AI-based image analysis features of the old IMM version-Intelligent Media Management(IMM)-阿里云帮助中心

After you create a project in Intelligent Media Management (IMM), you can make synchronous API calls to use AI-based image analysis features, such as content recognition, face detection, and QR code recognition.

Important

This topic is no longer updated. We recommend that you use the new IMM version. For a comparison between the new IMM version and the old one, see Overview of the new and old IMM versions.

You can access AI-based image analysis features only by making synchronous requests. The following table describes the API operations that provide AI-based image analysis capabilities.

API operation	Description
DetectImageTags	Detects labels in an image.
DetectImageFaces	Detects faces in an image.
DetectImageQRCodes	Detects QR codes in an image and returns the positions and contents of QR codes.
DetectImageBodies	Detects human bodies in an image.
FindSimilarFaces	Searches for a specific number of images that contain faces that are most similar to a specific face.
CompareImageFaces	Compares two faces to determine the degree of face similarity. You can call the operation by using two methods: Provide the URIs of two images in Object Storage Service (OSS) to calculate the similarity between the largest face in one image and the largest face in the other image. In this case, you do not need to create a dataset first. Provide the face IDs in two images that are indexed into a dataset.
EncodeBlindWatermark	Adds a blind watermark to an image. A blind watermark is not visible. However, you can call the DecodeBlindWatermark operation to decode the invisible watermark.
GetImageCroppingSuggestions	Returns image cropping suggestions.
GetImageQuality	Returns an image quality score.