Scribd
Upload
1 views

Computer Vision

The document outlines the differences between human vision and computer vision, emphasizing that CV uses algorithms for image interpretation. It covers key concepts such as convolution, the role of machine learning, and applications of CV like facial recognition and autonomous vehicles. Additionally, it introduces OpenCV as a library for computer vision tasks and explains the structure of Convolutional Neural Networks.

Uploaded by

srishithsrinand
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
1 views

Computer Vision

The document outlines the differences between human vision and computer vision, emphasizing that CV uses algorithms for image interpretation. It covers key concepts such as convolution, the role of machine learning, and applications of CV like facial recognition and autonomous vehicles. Additionally, it introduces OpenCV as a library for computer vision tasks and explains the structure of Convolutional Neural Networks.

Uploaded by

srishithsrinand
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 3

1.

Human vision relies on perception and experience, while Computer


Vision (CV) uses algorithms to interpret images, focusing on patterns,
features, and data without subjective understanding.

2.Computer Vision is an AI field enabling machines to interpret images or


videos, often using Machine Learning to train models for tasks like
recognition and analysis.

3.Object detection identifies objects and their locations in images, while


object classification only determines the object type without pinpointing
location.

4.Applications of CV include facial recognition, autonomous vehicles,


medical imaging, industrial inspection, and augmented reality.

5. Concept of convolution in computer vision


Convolution is a mathematical operation used to filter or process images by
applying a kernel (small matrix) to enhance features like edges or textures.

6. Purpose of convolution
It detects patterns, like edges or shapes, in images and simplifies image
data for analysis.

7. Introduction to OpenCV
OpenCV is a free, open-source library for computer vision tasks like image
and video processing, object detection, and face recognition.

8. Tasks performed by computer vision


Examples:

Object detection
Image classification

Facial recognition

9. Difference between grayscale and RGB images

Grayscale: Black-and-white images with shades of gray.

RGB: Colored images with red, green, and blue channels.

10. Role of Machine Learning in computer vision


Machine Learning helps analyze patterns in image data to recognize
objects, faces, or scenes automatically.

11. What is kernel in image processing?


A kernel is a small matrix (e.g., 3x3) used in convolution to extract features,
like edges or blurring.

12. Explain the layers in CNN (Convolutional Neural Network)

Convolution layer: Detects patterns.

Pooling layer: Reduces image size.

Fully connected layer: Makes decisions based on learned features.

13. Given an image with dimensions 1024x768 pixels, calculate the total
number of pixels.
Multiply width × height:
1024 × 768 = 786,432 pixels.

14. Perform convolution with given kernel and input matrix.


Let me solve this for you. One moment!

15. Convolution result


The output matrix after applying the given kernel to the input matrix is:

[[37, 47],
[67, 77]]

You might also like