Page 108 - TP_V5.1_C8_fb
P. 108
Human Vision System
bowl, oranges,
bananas, lemons,
peaches
Eye Brain
(sensing device responsible for capturing interpreting device responsible for
images of the environment) understanding the image content
Computer Vision System
bowl, oranges,
bananas, lemons,
peaches
Input Sensing device Interpreting device Output
How does Computer Vision Work?
The two technologies required to accomplish these are:
Machine Learning (Deep Learning)
Convolutional Neural Network (CNN)
Machine learning enables a computer to understand the context of visual data by using algorithmic
models. To achieve this, enough data needs to be fed through the model so that the computer can
teach itself to recognise images.
A Convolutional Neural Network (CNN) helps a machine learning model to process the image by
breaking it down into tiny parts called pixels. It then transforms it into digital data by applying
algorithms before comparing the captured images with those stored in the database. These
systems are used to identify an individual based on their facial features like the spacing of their
eyes, ears, chin, etc.
Examples of AI Applications based on Computer Vision
Face recognition systems are used at the workplace and schools to mark attendance.
Biometric software is used by law enforcement agencies to scan faces in CCTV footage.
Image enabled searches at online shopping websites using camera.
Selfie-based authentication for banking and payments apps using face recognition technology.
NATURAL LANGUAGE PROCESSING
Natural Language Processing (NLP) is the ability of an AI system to understand human language
as it is spoken. Computer cannot understand the language we speak. Hence, we need software
and programming languages to communicate with the computer.
106 Premium Edition-VIII

