RecognizeCarInvoice-阿里云帮助中心

Operation description

Applicable scenarios

Alibaba Cloud motor vehicle sales invoice recognition is an officially self-developed OCR text recognition product. It is applicable to scenarios where you need to recognize key information on vehicle purchase invoices, such as invoice amount, purchaser name, vehicle type, brand model, and seller name.
Alibaba Cloud OCR products are built on the powerful AI technology and massive data resources of Alibaba DAMO Academy. After years of development and refinement, they offer high service stability, easy operation, real-time performance, and comprehensive capabilities.
Sample image for this API

Core capabilities

Categorization	Description
Image formats	Supports PNG, JPG, JPEG, BMP, GIF, TIFF, and WebP.
Image enhancement	Image enhancement is enabled by default, including automatic image rotate, automatic distortion correction, and automatic enhancement of blurry images.
Multiple type coverage	Supports image recognition of low-quality images with blur, uneven lighting, perspective distortion, and arbitrary backgrounds.
High accuracy	The overall recognition accuracy can reach 98%.

How to use this API

Step	Description
1	Activate the Invoice and Certificate Recognition service. Before or after activation, you can try the recognition feature for free in the Experience Center.
2	Purchase a Motor Vehicle Sales Invoice Recognition resource plan. This API provides a free quota for testing. You can also skip purchasing a resource plan, and the system will automatically deduct fees based on actual usage through the "pay-as-you-go" billing method.
3	Refer to the code samples provided on the debug page to complete API integration. After integration, invoke the API to obtain recognition results. If you use a RAM user to invoke the API, the Alibaba Cloud account must grant authorization to the Resource Access Management (RAM) users. For information about how to create a RAM user, see Create a RAM user. The OCR service provides a system policy named AliyunOCRFullAccess. For information about how to grant permissions, see Grant permissions to a RAM user on the Users page.

Important notes

Type	Description
Image formats	This API supports PNG, JPG, JPEG, BMP, GIF, TIFF, and WebP. PDF format is not supported.
Image dimensions	The image width and height must be greater than 15 pixels and less than 8192 pixels. The aspect ratio must be less than 50. For optimal recognition results, both width and height should be greater than 500 px.
Image size	The image binary file cannot exceed 10 MB. Large images affect API response speed. Use images smaller than 1.5 MB for recognition and invoke the API by passing the image URL.
Related capabilities	Alibaba Cloud Marketplace motor vehicle sales invoice recognition.

Try it now

Try this API in OpenAPI Explorer, no manual signing needed. Successful calls auto-generate SDK code matching your parameters. Download it with built-in credential security for local usage.

Test

RAM authorization

The table below describes the authorization required to call this API. You can define it in a Resource Access Management (RAM) policy. The table's columns are detailed below:

Action: The actions can be used in the Action element of RAM permission policy statements to grant permissions to perform the operation.
API: The API that you can call to perform the action.
Access level: The predefined level of access granted for each API. Valid values: create, list, get, update, and delete.
Resource type: The type of the resource that supports authorization to perform the action. It indicates if the action supports resource-level permission. The specified resource must be compatible with the action. Otherwise, the policy will be ineffective.
- For APIs with resource-level permissions, required resource types are marked with an asterisk (*). Specify the corresponding Alibaba Cloud Resource Name (ARN) in the Resource element of the policy.
- For APIs without resource-level permissions, it is shown as All Resources. Use an asterisk (*) in the Resource element of the policy.
Condition key: The condition keys defined by the service. The key allows for granular control, applying to either actions alone or actions associated with specific resources. In addition to service-specific condition keys, Alibaba Cloud provides a set of common condition keys applicable across all RAM-supported services.
Dependent action: The dependent actions required to run the action. To complete the action, the RAM user or the RAM role must have the permissions to perform all dependent actions.

Action

Access level

Resource type

Condition key

Dependent action

ocr:RecognizeCarInvoice

get

*All Resource

*

None

Request parameters

Parameter	Type	Required	Description	Example
Url	string	No	Either this field or the body field must be specified. You cannot specify both or leave both empty. The URL of the image (up to 2048 bytes, base64 not supported).	https://img.alicdn.com/tfs/TB1hC7bXCzqK1RjSZPcXXbTepXa-832-616.jpg
body	string	No	Either this field or the URL field must be specified. You cannot specify both or leave both empty. The image binary file, up to 10 MB. When using HTTP, place the image binary file in the HTTP body for upload. When using the SDK, place the image in the SDK body.	Image binary file

