Save time and money by filtering faces during indexing with Amazon Rekognition
Amazon Rekognition is a deep learning-based image and video analysis service that can identify objects, people, text, scenes, and activities, as well as detect any inappropriate content. Using Amazon Rekognition’s new face filtering feature, you can now have control over the quality and quantity of faces indexed for face recognition, thus saving on cost, reducing development time, and improving face recognition accuracy.
When using the IndexFaces API, Amazon Rekognition detects all the faces in an image and indexes them into the collection specified. Some images may contain faces that aren't suitable or required for indexing. For example, an image may contain small, blurry faces which adversely affect face search quality, or irrelevant faces in the background at a crowded event such as red carpet premiere. Indexing such faces increases cost and is detrimental to accuracy in many cases.
Until now, you could only filter such faces out by running face detection, applying filtering rules on each face crop, and indexing the face crops that passed the filters. Amazon Rekognition's new face filtering simplifies this process by allowing you to filter faces during indexing itself using just two parameters. You no longer need to write and maintain additional code with multiple API calls or create your own rules to gauge quality.
Face filtering is available in all supported AWS Regions where Amazon Rekognition is available, at no additional cost. For more information, please see our blog and the documentation page. You can get started by downloading the latest version of the AWS SDK.