7 terms
Facial recognition is a computer vision technique that identifies or verifies a person by comparing a numerical encoding of their face with stored templates.
Image classification is the computer vision task of assigning one or more labels from a fixed set of categories to an entire image based on its…
Image segmentation is the computer vision task of assigning every pixel of an image to a class or object, producing precise masks instead of boxes.
Object detection is the computer vision task of finding objects in an image and labeling each with a class, a bounding box and a confidence score.
OCR (optical character recognition) is the computer vision task of converting text in images and scanned documents into machine-readable, searchable text.
Pose estimation in computer vision locates the keypoints and orientation of people or objects in images and video to describe their posture or position.
A vision transformer is a computer vision model that splits an image into patches and processes them as tokens with self-attention instead of convolutions.