AI-900 Practice Question: Describe features of computer vision workloads on Azure

Answer analysis

Option-by-option breakdown

For each option: why learners choose it and why it is or isn't the right answer here.

• ✗

  Speech recognition; provided by Azure AI Speech

  Why it's wrong here

  Speech recognition, provided by Azure AI Speech, transcribes spoken language from audio waveforms into textual output; it does not accept image files or process visual information in any way. The input modality is audio, not pixels, so the service has no mechanism to locate or read characters printed on a page. While both speech recognition and OCR produce text as their final output, OCR (via Azure AI Vision) extracts text from images, whereas speech-to-text converts audible speech. Thus this option identifies the correct end result but the wrong input source and service.

• ✓

  Technology that extracts text from images; provided by Azure AI Vision

  Why this is correct

  Optical Character Recognition (OCR) is the technology that extracts text from images, and in Azure it is provided by the Azure AI Vision service through the Read API. The Read API analyzes images, PDFs, and TIFF files to detect text regions, then returns the recognized words, their bounding boxes, and confidence scores. It supports both printed and handwritten text, making it the direct answer to the question's description of extracting text from images. Unlike translation or speech processing, OCR operates purely on visual input to produce machine-readable text.

• ✗

  Language translation; provided by Azure AI Translator

  Why it's wrong here

  Azure AI Translator performs machine translation, converting existing text from one language to another; it does not detect or localize text within an image. The service accepts plain text or document formats, not raw image pixels, so it has no OCR pipeline. Extracting text from an image is a vision task handled by Azure AI Vision's Read API, which is a necessary prerequisite before translation can occur. Thus translation is a downstream language service, not the text-extraction technology.

• ✗

  Handwriting analysis for personality assessment; provided by Azure AI Face

  Why it's wrong here

  Azure AI Face detects faces, analyzes facial attributes, and performs identity verification; it does not interpret handwriting or infer personality traits. Handwriting analysis for personality assessment, commonly called graphology, is not a capability of any Azure AI service, including Vision or Language. Azure AI Vision's Read API can recognize handwritten text from images, but the output is only the recognized characters and layout, not psychological insight about the writer. Therefore this option conflates OCR accuracy with a pseudoscientific assessment and points to the wrong Azure service.

Go deeper

Related to this question