Page 257 - AI Ver 1.0 Class 10
P. 257

Single Objects
                 This means giving one image as input to the Computer Vision application. It can be further divided into two
                 categories:

                 Classification

                 Classification  is  the  process  of  finding  out  the  class/category  of
                 the  input  image.  The  input  image  is  processed  using  a  machine
                 learning algorithm and classified into predefined categories. These
                 predefined categories are created in a computer by a set of sample
                 images. The most popular architecture used for image classification
                 is Convolutional Neural Networks (CNNs). For example, identifying
                 the image of monument as India Gate.

                 Classification + Localisation
                 Localisation means where the object is in the image. So, this combined task of classification and localisation
                 means processing the input image to identify its category along with the location of the object in the image. For
                 example, Identifying the above image of the monument as India Gate and its location in Delhi, India. These two
                 processes together are applicable only for single objects.


                 Multiple Objects
                 This means giving multiple images as input to the Computer Vision application. It can be further divided into
                 two categories:

                 Object Detection
                 Object detection is the process of identifying or detecting the instances of real-world objects like cars,
                 bicycles, buses, animals, humans, or anything on which the detection model has been trained. This kind of
                 system uses Object detection algorithms to extract the features of the object and after that machine learning
                 algorithms will recognize the instances of an object category by matching it with the sample images already
                 fed into the system. It is commonly used in applications such as image retrieval and automated vehicle
                 parking systems.


                 Instance Segmentation
                 Instance Segmentation is the process of division of an image into smaller objects so that the machine can
                 identify an object from the background or by using information about other objects present along with it in
                 the input image. After it has identified it, then each pixel is given a label on the basis of that. A segmentation
                 algorithm takes an image as input and outputs a collection of regions (or segments).

                                                    Classification                            Instance
                               Classification                         Object Detection
                                                    + Localization                          Segmentation








                                   CAT                 CAT                CAT, DOG              CAT, DOG


                                         Single object                           Multiple objects


                                                                                          Computer Vision   255
   252   253   254   255   256   257   258   259   260   261   262