/docs/ocr/api-ref/ocr_03_0029.html b/docs/ocr/api-ref/ocr_03_0029.html index 418c3f635..0ed0d549f 100644 --- a/docs/ocr/api-ref/ocr_03_0029.html +++ b/docs/ocr/api-ref/ocr_03_0029.html @@ -13,6 +13,16 @@

    This issue is the first official release.

    +

    2024-11-15

    + +

    Changed the default value of the language parameter in the General Text OCR API. If this parameter is not specified, German and English are recognized by default.

    + + +

    2025-03-04

    + +
    • Enhanced the functions of General Text OCR to support the recognition of images in PNG, JPG, JPEG, BMP, GIF, TIFF, WebP, PCX, ICO, PSD, or PDF format. Added the recognition of Cambodian and Hebrew.
    • Added the Smart Document Recognizer API.
    + + diff --git a/docs/ocr/api-ref/ocr_03_0031.html b/docs/ocr/api-ref/ocr_03_0031.html index ec4daf771..3bd3444f7 100644 --- a/docs/ocr/api-ref/ocr_03_0031.html +++ b/docs/ocr/api-ref/ocr_03_0031.html @@ -96,7 +96,7 @@

    String

    -

    Set either this parameter or image. Image URL. Currently, the following URLs are supported:

    +

    Set either this parameter or image. The image file has a size limit of 10 MB. The following image URLs are currently supported:

    • Public HTTP/HTTPS URL
    • URL provided by OBS.
    NOTE:
    • The API response time depends on the image download time. If the image download takes a long time, the API call will fail.
    • Ensure that the storage service where the images to be detected reside is stable and reliable. OBS is recommended for storing image data.
    • The URL cannot contain Chinese characters. If Chinese characters exist, they must be encoded using UTF-8.
    diff --git a/docs/ocr/api-ref/ocr_03_0042.html b/docs/ocr/api-ref/ocr_03_0042.html index 7cbc8d632..650132b7d 100644 --- a/docs/ocr/api-ref/ocr_03_0042.html +++ b/docs/ocr/api-ref/ocr_03_0042.html @@ -3,7 +3,7 @@

    General Text

    Function

    This API detects and extracts text from images and converts the text and coordinates into JSON format. It can be used in various scenarios, such as scanned documents, electronic documents, books, receipts, and forms.

    -

    Constraints and Limitations

    • Only images in PNG, JPG, JPEG, BMP, GIF, 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 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.
    +

    Constraints and Limitations

    • 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.

    URI

    POST /v2/{project_id}/ocr/general-text

    @@ -96,7 +96,7 @@

    String

    -

    Set either this parameter or image. Image URL. Currently, the following URLs are supported:

    +

    Set either this parameter or image. The image file has a size limit of 10 MB. The following image URLs are currently supported:

    • Public HTTP/HTTPS URL
    • URL provided by OBS.
    NOTE:
    • The API response time depends on the image download time. If the image download takes a long time, the API call will fail.
    • Ensure that the storage service where the images to be detected reside is stable and reliable. OBS is recommended for storing image data.
    • The URL cannot contain Chinese characters. If Chinese characters exist, they must be encoded using UTF-8.
    @@ -142,8 +142,8 @@

    String

    -

    Language. If this parameter is not specified, Chinese and English will be used by default. The options are as follows:

    -
    • auto: automatic language classification
    • ms: Malay
    • uk: Ukrainian
    • hi: Hindi
    • ru: Russian
    • vi: Vietnamese
    • id: Indonesian
    • th: Thai
    • zh: Chinese and English
    • ar: Arabic
    • de: German
    • la: Latin
    • fr: French
    • it: Italian
    • es: Spanish
    • pt: Portuguese
    • ro: Romanian
    • pl: Polish
    • am: Amharic
    • ja: Japanese
    • ko: Korean
    • tr: Turkish
    • no: Norwegian
    • da: Danish
    • sv: Swedish
    +

    Language. If this parameter is not specified, German and English will be used by default. The options are:

