Basic Information
| Field | Details |
|---|---|
| English name | Amazon Rekognition |
| Full name | Amazon Rekognition |
| Chinese description | 图像与视频分析 |
| Japanese description | 画像・動画分析 |
| Exam frequency | ⭐⭐⭐ |
| Often confused with | Textract |
In one sentence
Analyze objects, scenes, text, faces, and unsafe content in images and video with pretrained capabilities.
Key points
- It fits image labeling, moderation, media analysis, and visual search.
- It is a pretrained AI service and usually does not require training a full vision model.
- For forms, tables, and structured fields in scanned documents, compare Textract first.
Exam focus
- Image or video recognition and object or scene detection point to Rekognition.
Common pitfalls
- Do not choose by product name alone; confirm data type, latency, control, operations, and cost constraints.
Remember
Rekognition sees images and video; Textract extracts document structure.