Page 299 - AI Computer 10

The following screen appears.

Click the LET’S PLAY button to start the game. Try to locate the object shown within the given time
frame. Click NEXT EMOJI button to continue the game after locating the given emoji to continue the
game.
Once the game is over, answer the following questions:
● How many games have you played? _______________________
● Write the number of games in which you are the winner. _______________________
● Which kind of strategy did you adopt to win the game? _______________________
● Was the computer able to identify all the items you bought in front of it? ______________________
● Did the lighting effect of the room affect the identification process of
items by the machine? ______________________

TASKS INVOLVED IN COMPUTER VISION

Image Classification, object recognition, object detection, semantic segmentation, instance segmentation, etc. are
some special kind of tasks that are involved in the field of computer vision. These tasks can be performed to get certain
information from the input image which can be directly used for prediction or forms the base for further analysis.
Among these tasks, object detection is one of the most important and challenging branches of computer vision, which
has been widely applied in everyday life, such as security systems and autonomous driving.
u Image Classification: Image Classification problem refers to the task of assigning a label to an input image
from a fixed set of categories. Image classification is simple in nature, but it is one of the core problems in
the field of computer vision which has a large variety of practical applications.
u Object Recognition (Classification and Localisation): Object Recognition is a general term to describe
a collection of related computer vision tasks that involve identifying objects in digital photographs. The
process of image classification is to predict the category of an object in an image. Object Localization refers
to identifying the location of one or more objects in an image and drawing a bounding box around their
extent.
Object
Recognition

Image Object
Classification Localization

Object
Detection

Object
Segmentation
165
165