    +
    • auto: automatic language classification
    • ms: Malay
    • uk: Ukrainian
    • hi: Hindi
    • ru: Russian
    • vi: Vietnamese
    • id: Indonesian
    • th: Thai
    • zh: Chinese and English
    • ar: Arabic
    • de: German
    • la: Latin
    • fr: French
    • it: Italian
    • es: Spanish
    • pt: Portuguese
    • ro: Romanian
    • pl: Polish
    • am: Amharic
    • ja: Japanese
    • ko: Korean
    • tr: Turkish
    • no: Norwegian
    • da: Danish
    • sv: Swedish
    • km: Khmer
    • he: Hebrew

    single_orientation_mode

    @@ -157,6 +157,15 @@

    If this parameter is not specified, false is used by default. In this case, the fields in the image are recognized as in multiple directions by default.

    +

    pdf_page_number

    + +

    No

    + +

    Integer

    + +

    Specify which page of the PDF to recognize. If this parameter is specified, the content on the specified page is identified. If not specified, the default is to recognize the first page.

    + +
    @@ -350,11 +359,11 @@ "direction" : 67.6506, "words_block_count" : 1, "words_block_list" : [ { - "words": "Word", + "words": "Word", "confidence" : 0.9999, "location" : [ [ 517, 447 ], [ 540, 504 ], [ 505, 518 ], [ 482, 461 ] ], "char_list" : [ { - "char": "Character", + "char": "Character", "char_location" : [ [ 517, 447 ], [ 530, 479 ], [ 495, 493 ], [ 482, 461 ] ], "char_confidence" : 0.9999 }, { diff --git a/docs/ocr/api-ref/ocr_03_0043.html b/docs/ocr/api-ref/ocr_03_0043.html index 5f3fce9f7..c94204063 100644 --- a/docs/ocr/api-ref/ocr_03_0043.html +++ b/docs/ocr/api-ref/ocr_03_0043.html @@ -1,7 +1,7 @@

    Subscribing to an OCR Service

    -
    1. Log in to the OCR management console.

      Select a region based on your business needs. For details about the regions where services are deployed, see Regions and Endpoints.

      +
      1. Log in to the OCR management console.

        Select a region based on service requirements. For details about the regions where services are deployed, see Regions and Endpoints.

      2. On the page displayed, select and subscribe to your desired APIs.
      diff --git a/docs/ocr/api-ref/ocr_03_0047.html b/docs/ocr/api-ref/ocr_03_0047.html index a6e18b592..140e67752 100644 --- a/docs/ocr/api-ref/ocr_03_0047.html +++ b/docs/ocr/api-ref/ocr_03_0047.html @@ -19,6 +19,11 @@

      This API detects and extracts text from images of general tables and converts the text into a structured format.

      +

      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.

      + +
      diff --git a/docs/ocr/api-ref/ocr_03_0060.html b/docs/ocr/api-ref/ocr_03_0060.html index 384e87af2..c0b4ae56c 100644 --- a/docs/ocr/api-ref/ocr_03_0060.html +++ b/docs/ocr/api-ref/ocr_03_0060.html @@ -10,7 +10,7 @@
    2. Endpoint
      3. -
    3. Constraints and Limitations
      +
    4. Notes and Constraints
    5. Basic Concepts
      6. diff --git a/docs/ocr/api-ref/ocr_03_0062.html b/docs/ocr/api-ref/ocr_03_0062.html index 369f45072..c7c0ae6f4 100644 --- a/docs/ocr/api-ref/ocr_03_0062.html +++ b/docs/ocr/api-ref/ocr_03_0062.html @@ -1,7 +1,7 @@

      Endpoint

      -

      An endpoint is the request address used to call an API. Different services have different endpoints for different regions. You can query all service endpoints at Regions and Endpoints.

      +

      An endpoint is the request address for calling an API. Endpoints vary depending on services and regions. For more information, see Regions and Endpoints.

      diff --git a/docs/ocr/api-ref/ocr_03_0063.html b/docs/ocr/api-ref/ocr_03_0063.html index 42dd0d763..64f68e2fd 100644 --- a/docs/ocr/api-ref/ocr_03_0063.html +++ b/docs/ocr/api-ref/ocr_03_0063.html @@ -1,9 +1,11 @@ -

      Constraints and Limitations

      +

      Notes and Constraints

      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 supported but support for traditional Chinese characters is limited.
      -

      General Text OCR

      • Only images in PNG, JPG, JPEG, BMP, GIF, 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 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/api-ref/ocr_03_0161.html b/docs/ocr/api-ref/ocr_03_0161.html new file mode 100644 index 000000000..7e5273b80 --- /dev/null +++ b/docs/ocr/api-ref/ocr_03_0161.html @@ -0,0 +1,884 @@ + + +

      Smart Document Recognizer

      +

      Function

      This API 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.

