Scribd
Upload
11 views

UNIT 2

Uploaded by

aarthir88
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
11 views

UNIT 2

Uploaded by

aarthir88
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/ 4

lOMoARcPSD|43574471

QB Unit 2 CCS338- Computer Vision

Computer Vision (Anna University)

Scan to open on Studocu

Studocu is not sponsored or endorsed by any college or university


Downloaded by Aarthi R ([email protected])
lOMoARcPSD|43574471

VELAMMAL INSTITUTE OF TECHNOLOGY, CHENNAI- 601204


DEPARTMENT OF ELECTRONICS AND COMMUNICATION ENGINEERING

Focussed Question Bank

Subject Code & Name : CCS338- COMPUTER VISION Unit : 2


Part-A ( 2 Marks)

1
1. Describe segmentation.
The process of dividing an image into different regions based on the characteristics of
pixels to identify objects or boundaries to simplify an image and more efficiently analyze it.

2 Define line and edge.

LINE DETECTION
It is an algorithm that takes a collection of n edge points and finds all the lines on
which these edge points lie.
EDGE DETECTION
Edge detection is the process of identifying boundaries in an image to identify
objects in an image.

3 List some of the popular segmentation algorithms.


*K-Means clustering
*Mean shift clustering
*Graph cut
*Normalized cut
*Minimum cut

4 State RANSAC algorithm


When the number of measurements is quite large,it may be perfectable to only score a
subset of the measurements in an initial round that selects the most plausible hypothesis for
additional scoring and selection.This modification of RANSAC, which can significantly speed
up its performance, is called preemptive RANSAC.
S = log(1-P)/log(1-p^k)

5. State Grab cut algorithm.


Grab Cut algorithm is one of the most popular method in the field of image segmentation. It
uses texture information and boundary information of image, and achieves good segmentation
results with a small number of user interaction.

6. List the Feature detectors and feature descriptors.


A generic neighborhood procedure or feature detection applied to the image may also
produce features. A feature descriptor is the information retrieved from images in the form of
numerical values that are challenging for a human to comprehend and correlate.

7. Define vanishing point.

Downloaded by Aarthi R ([email protected])


lOMoARcPSD|43574471

A point on the image plane where the two-dimensional perspective projections of mutually
parallel lines in three-dimensional space appear to converge is called as vanishing point.
8. Define region splitting
Region splitting is a technique that starts with the whole image as a single region and
recursively divides it into smaller regions based on some homogeneity criterion.

9. Define Region merging.


It is a process which groups adjacent image pixel's or sub-regions into larger regions based
on the probability that they will have the same statistical distribution of intensity.

10. Define Watershed.


M A watershed is a transformation defined on a grayscale image. The watershed
transformation treats the image it operates upon like a topographic map, with the brightness of
each point representing its height, and finds the lines that run along the tops of ridges.

11. Define Normalized cut.


The normalized cut criterion measures both the total dissimilarity between the different
groups as well as the total similarity within the groups.

12. Define graph cut.


A graph G = (V,E) can be partitioned into two disjoint sets, by simply removing
edges connecting the two parts.

13. State B-spline algorithm.

Part-B
1. Explain Harris corner and SIFT in detail
The harris corner detector is a corner detection operator that is commonly used in computer
vision algorithm to extract corners and infer features of an image.
Explanation-4marks
Harris corner-4marks
Sift is an algorithm in computer vision to detect and describe local features in images. The
SIFT technique involves generating a scale space of images with different scales and then
using the Difference of Gaussian (DoG) method to identify keypoints in the images. It also
involves computing descriptors for each keypoint, which can be used for feature matching and
object recognition.

SIFT – 4marks
Diagram – 2 marks

2. Illustrate the Hough transform in detail for line detection.

Downloaded by Aarthi R ([email protected])


lOMoARcPSD|43574471

While curve approximation with polylines each of lead to successful line extractions.
*many lines
*those collision lines
*those extended lines
* each edge point votes.
Explanation – 4marks
Diagram – 4 marks

3. Explain the edge detection in detail.


Edge detection is the process of identifying boundaries in an image to identify objects in an
image.
Explanation – 6marks

4. Summarize segmentation and explain the region splitting, region merging and watershed
techniques used in detail.
Image segmentation is the process of dividing an image into several disjoint small local
areas or cluster sets according to certain rules and principles. The watershed algorithm is a
computer vision technique used for image region segmentation. The segmentation process
will take the similarity with adjacent pixels of the image as an important reference to connect
pixels with similar spatial positions and gray values. Constitute a closed contour(outline), and
this closure is an important feature of the watershed algorithm. In short, it is an algorithm that
correctly determines the “outline of an object“.

Explanation – 4marks
Region splitting – 4marks
Region merging – 4marks
Watershed techniques – 2marks

5. Explain Normalized cut and Mean Shift algorithm in detail.

While bottom up merging techniques aggregate regions into coherent and mean shift techniques
try to find clusters of similar pixels using mode finding ,the normalized cut technique
introduced by shi andmalik(2000) examines the affline between nearby pixels and tries to
separate groups that are connected by weak affinities.
Explanation – 4 marks
Diagram – 4marks
Mean shift – 6 marks.

Explain the SIFT descriptor and discuss the feature matching strategy and performance
measures.

6. Explain active contour in detail.


7. Explain K-means clustering in detail.

Downloaded by Aarthi R ([email protected])

You might also like