Scribd
Upload
18 views2 pages

Ch-5 Computer Vision

Uploaded by

gtcxgamer
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
18 views2 pages

Ch-5 Computer Vision

Uploaded by

gtcxgamer
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 2

L- 5 (Computer vision)

1. What is computer vision?


It is the domain of artificial intelligence which read,understanbd and analyse visual data.
2. What are the applications of Computer vision?
Applications of Computer Vision are:-
1. Object Recognition:- This branch of computer vision AI is concerned with detecting one or more
things in an image or video. Surveillance cameras, for example, intelligently recognize humans
and their activities (no movement, things such as firearms or knives, etc.) so those suspicious
activities are flagged.
2. Object Classification: Google Lens is an application with google that can be used to identify any
image by clicking a picture from the real world. It uses the concept of object detection by
identifying an object in images. For example, if you are unaware of a flower name in your
garden, click a picture with your phone using Google Lens application and it will reveal its name
along with the description.
3. Categorization of Photos in your Phone: Smartphones use CV to categorize the photos on your
phone under the different categories. For example, if you try to search for "Cakes" in the photos
folder it will show you all the pictures with cake in it.
4. Face Lock in Smartphones: Nowadays smartphones come with a new security system of using
face recognition to lock and unlock phones. It uses the front camera to detect the features of
the face and save it. Once it is stored, every time to unlock it matches the input face with the
features already stored in it.
5. Self-driving Cars: CV is used in self-driving cars to recognize lamp posts and to tell the difference
between pedestrians and stop signs. Image classification technique allows self-driving cars to
identify where the road is and what all obstacles are, when to stop or keep driving on the road.
Companies like Tesla and Google are building self-driving cars.
6. Unusual behavior Detection: CV is used to identify faces in CCTV footage and also in real time at
airports to help identify and track unusual activities or behavior.

3. What is a Pixel ?Give any two important features of a Pixel ina digital image.
Pixel stands for “Picture Element”. It is the smallest unit of information in a digital image. These pixels
are arranged in a 2-dimensional grid to form a complete image, video, text, or any visible thing on a
digital platform. A pixel can have only one color at a time.
4. What do you mean by the term-Image Features?
Ans:- In computer vision an image feature is simply a piece of information about the content of an
image. It can be an edge, corners, start point or end point that can be taken.
5. Define the following
Grey scale image:- It is the image which has a range of shades of grey .These images have only
two colors ie Black and white.Black is at weakest intensity to white at the strongest intensity. It
means, the shade range start with 0 (pure black) and ends with 255 (pure white).

RGB Images:- These images are made up of three primary colors Red,Green and Blue.All the
colours are made by combining different intensity of red,green and blue.
6. Explain the task used in Computer vision application for single object.
Ans:- Classification:- It is the process of finding out the class/category of the input image.The input
image is processed using machine learning algorithm and classified into predefined categories.
Classification+Localisation:- Localisation means where the object is in the image.
The combined task of classification and localisation means processing the input image to identify its
category and location.
7. Explain the task used in Computer vision application for multiple objects.
Ans:- Multiple Objects means giving multiple images as input to the Computer Vision application. It can
be further divided into two categories:
• Object Detection: It 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: It 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).

You might also like