      +
      +

      Notes and Constraints

      • 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.
      +
      +

      URI

      POST /v2/{project_id}/ocr/smart-document-recognizer

      + +
      + + + + + + + + + + + + + +
      Table 1 URI parameters

      Parameter

      +

      Mandatory

      +

      Description

      +

      endpoint

      +

      Yes

      +

      Endpoint, which is the request address for calling an API.

      +

      The endpoint varies depending on services in different regions. For more details, see Endpoint.

      +

      project_id

      +

      Yes

      +

      Project ID, which can be obtained by referring to Obtaining the Project ID.

      +
      +
      +
      +

      Request Parameters

      +
      + + + + + + + + + + + + + + + + +
      Table 2 Request header parameters

      Parameter

      +

      Mandatory

      +

      Type

      +

      Description

      +

      X-Auth-Token

      +

      Yes

      +

      String

      +

      User token. During API authentication using a token, the token is added to requests to obtain permissions for calling the API. The token is the value of X-Subject-Token in the response header.

      +

      Content-Type

      +

      Yes

      +

      String

      +

      MIME type of the request body. The value is application/json.

      +
      +
      + +
      + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
      Table 3 Request body parameters

      Parameter

      +

      Mandatory

      +

      Type

      +

      Description

      +

      data

      +

      No

      +

      String

      +

      Set either this parameter or url. Base64 encoded string of the image or PDF. The file has a size limit of 10 MB. No side of the image can be smaller than 15 or larger than 8,192 pixels. Only images in JPG, PNG, BMP, or TIFF format can be recognized. PDFs are converted to images with a resolution of 144 dpi for document analysis, and they must meet the image size requirements mentioned above. If a PDF has multiple pages, only the first page will be recognized.

      +

      url

      +

      No

      +

      String

      +

      Set either this parameter or image. The image file has a size limit of 10 MB. The following image URLs are currently supported:

      +
      • Public HTTP/HTTPS URL
      • URL provided by OBS.
      +
      NOTE:
      • The API response time depends on the image download time. If the image download takes a long time, the API call will fail.
      • Ensure that the storage service where the images to be detected reside is stable and reliable. OBS is recommended for storing image data.
      • The URL cannot contain Chinese characters. If Chinese characters exist, they must be encoded using UTF-8.
      +
      +

      single_orientation_mode

      +

      No

      +

      Boolean

      +

      Whether to enable the single direction mode. The options are:

      +
      • true: Enables the single direction mode.
      • false: Disables the single direction mode.
      +

      Enabling this function when text in the image is oriented uniformly improves recognition accuracy. Disabling it when text in the image varies in direction allows for multi-direction text recognition. If not specified, true is used by default. In this case, the fields in the image are recognized as in a single direction by default.

      +

      language

      +

      No

      +

      String

      +

      Chinese and English recognition. The value is zh.

      +

      kv

      +

      No

      +

      Boolean

      +

      Whether to extract key-value pairs. If you choose to extract key-value pairs, the results will be returned with the keyword kv_result.

      +

      table

      +

      No

      +

      Boolean

      +

      Whether to recognize tables. Here, tables refer to logical tables that typically have an M x N format and have a header in the first row or column. If you choose to recognize tables, the results will be returned with the keyword table_result.

      +

      layout

      +

      No

      +

      Boolean

      +

      Whether to analyze the layout. If you choose to analyze the layout, the results will be returned with the keyword layout_result.

      +

      return_excel

      +

      No

      +

      Boolean

      +

      This parameter is available only when table is set to True. Whether to return the Base64-encoded field for converting a table into a Microsoft Excel file.

