Microsoft Azure AI Fundamentals (AI-900)Describe features of Natural Language Processing (NLP) workloads on AzureMedium
A publishing company wants to convert a vast archive of scanned historical books into editable and searchable digital text. Which Azure AI service or capability is essential for converting the images of text into machine-readable text?
- AText Summarization
- BLanguage Understanding (LUIS)
- CNamed Entity Recognition (NER)
- DOptical Character Recognition (OCR)
Show answer & explanationAnswer & explanation
Correct answer: D. Optical Character Recognition (OCR)
Optical Character Recognition (OCR) is the technology specifically designed to convert different types of documents, such as scanned paper documents, PDF files, or images captured by a digital camera, into editable and searchable data.
Why the other options are wrong
- A. Text Summarization condenses existing text, it doesn't handle image-to-text conversion.
- B. LUIS understands intent and entities in conversational text, it's not for image-to-text conversion.
- C. NER identifies entities within existing text, it doesn't convert image text.
Optical Character Recognition (OCR)
Optical Character Recognition (OCR) is a technology that enables conversion of images of text (typewritten, handwritten or printed) into machine-encoded text.
- Essential for digitizing physical documents.
- Allows text searchability and editing of scanned content.
- Often a prerequisite for further NLP tasks on scanned documents.
Memory trick: OCR Makes Image Text Readable.