Page 253 - Ai Book - 10

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 people’s life, such as monitoring security, autonomous driving
and so on.

u Image Classification: Image Classification problem refers to the task of assigning an input image one label
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 Object Recognition
collection of related computer vision tasks that involve
identifying objects in digital photographs. The process of Image Object
Image classification is to predict the class of one object Classification Localization
in an image. Object localization refers to identifying
the location of one or more objects in an image and Object
drawing a bounding box around their extent. Detection

u Object Detection: In simple words, the term “Object
detection” combines the tasks of object localisation Object
and object classification into one. Object detection Segmentation
algorithms are used in object detection techniques to extract features and identify instances of an object. It
is commonly used in applications such as image retrieval and automated vehicle parking systems.

u Instance Segmentation: Object segmentation is one of the challenging tasks in the field of computer vision
that requires the prediction of object instances and their per-pixel segmentation mask. This makes it a
hybrid of semantic segmentation and object detection.
Image Classification Classification with localization Detection

“Car” “Car”

One object Multiple object

Object detection is one of the critical components to support autonomous driving.

FUNDAMENTAL CONCEPTS OF IMAGES

In your daily life, you have seen a lot of images around you either on your mobile phones, TVs, or computers. The
word “image” is derived from the latin word “imago” which means an artifact that represents visual perception
of a thing or an object. But , while seeing different types of images, have you ever thought about the various
questions that revolve around images like:

127
127