      +

      form

      +

      No

      +

      Boolean

      +

      Whether to recognize wired forms. A wired form displays crucial information in wired cells, like household registers and motor vehicle sales invoices. If you choose to recognize wired forms, the results will be returned with the keyword form_result.

      +

      formula

      +

      No

      +

      Boolean

      +

      Whether to recognize formulas. The results are returned as a LaTeX sequence. If you choose to recognize formulas, the results will be returned with the keyword formula_result.

      +
      • Enabling formula recognition may slow down the response speed.
      • Recognition of formulas is currently limited to a maximum of three lines. Formulas longer than this limit will not be recognized.
      +

      kv_map

      +

      No

      +

      String

      +

      JSON-serialized string of a dictionary that needs to be passed in, which is used to normalize and map specific key values in kv_result. For example, if kv_result contains the key-value pair {"Name": "Xiaoming"}, passing in the kv_map {"Name": "Full name"} would result in {"Full Name": "Xiaoming"}.

      +
      NOTE:

      Example:

      +
      • "kv_map":"{"Name":"Full name"}"
      +
      +

      erase_seal

      +

      No

      +

      Boolean

      +

      Whether to erase the seal. Enabling it can enhance the character recognition accuracy in the area blocked by the seal.

      +

      pdf_page_number

      +

      No

      +

      Integer

      +

      Specify which page of the PDF to recognize. If this parameter is specified, the content on the specified page is identified. If not specified, the default is to recognize the first page.

      +
      +
      +
      +

      Response Parameters

      Status code: 200

      + +
      + + + + + + + + + +
      Table 4 Response body parameter

      Parameter

      +

      Type

      +

      Description

      +

      result

      +

      Array of SmartDocumentRecognizerResult objects

      +

      List of results returned in the order of the pages, with the first item in the list being the recognition result of the first page, and so on. This parameter is not included for a failed call.

      +
      +
      + +
      + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
      Table 5 SmartDocumentRecognizerResult

      Parameter

      +

      Type

      +

      Description

      +

      ocr_result

      +

      SmartDocumentRecognizerOcrResult object

      +

      Character recognition results

      +

      kv_result

      +

      SmartDocumentRecognizerKvResult object

      +

      Key-value pair extraction results. This parameter is returned only when kv is set to true.

      +

      table_result

      +

      SmartDocumentRecognizerTableResult object

      +

      Table recognition results. This parameter is returned only when table is set to true.

      +

      layout_result

      +

      SmartDocumentRecognizerLayoutResult object

      +

      Layout analysis results. This parameter is returned only when layout is set to true.

      +

      form_result

      +

      SmartDocumentRecognizerFormResult object

      +

      Wired form recognition results. This parameter is returned only when form is set to true.

      +

      formula_result

      +

      SmartDocumentRecognizerFormulaResult object

      +

      Formula recognition result

      +
      +
      + +
      + + + + + + + + + + + + + + + + + +
      Table 6 SmartDocumentRecognizerOcrResult

      Parameter

      +

      Type

      +

      Description

      +

      direction

      +

      Float

      +

      Image direction

      +

      words_block_count

      +

      Integer

      +

      Number of text blocks that have been recognized

      +

      words_block_list

      +

      Array of SmartDocumentRecognizerWordsBlockList objects

      +

      List of text blocks that have been recognized. The output sequence is from left to right and from top to bottom.

      +
      +
      + +
      + + + + + + + + + + + + + + + + + +
      Table 7 SmartDocumentRecognizerWordsBlockList

      Parameter

      +

      Type

      +

      Description

      +

      words

      +

      String

      +

      Recognition result of a text block

      +

      location

      +

      Array<Array<Integer>>

      +

      List of location information about a text block, including the 2D coordinates (x, y) of four vertexes in the text area, where the coordinate origin is the upper-left corner of the image, the X axis is horizontal, and the Y axis is vertical.

      +

      confidence

      +

      Float

      +

      Confidence of a recognized text block

      +
      +
      + +
      + + + + + + + + + + + + + +
      Table 8 SmartDocumentRecognizerKvResult

      Parameter

      +

      Type

      +

      Description

      +

      kv_block_count

      +

      Integer

      +

      Number of key-value pairs recognized by the model

      +

      kv_block_list

      +

      Array of SmartDocumentRecognizerKVBlock objects

      +

      List of key-value pair recognition results

      +
      +
      + +
      + + + + + + + + + + + + + + + + + + + + + +
      Table 9 SmartDocumentRecognizerKVBlock

      Parameter

      +

      Type

      +

      Description

      +

      key

      +

      String

      +

      Key in a key-value pair, for example, Name in Name: Xiaoming.

