AI-102 Optical Character Recognition (OCR) Practice Question
Which THREE Azure AI services can be used to extract text from images?
⚠ Common exam trap
The trap is that candidates may overlook Azure AI Search as a text extraction service because it is not a dedicated OCR service, but it can indeed extract text from images when configured with an OCR skill.
Answer choices
Why each option matters
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
Azure AI Search
Option B (Azure AI Search) is correct because it includes AI enrichment with the OCR cognitive skill, which extracts text from image files (e.g., JPEG, PNG) during the indexing pipeline, making the text searchable. Option C (Azure AI Document Intelligence layout model) is correct because the layout model performs OCR on documents and images, extracting printed and handwritten text along with tables and structure from forms and files. Option D (Azure AI Vision OCR) is correct because the Read/OCR API in Azure AI Vision extracts printed and handwritten text from images and documents. Option A (Azure AI Speech) is incorrect because it handles speech-to-text, text-to-speech, and translation of audio, not text extraction from images. Option E (Azure AI Language custom NER) is incorrect because it extracts named entities from existing text, not text from images.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Azure AI Speech
Why it's wrong here
Azure AI Speech transcribes spoken audio into text and synthesises speech; it processes acoustic signals, not image pixels, so it cannot perform OCR. It is tempting because it is a text-extraction service, but it would be correct only when the source content is recorded or live audio rather than a picture.
- ✓
Azure AI Search
Why this is correct
Azure AI Search supports OCR enrichment through its built-in cognitive skills, extracting text from image content during indexing. This satisfies the requirement for a service that pulls text out of images, alongside Vision and Document Intelligence.
- ✓
Azure AI Document Intelligence layout model
Why this is correct
The layout model performs OCR over scanned and printed text while preserving structure such as tables, headings and reading order. It extracts text from images embedded in documents, satisfying the requirement to pull textual content from image-based sources rather than only classifying or describing them.
- ✓
Azure AI Vision OCR
Why this is correct
Azure AI Vision OCR extracts printed and handwritten text from images through the Read API, returning lines and words with bounding-box coordinates. It satisfies the stem's requirement to pull text directly from image content, unlike speech or language services that process audio or already-extracted text.
- ✗
Azure AI Language custom NER
Why it's wrong here
Custom NER extracts named entities such as people, places and organisations from text; it performs no optical character recognition, so it cannot read pixels in an image. It is tempting because it is a text-extraction service, but it would be correct only when the source is already machine-readable text needing entity labelling.
Go deeper
Related to this question
About these practice questions
One of 761 original AI-102 practice questions on Courseiva, each with a full explanation and wrong-answer analysis — not exam dumps or protected exam content. Learn why practice questions differ from exam dumps →
JA
Written by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
This AI-102 practice question is part of Courseiva's free Microsoft certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the AI-102 exam.