Scribd
Upload
37 views

Computer Vision Sheet (3) : Recognition, Feature Extraction, Segmentation

This document contains 10 questions about various computer vision concepts and techniques including: defining terms like image enhancement and filters; the difference between detection and classification; segmentation methodologies; applying filters like Sobel and ideal high/low pass filters; finding Fourier transforms and inverse Fourier transforms; working with histograms to find thresholds for segmentation; and applying morphological opening.

Uploaded by

Hussein Mohamad Elnaggar
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
37 views

Computer Vision Sheet (3) : Recognition, Feature Extraction, Segmentation

This document contains 10 questions about various computer vision concepts and techniques including: defining terms like image enhancement and filters; the difference between detection and classification; segmentation methodologies; applying filters like Sobel and ideal high/low pass filters; finding Fourier transforms and inverse Fourier transforms; working with histograms to find thresholds for segmentation; and applying morphological opening.

Uploaded by

Hussein Mohamad Elnaggar
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/ 3

Computer Vision

Sheet (3)

1- Clarify the following terms in the context of computer vision:


Image enhancement, median filter, low pass filter, image morphology, image
recognition, feature extraction, segmentation.
2- What is the difference between detection and classification in computer
vision?
3- What are the segmentation methodologies in computer vision? Explain
briefly.

4- Apply the Sobel differential filter to the matrix

50 4 10 200
1 3 15 220
215 87 5 180
100 6 12 15

5- The following matrix is the Fourier frequency domain matrix for an image
matrix. Find the resultant matrix after applying Ideal high pass filter with
cutoff frequency 1.002. Use the resultant matrix to find the inverse Fourier
transform for the element f (0, 0).

𝟑 + 𝒋𝟐 𝟓 𝟏𝟎 + 𝒋𝟑
[ 𝟓 𝟎 𝟎 ]
𝟎 𝟏 𝟑 + 𝒋𝟕
6- For the following matrix, find Fourier transform for the least & the highest
frequency elements. For the two elements, find the phase & power.

0 5 10 0
5 7 20 0
0 5 20 5
0 5 4 0
7- The following are gray count taken from an image matrix:
Gray 15 25 30 40 65 100 110 118 130 150 170 200 220
level
Gray 10 150 250 1500 260 120 20 250 400 1500 400 200 150
count
For the histogram above, find the equalized histogram then from the equalized
histogram find the probabilistic threshold assuming normal distribution &
object/ Background of image.

8- The following are gray count assuming dark object in a white Background.
Find out the segmentation threshold based on symmetrical background, show
the steps & optimal threshold.
Gray 10 5 20 30 65 100 110 118 120 150 170 220
level
Gray 10 100 500 100 10 10 100 500 1000 400 100 20
count

9- The following matrix is the Fourier frequency domain matrix for an image
matrix. Find the resultant matrix after applying Ideal low pass filter with
cutoff frequency 1.99. Use the resultant matrix to find the Inverse Fourier
Transform for the least and the highest frequency elements?

10- Using the binary matrix generated from the labeling process of the matrix
below giving the connectivity set as {10}, and N4, followed by setting the
label set pixels to one and the rest to zero. Find the resultant matrix from
applying the opening morphology operation using the following operator:-
1 1 1
1 1 1
1 1 1

*****************good luck*******************

You might also like