Computer Vision Glossary

Question 1

Optical Character Recognition (OCR)

Answer 1

The technology that enables machines to convert images of text into machine-readable text data.

Question 2

Azure AI Vision

Answer 2

A service on the Azure platform that provides AI-powered vision capabilities, including OCR.

Question 3

Read API

Answer 3

The OCR engine within Azure AI Vision, used to extract text from images, PDFs, and TIFF files.

Question 4

Machine Learning Model

Answer 4

Algorithms trained on data to recognize patterns and make predictions, used in OCR to identify text elements.

Question 5

Bounding Box

Answer 5

A rectangular region that marks the location of an object within an image, described by its coordinate points.

Question 6

Vision Studio

Answer 6

A graphical user interface within Azure that allows users to access and experiment with AI vision capabilities without needing to code.

Question 7

REST API

Answer 7

A standardized way to interact with web services using HTTP requests, used to programmatically access the Read API.

Question 8

SDK (Software Development Kit)

Answer 8

A set of tools and resources that developers can use to build applications, used for accessing the Read API through programming languages.

Question 9

JSON

Answer 9

A lightweight, text-based data interchange format used to represent data structures, commonly used in APIs to return structured data.

Question 10

Natural Language Processing (NLP)

Answer 10

A field of AI focused on enabling computers to understand, interpret, and generate human language.

Question 11

Face Detection

Answer 11

The process of identifying the presence and location of human faces within an image or video.

Question 12

Facial Analysis

Answer 12

The process of examining specific facial features to derive additional information.

Question 13

Facial Recognition

Answer 13

The process of identifying individuals from their facial features using trained models.

Question 14

Azure AI Face Service

Answer 14

A Microsoft Azure service that provides pre-built algorithms for face detection, recognition, and analysis.

Question 15

Accessories

Answer 15

Objects such as glasses, masks, or headwear that can be detected on a face.

Question 16

Occlusion

Answer 16

The blocking of a face in an image by an object, impacting accuracy of detection and analysis.

Question 17

Limited Access

Answer 17

A policy restricting access to advanced features of the Azure AI Face service, requiring approval from Microsoft.

Question 18

Responsible AI

Answer 18

Microsoft’s approach to AI development, which includes ethical guidelines for the design and implementation of AI technologies.

Question 19

Liveness Detection

Answer 19

The process of determining whether an input source is real or fake to prevent manipulation or spoofing.

Question 20

Convolutional Neural Network (CNN)

Answer 20

A type of deep learning architecture commonly used in computer vision, which uses filters to extract feature maps from images.

Question 21

Deep Learning

Answer 21

A subset of machine learning that uses neural networks with many layers to learn complex patterns from data.

Question 22

Feature Map

Answer 22

An array of numeric values that result from applying a filter to an image, used in deep learning models.

Question 23

Filter (Kernel)

Answer 23

An array of numeric values used to perform convolutional filtering, modifying pixel values in an image.

Question 24

Image Classification

Answer 24

The process of predicting the category or class of an image.

Question 25

Multi-Modal Model

Answer 25

An AI model trained using multiple types of data, encapsulating relationships between image features and text embeddings.

Question 26

Object Detection

Answer 26

The process of detecting and locating specific objects within an image, and classifying them.

Question 27

Pixel

Answer 27

A single point of color in a digital image, represented by numerical values.

Question 28

Resolution

Answer 28

The dimensions of an image, measured in pixels, indicating its quality or clarity.

Question 29

Transformer

Answer 29

A type of neural network architecture commonly used in NLP, encoding words as vector-based embeddings.

Question 30

Vector-based Embedding

Answer 30

An array of numeric values that represent semantic attributes of a word or token.