Computer Vision

Optical character recognition (OCR) is technology that converts images of text, such as scanned documents and photographs, into machine-readable text that software can search, edit and process.

Facial recognition is technology that identifies or verifies a person from an image of their face by converting facial features into a numeric template and comparing it with stored templates.

Image segmentation is the computer vision task of labelling every pixel in an image, producing exact object outlines rather than rectangular boxes.

Object detection is the computer vision task of finding objects in an image and marking where each one is with a bounding box, along with a class label and confidence score.

Image classification is the computer vision task of assigning one or more labels to an entire image, such as deciding whether a photo shows a defective or acceptable product.

Computer vision is the field of AI concerned with enabling machines to interpret images and video, covering tasks from classifying photos to detecting objects, reading text and understanding scenes.

Generative vision AI refers to AI that creates or modifies visual content, including image generation, editing, upscaling, video generation and 3D reconstruction.

Pose estimation is the computer vision task of detecting the positions of body joints, called keypoints, to determine how a person or object is positioned and how it moves.

Visual question answering (VQA) is the task of answering a natural-language question about an image, combining visual understanding with language reasoning to produce a text answer.

Image captioning is the task of generating a natural-language description of an image, combining a vision model that understands the picture with a language model that writes about it.