Computer Vision

Computer vision is the field of AI that enables computers to interpret and understand visual information from images and videos, such as recognizing objects, faces, or text.

Data & AI

Tasks include image classification (what's in this picture?), object detection (where are the objects?), and segmentation (which pixels belong to each object). Modern computer vision is dominated by deep learning, especially convolutional neural networks and, increasingly, transformers.

It powers self-driving cars, medical image analysis, face unlock, and photo search. Images are fed to models as tensors of pixel values, which the network learns to interpret layer by layer.

Examples

Python

import numpy as np

# A tiny grayscale image as a tensor of pixel values
image = np.zeros((3, 3))
image[1, 1] = 255   # one bright pixel
print(image.shape)

Output:

(3, 3)

Learn it in a lesson

See also

Back to the Dictionary