Response elements

Element	Type	Description	Example
	object	Schema of Response
Code	string	The fault code. This field is not returned if the recognition is successful.	noPermission
Data	string	The returned data.	{ "data": { "taxCode": "0492725/+0/法55337<56-24/184-/<94 16-6+9-897+98546/<>74++16<43800>+-< 116丰1<4201/18+-/74++16<43800>+-< 116丰1<4201/*18+-/
Message	string	The fault message. This field is not returned if the recognition is successful.	You are not authorized to perform this operation.
RequestId	string	The unique request ID.	43A29C77-405E-4CC0-BC55-EE694AD00655

Metric description of response elements

Field	Type	Description
data	object	The structured information.
sliceRect	list	The coordinate information of detected sub-images.
prism_keyValueInfo	list	The coordinate information of structured fields.
ftype	int	Indicates whether the document is a photocopy (1: yes, 0: no).
height	int	The height of the image after algorithm correction.
width	int	The width of the image after algorithm correction.
orgHeight	int	The height of the original image.
orgWidth	int	The width of the original image.

Recognition results (data field)

Field	Type	Description
taxCode	string	The tax control code.
invoiceDate	string	The invoice date.
invoiceCode	string	The invoice code.
invoiceNumber	string	The invoice number.
machineCode	string	The machine code.
purchaserName	string	The purchaser name.
purchaseCode	string	The purchaser ID number/organization code.
vehicleType	string	The vehicle type.
brandMode	string	The brand model.
origin	string	The place of origin.
certificateNumber	string	The certificate number.
importCertificateNumber	string	The import certificate number.
commodityInspectionNumber	string	The commodity inspection number.
engineNumber	string	The engine number.
vinCode	string	The vehicle identification number (VIN)/frame number.
invoiceAmountCn	string	The total amount including tax (in Chinese characters).
invoiceAmount	string	The total amount including tax (in digits).
sellerName	string	The seller name.
sellerContact	string	The seller phone number.
sellerTaxNumber	string	The seller taxpayer identification number.
sellerBankAccount	string	The seller bank account number.
sellerAddress	string	The seller address.
sellerDepositaryBank	string	The seller depositary bank.
taxRate	string	The VAT rate or levy rate.
tax	string	The VAT amount.
taxAuthoritiesInfo	string	The tax authority name and code.
taxAuthoritiesName	string	The tax authority name.
taxAuthoritiesCode	string	The tax authority code.
preTaxAmount	string	The pre-tax amount.
passengerLimitNumber	string	The passenger limit.
issuer	string	The invoice issuer.
tonnage	string	The tonnage.
purchaserTaxNumber	string	The purchaser taxpayer identification number.
taxPaymentNumber	string	The tax payment certificate number.

Structured coordinate information (prism_keyValueInfo field)

Field	Type	Description
key	string	The recognized field name.
keyProb	int	The confidence score of the field name.
value	string	The value corresponding to the recognized field name.
valueProb	int	The

