AWS 教你用 Nova、SAM 3 和 Textract 搭一套能自动处理身份证和车牌的 PII 编辑管道，挺实用的。
该方案利用 Amazon Nova 的视觉推理能力协调多个工具：Meta 的 SAM 3 进行像素级分割、Amazon Textract 进行 OCR。管道处理指纹、身份证、各种朝向的车牌等边缘案例。所有组件部署在 Amazon SageMaker AI 上。最终输出合规的 PII 编辑结果。
Automatically redact PII in images with Amazon Nova
In this post, we present a multi-step pipeline directed by Amazon Nova, which uses its contextual vision reasoning to coordinate complementary tools, including Meta’s open-source Segment Anything Model (SAM 3) deployed on Amazon SageMaker AI for pixel-level segmentation, and Amazon Textract for optical character recognition (OCR). This pipeline is designed to provide comprehensive and compliant PII redaction even for challenging edge cases such as fingerprints, ID cards, or license plates in arbitrary orientations.