Amazon Lookout for Vision now provides anomaly localization and CPU inference on the edge

[AWS]

Amazon Lookout for Vision now provides anomaly localization through semantic segmentation. You can use Lookout for Vision’s segmentation models to identify the locations on an image where different types of anomalies (such as a scratch, dent, or tear) are present, the label of the anomaly and the size of the anomaly, which you can then use to make decisions such as classify, grade, bin product and ship, rework, or scrap the part. You can deploy the trained semantic segmentation models for inference in the AWS Cloud via the AWS SDK or CLI. You can also deploy them to an edge hardware device of your choice and run inference locally on the device.

View the full article