Examples

Success response

JSON format

{
  "Code": "noPermission",
  "Data": "{\n      \"data\": {\n            \"taxCode\": \"0492725/*+0/法55337*<56-24/*184-/*<94 16-6+9*-897+98546/<>74*++16<43800*>+-< 116*丰1<4201/*18+-/74*++16<43800*>+-< 116*丰1<4201/*18+-/                  \"valuePos\": [\n                        {\n                              \"x\": 203,\n                              \"y\": 510\n                        },\n                        {\n                              \"x\": 203,\n                              \"y\": 524\n                        },\n                        {\n                              \"x\": 176,\n                              \"y\": 524\n                        },\n                        {\n                              \"x\": 176,\n                              \"y\": 510\n                        }\n                  ],\n                  \"valueProb\": 99\n            },\n            {\n                  \"key\": \"tax\",\n                  \"keyProb\": 100,\n                  \"value\": \"14384.62\",\n                  \"valuePos\": [\n                        {\n                              \"x\": 413,\n                              \"y\": 509\n                        },\n                        {\n                              \"x\": 413,\n                              \"y\": 524\n                        },\n                        {\n                              \"x\": 323,\n                              \"y\": 524\n                        },\n                        {\n                              \"x\": 323,\n                              \"y\": 509\n                        }\n                  ],\n                  \"valueProb\": 100\n            },\n            {\n                  \"key\": \"taxAuthoritiesInfo\",\n                  \"keyProb\": 100,\n                  \"value\": \"安阳县国家税务局341052200\",\n                  \"valuePos\": [\n                        {\n                              \"x\": 633,\n                              \"y\": 498\n                        },\n                        {\n                              \"x\": 633,\n                              \"y\": 525\n                        },\n                        {\n                              \"x\": 537,\n                              \"y\": 525\n                        },\n                        {\n                              \"x\": 537,\n                              \"y\": 498\n                        }\n                  ],\n                  \"valueProb\": 99\n            },\n            {\n                  \"key\": \"taxAuthoritiesName\",\n                  \"keyProb\": 100,\n                  \"value\": \"安阳县国家税务局\",\n                  \"valuePos\": [\n                        {\n                              \"x\": 633,\n                              \"y\": 498\n                        },\n                        {\n                              \"x\": 633,\n                              \"y\": 525\n                        },\n                        {\n                              \"x\": 537,\n                              \"y\": 525\n                        },\n                        {\n                              \"x\": 537,\n                              \"y\": 498\n                        }\n                  ],\n                  \"valueProb\": 99\n            },\n            {\n                  \"key\": \"taxAuthoritiesCode\",\n                  \"keyProb\": 100,\n                  \"value\": \"341052200\",\n                  \"valuePos\": [\n                        {\n                              \"x\": 633,\n                              \"y\": 498\n                        },\n                        {\n                              \"x\": 633,\n                              \"y\": 525\n                        },\n                        {\n                              \"x\": 537,\n                              \"y\": 525\n                        },\n                        {\n                              \"x\": 537,\n                              \"y\": 498\n                        }\n                  ],\n                  \"valueProb\": 99\n            },\n            {\n                  \"key\": \"preTaxAmount\",\n                  \"keyProb\": 97,\n                  \"value\": \"84615.38\",\n                  \"valuePos\": [\n                        {\n                              \"x\": 216,\n                              \"y\": 557\n                        },\n                        {\n                              \"x\": 216,\n                              \"y\": 543\n                        },\n                        {\n                              \"x\": 305,\n                              \"y\": 544\n                        },\n                        {\n                              \"x\": 305,\n                              \"y\": 559\n                        }\n                  ],\n                  \"valueProb\": 97\n            },\n            {\n                  \"key\": \"passengerLimitNumber\",\n                  \"keyProb\": 100,\n                  \"value\": \"5\",\n                  \"valuePos\": [\n                        {\n                              \"x\": 723,\n                              \"y\": 545\n                        },\n                        {\n                              \"x\": 723,\n                              \"y\": 557\n                        },\n                        {\n                              \"x\": 714,\n                              \"y\": 557\n                        },\n                        {\n                              \"x\": 714,\n                              \"y\": 545\n                        }\n                  ],\n                  \"valueProb\": 100\n            },\n            {\n                  \"key\": \"issuer\",\n                  \"keyProb\": 100,\n                  \"value\": \"赵迪\",\n                  \"valuePos\": [\n                        {\n                              \"x\": 437,\n                              \"y\": 573\n                        },\n                        {\n                              \"x\": 437,\n                              \"y\": 588\n                        },\n                        {\n                              \"x\": 410,\n                              \"y\": 588\n                        },\n                        {\n                              \"x\": 410,\n                              \"y\": 573\n                        }\n                  ],\n                  \"valueProb\": 100\n            },\n            {\n                  \"key\": \"tonnage\",\n                  \"keyProb\": 100,\n                  \"value\": \"\",\n                  \"valueProb\": 100\n            },\n            {\n                  \"key\": \"purchaserTaxNumber\",\n                  \"keyProb\": 100,\n                  \"value\": \"410523197206046072\",\n                  \"valuePos\": [\n                        {\n                              \"x\": 730,\n                              \"y\": 240\n                        },\n                        {\n                              \"x\": 730,\n                              \"y\": 253\n                        },\n                        {\n                              \"x\": 569,\n                              \"y\": 253\n                        },\n                        {\n                              \"x\": 569,\n                              \"y\": 240\n                        }\n                  ],\n                  \"valueProb\": 100\n            },\n            {\n                  \"key\": \"taxPaymentNumber\",\n                  \"keyProb\": 100,\n                  \"value\": \"\",\n                  \"valueProb\": 100\n            }\n      ],\n      \"width\": 832\n}",
  "Message": "You are not authorized to perform this operation.",
  "RequestId": "43A29C77-405E-4CC0-BC55-EE694AD00655"
}

Error codes

See Error Codes for a complete list.

Release notes

See Release Notes for a complete list.