[TBD]Role of computer vision in data science

Introduction

Laymen explanation

The effects of recent advances on the computer vision field have been astounding. Accuracy rates for object identification and classification have gone from 50 percent to 99 percent in less than a decade — and today’s systems are more accurate than humans at quickly detecting and reacting to visual inputs.

Technical explanation

Computer vision is a field of artificial intelligence that trains computers to interpret and understand the visual world. Using digital images from cameras and videos and deep learning models, machines can accurately identify and classify objects — and then react to what they “see.”

Fields which support computer vision

• Mathematics - Statistics, Geometry, Optimisation

• Machine learning - Cognitive vision

• Robotic vision

• Signal processing

• Physics

• Imaging

• Neurobiology

Challenges with computer vision

• • Very high dimension for images due to high resolution

  • Finding detail in the picture is hard. For example, finding bird in a picture

  • What is perceived and what is cognised? For example, whether it is rope or snake

  • Verifiability of mathematical/physical models is non-trivial

Reference

https://youtu.be/rfAvjCf1_ZI

https://www.sas.com/en_us/insights/analytics/computer-vision.html

https://youtu.be/rfAvjCf1_ZI?t=1833