The Oracle Cloud Infrastructure (OCI) Vision service performs deep learning-based image analysis at scale. With prebuilt models available, developers can easily build image recognition and text recognition into their applications without machine learning (ML) expertise. For industry-specific use cases, developers can automatically train custom vision models with their own data. They can use these models to detect visual anomalies in manufacturing, organize digital media assets, and tag items in images to count products or shipments.
Today, we’re excited to announce the general availability of a new pretrained model: Face Detection. No data science experience is required to use this pretrained model.
You can send an image or a batch of images to the OCI Vision service and now analyze those images using our pretrained face detection model. The face detection feature provides the following information:
Identify the existence of faces in each image
The location of faces in each image using bounding box coordinates
Facial landmarks for each detected face, including left eye, right eye, nose tip, and left and right edges of mouth
Visual quality of each face: A higher score indicates that the image of the face is more likely to be suitable for biometrics
The feature is beneficial for the following use cases:
Privacy: Hide identities by adding a blur to the image using face location information returned through the face detection feature.
Prerequisite for Biometrics: Use the facial quality score to determine if a face is clear and unobstructed.
Digital asset management: Tag images with facial information for better indexing and retrieval.
The face detection feature is available through the Oracle Cloud Console and a software development kit (SDK). You can find more details, such as facial landmarks, in the JSON response.
For more information on the Oracle Cloud Infrastructure Vision service, see the following resources:
Try OCI Vision with Livelabs