Page 98 - Code Craft Computer-8

• Retail Stores: One of newest and most innovative applications of computer vision is its use
in retail shopping. Amazon Go is an innovative retail store where there are no cashiers or
checkout stations. It is a partially automated store that is created by utilising computer
vision.

• Autonomous Vehicles: Self-driving automobiles use computer vision extensively and are
amongst the most challenging applications of computer vision, since in autonomous vehicles
it can be a life-or-death issue, whether it is for the driver or other road users. Automated cars
from companies, like Tesla using computer vision, can detect the 360-degrees movements of
pedestrians, cyclists, vehicles, etc.

• Facial Recognition: Facial recognition is a technology that is capable of identifying or
verifying a person from a digital image or a video. It is used as security for unlocking devices
and also by investigation agencies to identify criminals. Social media applications, like
Facebook, use it for identifying and tagging people.

Natural Language Processing (NLP)
As humans, you use languages without much effort because you have been conditioned to
understand languages from a young age. This process is quite complex since words can be

combined in infinite ways and have different meanings depending on the context they are being
used in and the cultural background of the communicators.
For example, the meaning of ‘bat’ is different in the following two sentences:

• I saw a bat hanging upside down on a tree.
• The player bought a new bat for the tournament.
Humans can master a language quite easily, but the vague characteristics and ambiguity of natural

languages are the two biggest aspects that make it difficult for a machine to understand and
communicate in a natural human language. In order to narrow the communication gap between
machines and humans, the Natural Language Processing (NLP) domain of artificial intelligence is
used.
Natural Language Processing (NLP) is the ability of machines to understand and interpret human

language the way it is written or spoken. NLP helps machines comprehend, interpret, and
manipulate natural language used by humans. For example, when you type something on your
smartphone using a search engine like Google, it comes up with word suggestions based on what
you are currently typing and what you usually type.
How NLP works?: A typical verbal interaction between an NLP system and a human is given
below:

Communication
The machine between
The audio The machine
The machine evaluates the The text is machine and the
A person talks records this signal is processes data possible decoded by person through
to machine. converted into action,
audio signal. responses and the machine. verbal or
into text. audio or text.
action. text outputs or
action taken.

98