      +

      value

      +

      String

      +

      Value in a key-value pair, for example, Xiaoming in Name: Xiaoming.

      +

      words_block_count

      +

      Integer

      +

      Number of text boxes contained in the key-value pair

      +

      words_block_list

      +

      Array of SmartDocumentRecognizerKVWordsBlock objects

      +

      List of text box recognition results

      +
      +
      + +
      + + + + + + + + + + + + + + + + + +
      Table 10 SmartDocumentRecognizerKVWordsBlock

      Parameter

      +

      Type

      +

      Description

      +

      words

      +

      String

      +

      Recognition result of a text block

      +

      location

      +

      Array<Array<Integer>>

      +

      List of location information about a text block, including the 2D coordinates (x, y) of four vertexes in the text area, where the coordinate origin is the upper-left corner of the image, the X axis is horizontal, and the Y axis is vertical.

      +

      type

      +

      String

      +

      Type

      +
      +
      + +
      + + + + + + + + + + + + + +
      Table 11 SmartDocumentRecognizerTableResult

      Parameter

      +

      Type

      +

      Description

      +

      table_count

      +

      Integer

      +

      Number of tables recognized by the model

      +

      table_list

      +

      Array of SmartDocumentRecognizerTableBlock objects

      +

      List of table recognition results

      +
      +
      + +
      + + + + + + + + + + + + + +
      Table 12 SmartDocumentRecognizerLayoutResult

      Parameter

      +

      Type

      +

      Description

      +

      layout_block_count

      +

      Integer

      +

      Number of document layout areas recognized by the model

      +

      layout_block_list

      +

      Array of SmartDocumentRecognizerLayoutBlock objects

      +

      List of document layout area recognition results

      +
      +
      + +
      + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
      Table 13 SmartDocumentRecognizerLayoutBlock

      Parameter

      +

      Type

      +

      Description

      +

      location

      +

      Array<Array<Integer>>

      +

      List of location information about a text block, including the 2D coordinates (x, y) of four vertexes in the text area, where the coordinate origin is the upper-left corner of the image, the X axis is horizontal, and the Y axis is vertical.

      +

      type

      +

      String

      +

      Document area type. The options are text, title, sub_title, image, image_caption, form, table, table_caption, header, footer, page_number, reference, formula, stamp, and directory.

      +

      text

      +

      String

      +

      Text in the document area. For tables and images, the text content is not returned.

      +

      words_ids

      +

      Array of integers

      +

      Index list of character recognition results, indicating which text blocks in words_block_list of ocr_result are located within the document area.

      +

      table_id

      +

      Integer

      +

      This parameter is returned only when type is table and the input parameter table is True, indicating which recognition result corresponds to the current logical table area in table_result.

      +

      form_id

      +

      Integer

      +

      This parameter is returned only when type is form and the input parameter table is True, indicating which recognition result corresponds to the current wired form area in form_result.

      +
      +
      + +
      + + + + + + + + + + + + + +
      Table 14 SmartDocumentRecognizerFormResult

      Parameter

      +

      Type

      +

      Description

      +

      form_count

      +

      Integer

      +

      Number of wired forms recognized by the model

      +

      form_list

      +

      Array of SmartDocumentRecognizerTableBlock objects

      +

      List of wired form recognition results

      +
      +
      + +
      + + + + + + + + + + + + + + + + + + + + + +
      Table 15 SmartDocumentRecognizerTableBlock

      Parameter

      +

      Type

      +

      Description

      +

      location

      +

      Array<Array<Integer>>

      +

      Location information of the current table, in list format, indicating the X and Y coordinates of the four vertices in a text block. The coordinate origin is the upper left corner of the image, the X axis is horizontal, and the Y axis is vertical.

