Page 250 - Ai Book - 10

5 5 Computer V
Computer Visionision

u Applications of Computer Vision u Convolution Network
u Tasks Involved in Computer Vision u Kernel Matrix
u Fundamental Concepts of Images u Neural Network
u Basics of Image u Deploying a CNN
u Open Source Computer Vision

In the previous chapters, you have learnt that a digital technology which is used for teaching machines how to see and
perceive the human world is known as Computer vision. As we all know, computers can mimic human intelligence
using artificial intelligence. Humans can see things, analyse them, and then take actions based on what they see.
Computer vision is a branch in the Domain of AI that enables computers to analyse meaningful information from
images, vidoes, and other visual inputs.
APPLICATIONS OF COMPUTER VISION

As you know, Computer Vision is a branch of artificial intelligence that enables computers to visualise and
recognise images, processing them as humans do. Using images from cameras and videos, deep learning models
enable machines to accurately identify and classify the objects. Computer vision, a special domain of AI is a
mature and reliable technology that can save us time, improve the quality and ultimately generate cost savings.
The various applications of Computer Vision are as follows:

u Manufacturing: In the manufacturing industry, the closely allied field of
machine vision has long been used for automated inspections, identifying
defective products on the production line and for remote inspections of
pipelines and equipment. The technology is also used to automate and
optimize operational and control processes, by flagging irregular events or
inconsistencies.

u Social Networking Applications : Have you ever thought about the
special filters that are used in these applications (Snapchat and
Instagram) to identify the faces in the picture? These applications use
computer vision technology to identify the facial dynamics of the
person and apply the facial filter selected.

u Google Translate: Google translate, a Google application launched
in 2019 uses computer vision technology to translate large blocks
of text without having to type word-for-word in the app. In simple
terms, if a user doesn’t know the language in which he/she is trying
to translate, Google Translate’s camera feature can easily detect the
source language.

124
124