General Image Recognition (Enhanced)

Overview

The General Image Recognition (Enhanced) API leverages large models to identify various elements in an image and provides corresponding tags for the identified elements.

Billing

General Image Recognition (Enhanced) supports two billing methods: pay-as-you-go and resource plans.

Pay-as-you-go

After you activate the Content Moderation (Enhanced) service, the default billing method is pay-as-you-go. You are charged daily based on your actual usage. You are not charged if you do not call the service.

Integration

1. Create an Alibaba Cloud account: Sign up now, and follow the on-screen instructions to complete the registration.

2. Activate pay-as-you-go for Content Moderation: Ensure that you have activated the service. Activation is free. After you start making API calls, you are automatically billed for your usage. For more information, see Billing. You can also purchase resource plans. Resource plans offer tiered discounts and are ideal if you have a predictable or high usage volume.

3. Create an AccessKey pair: Ensure that you have created an AccessKey pair in RAM. If you are using a sub-account, the primary account must grant the AliyunYundunGreenWebFullAccess permission to the sub-account. For detailed instructions, see Grant permissions by using RAM.

4. Integrate the API: We recommend using an SDK to make API calls. For details, see the SDKs and integration guide for Image Moderation V2.0 (Enhanced).

API reference

Usage

You can call this API operation to create an image moderation task. For information on how to construct an HTTP request, see the Integration guide. You can also use pre-configured HTTP requests. For more information, see the SDK Reference.

• Business interface: ImageModeration

• Supported regions and endpoints:

• Billing: This is a billable API operation. You are charged only for requests that return an HTTP status code of 200. Requests that result in errors are not charged. For more information about billing methods, see Billing.

• Image requirements:

• Images in the following formats are supported: PNG, JPG, JPEG, BMP, WEBP, TIFF, SVG, HEIC (the longest side must be less than 8,192 px), GIF (only the first frame is processed), and ICO (only the last image is processed).

• The image size cannot exceed 20 MB. The height or width cannot exceed 16,384 pixels, and the total number of pixels cannot exceed 167 million. For best results, we recommend that the image resolution be at least 200 x 200 pixels. Low resolution may affect the accuracy of the recognition algorithm.

• The image must be downloaded within 3 seconds. If the download times out, an error is returned.

QPS limit

The QPS limit for a single user for this API operation is 10 calls per second. If you exceed this limit, the system throttles your calls, which may impact your business. If your business requires a higher QPS limit, contact your business manager.

Debugging

Before integration, you can use OpenAPI Explorer to debug the Image Moderation (Enhanced) API online. This tool provides API call examples and SDK dependency information to help you quickly understand the API operations and parameters.

Request parameters

For information about the common request parameters that must be included in a request, see SDKs and integration guide for Image Moderation V2.0 (Enhanced).

The request body is a JSON object that contains the following parameters:

Table 1. ServiceParameters

Response parameters

Table 2. Data

Table 3. Ext

Table 4. Recognition

Table 5. Result

Examples

Request example

{
    "Service": "generalRecognition",
    "ServiceParameters": {
        "imageUrl": "https://img.alicdn.com/tfs/TB1U4r9AeH2gK0jSZJnXXaT1FXa-2880-480.png",
        "dataId": "img123****"
    }
}

Response example

{
    "Msg": "OK",
    "Code": 200,
    "Data": {
        "DataId": "img123****",
        "Ext": {
            "Recognition": [
                {
                    "Classification": "Building",
                    "Confidence": 92.73
                },
                {
                    "Classification": "Art",
                    "Confidence": 88.95
                },
                {
                    "Classification": "Illustration",
                    "Confidence": 82.22
                },
                {
                    "Classification": "Pencil",
                    "Confidence": 81.78
                },
                {
                    "Classification": "Sky",
                    "Confidence": 77.95
                },
                {
                    "Classification": "Office Building",
                    "Confidence": 66.94
                }
            ]
        },
        "Result": [
            {
                "Label": "nonLabel"
            }
        ]
    },
    "RequestId": "ABCD1234-1234-1234-1234-1234XYZ"
}

Status codes

The following table describes the status codes returned by the API. You are charged only for requests that return a status code of 200. No fees are incurred for other status codes.