      +

      words_block_count

      +

      Integer

      +

      Number of cells in a table

      +

      words_block_list

      +

      Array of SmartDocumentRecognizerTableWordsBlock objects

      +

      List of cell recognition results

      +

      excel

      +

      String

      +

      Base64 encoded string of the table recognition results. This parameter is returned only when return_excel is set to true. You can use base64.b64decode to decode the returned Excel code and save it as an .xlsx file.

      +
      +
      + +
      + + + + + + + + + + + + + + + + + +
      Table 16 SmartDocumentRecognizerTableWordsBlock

      Parameter

      +

      Type

      +

      Description

      +

      words

      +

      String

      +

      Character recognition results in a cell

      +

      rows

      +

      Array of integers

      +

      Rows occupied by text. The values start from 0 and are displayed in a list. The data type is Integer.

      +

      columns

      +

      Array of integers

      +

      Columns occupied by text. The values start from 0 and are displayed in a list. The data type is Integer.

      +
      +
      + +
      + + + + + + + + + + + + + +
      Table 17 SmartDocumentRecognizerFormulaResult

      Parameter

      +

      Type

      +

      Description

      +

      formula_count

      +

      Integer

      +

      Number of mathematical formulas

      +

      formula_list

      +

      Array of SmartDocumentRecognizerFormulaBlock objects

      +

      List of mathematical formula recognition results

      +
      +
      + +
      + + + + + + + + + + + + + +
      Table 18 SmartDocumentRecognizerFormulaBlock

      Parameter

      +

      Type

      +

      Description

      +

      formula

      +

      String

      +

      Mathematical formula recognition results, which are represented as LaTeX strings

      +

      location

      +

      Array<Array<Integer>>

      +

      Mathematical formula location information, in list format, indicating the X and Y coordinates of the four vertices. The coordinate origin is the upper left corner of the image and has a horizontal X axis and vertical Y axis.

      +
      +
      +

      Status code: 400

      + +
      + + + + + + + + + + + + + +
      Table 19 Response body parameters

      Parameter

      +

      Type

      +

      Description

      +

      error_code

      +

      String

      +

      Error code returned when the API fails to be called

      +

      This parameter is not returned when the API is successfully called.

      +

      error_msg

      +

      String

      +

      Error message returned when the API fails to be called

      +

      This parameter is not included when the API is successfully called.

      +
      +
      +
      +

      Example Request

      • Transfer the Base64 encoded string of the document image for recognition.
        POST https://{endpoint}/v2/{project_id}/ocr/smart-document-recognizer 
+  
+ { 
+   "data" : "/9j/4AAQSkZJRgABAgEASABIAAD/4RFZRXhpZgAATU0AKgAAAA..." 
+ }
        +
      • Transfer the URL of the document image for recognition.
        POST https://{endpoint}/v2/{project_id}/ocr/smart-document-recognizer 
+  
+ { 
+   "url" : "https://BucketName.obs.xxxcloud.com/ObjectName" 
+ }
        +
      +
      +

