Microsoft Certified: Azure AI Engineer AssociateImplement image and video processing solutionsMedium
A logistics company uses drones to inspect large warehouses. They need to automatically detect and count specific types of inventory boxes and identify their labels, which contain alphanumeric codes. The solution must process images captured by the drones. Which two Azure Cognitive Services should be combined to achieve both object counting and label extraction efficiently?
- AAzure Face API and Azure Computer Vision
- BAzure Custom Vision and Azure Form Recognizer
- CAzure Custom Vision and Azure Computer Vision
- DAzure Video Indexer and Azure Computer Vision
Show answer & explanationAnswer & explanation
Correct answer: C. Azure Custom Vision and Azure Computer Vision
Azure Custom Vision is ideal for training a model to detect and count specific types of inventory boxes (custom object detection). Azure Computer Vision's OCR capabilities can then be used to extract the alphanumeric codes from the labels identified on those boxes.
Why the other options are wrong
- A. Face API is for facial recognition; it's irrelevant here.
- B. Form Recognizer is for structured documents, not general image OCR from arbitrary labels on objects.
- D. Video Indexer is for video analysis, not static image processing for custom object detection and OCR.
Custom Vision + Computer Vision
Combining Azure Custom Vision for domain-specific object detection with Azure Computer Vision for general-purpose OCR allows for comprehensive analysis of images containing unique objects and their textual labels.
- Custom Vision for custom object detection/classification.
- Computer Vision for robust OCR.
- Synergistic for complex image analysis tasks.
Memory trick: Custom eyes for objects, computer eyes for text: a perfect pair.