Scribd
Upload
93 views2 pages

Computer Vision Assignment

Uploaded by

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

Computer Vision Assignment

Uploaded by

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

COMPUTER VISION ASSIGNMENT

REG NO: 21BCE9056


NAME: GURU SUBHASH BATHULA
1. RGB to Grayscale Conversion:
 The code reads an image and converts it to grayscale using OpenCV. It
then uses Matplotlib to display both the original RGB image and the
grayscale image side by side.
2. Histogram Creation (Grayscale):
 This reads the image in grayscale and calculates the pixel intensity
histogram. It then plots the histogram, showing the distribution of pixel
values from 0 to 255.
3. Color Histogram:
 This code reads a color image, splits it into its Red, Green, and Blue
channels, and calculates the histogram for each channel. The histograms
for all channels are plotted on the same graph.
4. Boundary Detection:
 It applies various edge detection algorithms like Sobel, Prewitt,
Laplacian, and Canny on a grayscale image. Each method highlights the
edges in different ways and all the results are plotted together.
5. Edge Detection:
 Similar to boundary detection, this code applies multiple edge detection
techniques (Sobel, Prewitt, Laplacian, and Canny) to detect edges in a
grayscale image. The results are displayed in a grid.
6. Line Detection (Hough Transform):
 This code first detects edges using the Canny edge detector, then uses
the Hough Line Transform to detect straight lines in the image. The lines
are drawn in red on the original image.
7. Corner Detection:
 The Harris and Shi-Tomasi corner detection algorithms are used here to
find and highlight corners in an image. Harris corners are marked in red,
while Shi-Tomasi corners are shown with green circles.
8. Space and Scale (SIFT Keypoint Detection):
 The SIFT (Scale-Invariant Feature Transform) algorithm detects keypoints
in an image. These keypoints represent distinct features in the image,
which are drawn and displayed on the original image.
9. Gaussian Pyramid:
 A Gaussian pyramid is constructed by repeatedly downscaling the image
using Gaussian blurring. Each level of the pyramid represents a smaller
version of the image. The code displays all pyramid levels alongside the
original image.
10. Laplacian Pyramid:
 Similar to the Gaussian pyramid, but each level of the pyramid is created
by subtracting the next level from the previous one to capture fine
details. The Laplacian pyramid helps in blending or compressing images.
11. GRBR Filter:
 This code applies a Gaussian Radial Basis Function (GRBR) filter to
smooth the image using a 2D Gaussian kernel, reducing noise while
preserving edges. Both the original and filtered images are displayed for
comparison.
12. Discrete Wavelet Transform (DWT):
 DWT decomposes an image into four components: approximation (cA),
horizontal (cH), vertical (cV), and diagonal (cD) details. These
components help in tasks like image compression or feature extraction.

You might also like