      Example Response

      Status code: 200

      +

      Example response for a successful request

      +
      {
+  "result" : [ {
+    "formula_result" : {
+      "formula_count" : 1,
+      "formula_list" : [ {
+        "formula" : "\\\\int _ { L } \\\\left ( 2 x y ^ { 3 } - y ^ { 2 } \\\\cos x \\\\right ) \\\\mathrm { d } x + \\\\left ( 1 - 2 y \\\\sin x + 3 x ^ { 2 } y ^ { 2 } \\\\right ) \\\\mathrm { d } y",
+        "location" : [ [ 171, 919 ], [ 950, 919 ], [ 950, 967 ], [ 171, 967 ] ]
+      } ]
+    }
+  }, {
+    "layout_result" : {
+      "layout_block_count" : 19,
+      "layout_block_list" : [ {
+        "location" : [ [ 1165, 368 ], [ 2031, 368 ], [ 2031, 465 ], [ 1165, 465 ] ],
+        "type" : "title",
+        "text": "VAT Special Invoice",
+        "words_ids" : [ 0 ]
+      }, {
+        "location" : [ [ 15, 19 ], [ 1078, 19 ], [ 1078, 637 ], [ 15, 637 ] ],
+        "type" : "form",
+        "text" : "xxxx",
+        "words_ids" : [ 2, 3, 4 ],
+        "form_id" : 0
+      }, {
+        "location" : [ [ 18, 180 ], [ 1077, 180 ], [ 1077, 636 ], [ 18, 636 ] ],
+        "type" : "table",
+        "text" : "xxxx",
+        "words_ids" : [ 0, 1, 2 ],
+        "table_id" : 0
+      } ]
+    }
+  }, {
+    "form_result" : {
+      "form_count" : 1,
+      "form_list" : [ {
+        "location" : [ [ 15, 19 ], [ 1074, 19 ], [ 1074, 636 ], [ 15, 636 ] ],
+        "words_block_count" : 24,
+        "words_block_list" : [ {
+          "words" : "xxx",
+          "rows" : [ 0 ],
+          "columns" : [ 0, 1, 2 ]
+        }, {
+          "words" : "xxxx",
+          "rows" : [ 1 ],
+          "columns" : [ 0, 1, 2 ]
+        } ],
+        "excel" : "UEsDBBQAAAAIAAAAIQBhXUk6TwEAAI8EAAATAAAAW0NvbnRlbnRfVHlwZX..."
+      } ]
+    }
+  }, {
+    "table_result" : {
+      "table_count" : 1,
+      "table_list" : [ {
+        "words_block_count" : 24,
+        "words_block_list" : [ {
+          "words": "Name of goods or taxable labor services",
+          "rows" : [ 0 ],
+          "columns" : [ 0 ]
+        }, {
+          "words": "Specifications and model",
+          "rows" : [ 0 ],
+          "columns" : [ 1 ]
+        } ],
+        "excel" : "xxxx",
+        "location" : [ [ 275, 967 ], [ 2919, 967 ], [ 2919, 1177 ], [ 275, 1177 ] ]
+      } ]
+    }
+  }, {
+    "kv_result" : {
+      "kv_block_count" : 25,
+      "kv_block_list" : [ {
+        "key": "Invoice issuance date",
+        "value": "August 31, 2017",
+        "words_block_count" : 2,
+        "words_block_list" : [ {
+          "words": "Invoice issuance date",
+          "location" : [ [ 2241, 589 ], [ 2480, 592 ], [ 2480, 646 ], [ 2241, 643 ] ],
+          "type" : "key"
+        }, {
+          "words": "August 31, 2017",
+          "location" : [ [ 2479, 591 ], [ 2850, 595 ], [ 2850, 649 ], [ 2479, 645 ] ],
+          "type" : "value"
+        } ]
+      } ]
+    }
+  }, {
+    "ocr_result" : {
+      "direction" : 0.4767,
+      "words_block_count" : 67,
+      "words_block_list" : [ {
+        "words": "Heilongjiang VAT Special Invoice",
+        "location" : [ [ 430, 100 ], [ 874, 99 ], [ 874, 139 ], [ 430, 141 ] ],
+        "confidence" : 0.9552
+      } ]
+    }
+  } ]
+}
      +

      Status code: 400

      +

      Example response for a failed request

      +
      {
+  "error_code" : "AIS.0103",
+  "error_msg" : "The image size does not meet the requirements."
+}
      +
      +

      Status Codes

      +
      + + + + + + + + + + +

      Status Code

      +

      Description

      +

      200

      +

      Response for a successful request

      +

      400

      +

      Response for a failed request

      +
      +
      +

      See Status Codes.

      +
      +

      Error Codes

      See Error Codes.

      +
      +
      +
      +
      +
      Parent topic: API
      +
      +
      + diff --git a/docs/ocr/api-ref/ocr_03_0162.html b/docs/ocr/api-ref/ocr_03_0162.html new file mode 100644 index 000000000..776b305d6 --- /dev/null +++ b/docs/ocr/api-ref/ocr_03_0162.html @@ -0,0 +1,200 @@ + + +

      Permissions Policies and Supported Actions

      +

      This section describes how you can use Identity and Access Management (IAM) for fine-grained permissions management of your OCR resources. If your account does not need individual IAM users, you may skip over this section.

      +

      New IAM users do not have any permissions by default. You need to add them to one or more groups and assign policies or roles to these groups. Users inherit permissions from the groups. Users then can perform specified operations on cloud services based on the permissions they have been granted.

