Page 319 - AI Computer 10

Step 18: Click the Predictions icons. A table appears that shows the prediction of test data based on
Logistic Regression.

K Keyey TTermserms

u Computer Vision
The domain of AI that enables machines to interpret and understand the visual world, processing information
from images.
u Image Classification
The task of assigning a label to an input image from a fixed set of categories.
u Object Recognition
Collection of related computer vision tasks that involve identifying objects in digital photographs.
u Object Localisation
Identification of the location of one or more objects in an image and drawing a bounding box around their
extent.
u Object Segmentation

Predicting individual object instances and creating pixel masks to distinguish them from other such instances.
u Pixel
The smallest unit of a digital image, representing individual point of colour.
u Resolution
Term used to describe the crispness and clarity of an image based on the number of pixels contained in it.
u Convolution

The process of multiplying together two arrays of numbers, generally of different sizes, but of the same
dimensionality, to produce a third array of numbers of the same dimensionality.

u Kernel Matrix
A matrix used to perform convolutional computations on an input image matrix to convert it into a desired
output matrix.
u Neural Network
A system of algorithms modelled after the human brain, comprising layers with weights and biases for
pattern recognition.
u Convolutional Neural Network (CNN)
A specialised neural network designed for image-related tasks, featuring convolutional layers for feature
extraction.

185
185