Microsoft Certified: Azure AI Engineer AssociateImplement image and video processing solutionsHard
A museum is digitizing its archive of ancient, fragile manuscripts. Many of these documents are discolored, have faded ink, and contain text in multiple historical languages. They need to extract all textual content accurately. Which Azure AI service feature is best suited for this challenging OCR task?
- AAzure Form Recognizer's Layout API
- BAzure Computer Vision's Read API with Multi-language support
- CAzure Computer Vision's General OCR
- DAzure Video Indexer's Visual Text Detection
Show answer & explanationAnswer & explanation
Correct answer: B. Azure Computer Vision's Read API with Multi-language support
The Azure Computer Vision Read API is specifically designed for robust OCR on complex documents, including those with faded text, discolored backgrounds, and mixed languages. Its multi-language support is crucial for historical manuscripts with diverse linguistic content.
Why the other options are wrong
- A. Form Recognizer's Layout API focuses on structure and key-value pairs in documents, not primarily on the advanced OCR of difficult, free-form text in multiple languages.
- C. General OCR is less robust and accurate for faded, discolored, or multi-language text compared to the Read API.
- D. Video Indexer processes video content and its visual text detection is not designed for high-accuracy OCR on static, challenging documents.
Computer Vision Read API Multi-language & Layout
An advanced OCR capability within Azure Computer Vision's Read API that accurately extracts text from diverse documents, supporting multiple languages and complex layouts, even with quality challenges.
- Handles printed and handwritten text
- Supports over 100 languages
- Robust against image quality issues (faded, discolored, skewed)
- Provides text lines, words, and bounding box information
Memory trick: Read API Reads All Languages on Old Pages.