      +

      You can grant permissions using roles and policies. Roles are a type of service-based, coarse-grained authorization mechanism provided by IAM to define permissions that match user responsibilities. Policies are more fine-grained, API-based permissions required to perform operations on specific cloud resources under certain conditions, meeting requirements for secure access control.

      +

      If you want to allow or deny the access to an API, use policy-based authorization.

      +
      +

      An account has full permissions to call all APIs, but IAM users under the account must be granted the required permissions to make successful API calls. The permissions required for calling an API are determined by the actions supported by the API. Only users with granted permissions can call the API successfully.

      +

      Supported Actions

      OCR provides system-defined policies that can be directly used in IAM. You can also create custom policies to supplement system-defined policies for more refined access control. Actions supported by policies are specific to APIs. The following are common concepts related to actions:

      +
      • Permissions: statements in a policy that allow or deny certain operations on specific resources under specific conditions.
      • APIs: APIs that can be called by a custom policy.
      • Actions: specific operations that are allowed or denied.
      • Dependencies: actions which a specific action depends on. When allowing an action for a user, you also need to allow any existing action dependencies for that user.
      +
      • IAM or enterprise projects: type of projects for which an action will take effect. Policies that contain actions supporting both IAM and enterprise projects can be assigned to user groups and take effect in both IAM and Enterprise Management. Policies that only contain actions supporting IAM projects can be assigned to user groups and only take effect for IAM.
      +

      √: supported; x: not supported

      +
      + +
      + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
      Table 1 Actions supported by OCR

      Permission

      +

      API

      +

      Action

      +

      IAM Project

      +

      (Project)

      +

      Enterprise Project

      +

      (Enterprise Project)

      +

      Subscribing to General Text OCR

      +

      x

      +

      ocr:generalText:subscribe

      +

      √

      +

      x

      +

      Unsubscribing from General Text OCR

      +

      x

      +

      ocr:generalText:unsubscribe

      +

      √

      +

      x

      +

      Listing the users who have subscribed to General Text OCR

      +

      x

      +

      ocr:generalText:getSubscribeUserList

      +

      √

      +

      x

      +

      Subscribing to General Text OCR for other IAM users

      +

      x

      +

      ocr:generalText:subscribeAllUsers

      +

      √

      +

      x

      +

      Unsubscribing from General Text OCR for other IAM users

      +

      x

      +

      ocr:generalText:unsubscribeAllUsers

      +

      √

      +

      x

      +

      Subscribing to General Table OCR

      +

      x

      +

      ocr:generalTable:subscribe

      +

      √

      +

      x

      +

      Unsubscribing from General Table OCR

      +

      x

      +

      ocr:generalTable:unsubscribe

      +

      √

      +

      x

      +

      Listing the users who have subscribed to General Table OCR

      +

      x

      +

      ocr:generalTable:getSubscribeUserList

      +

      √

      +

      x

      +

      Subscribing to General Table OCR for other IAM users

      +

      x

      +

      ocr:generalTable:subscribeAllUsers

      +

      √

      +

      x

      +

      Unsubscribing from General Table OCR for other IAM users

      +

      x

      +

      ocr:generalTable:unsubscribeAllUsers

      +

      √

      +

      x

      +

      Subscribing to Smart Document Recognizer

      +

      x

      +

      ocr:smartDocumentRecognizer:subscribe

      +

      √

      +

      x

      +

      Unsubscribing from Smart Document Recognizer

      +

      x

      +

      ocr:smartDocumentRecognizer:unsubscribe

      +

      √

      +

      x

      +

      Listing the users who have subscribed to Smart Document Recognizer

      +

      x

      +

      ocr:smartDocumentRecognizer:getSubscribeUserList

      +

      √

      +

      x

      +

      Subscribing to Smart Document Recognizer for other IAM users

      +

      x

      +

      ocr:smartDocumentRecognizer:subscribeAllUsers

      +

      √

      +

      x

      +

      Unsubscribing from Smart Document Recognizer for other IAM users

      +

      x

      +

      ocr:smartDocumentRecognizer:unsubscribeAllUsers

      +

      √

      +

      x

      +
      +
      +
      +
      +