CSE509F23_A3

pdf

School

Arizona State University *

*We aren’t endorsed by this school

Course

509

Subject

Computer Science

Date

Dec 6, 2023

Type

pdf

Pages

2

Uploaded by SuperHumanOstrich3671

Report
CSE 509 Digital Video Processing Assignment 3 Due: Sunday, October 8th at 11:59pm Submit a single PDF with your responses to Gradescope. 1. Write python code to demonstrate the superiority of SSIM to MSE for assessing the quality of images with structural distortions. Use the original nadia image provided on our website to create an image with impulse noise and one with structural distortions. Calculate the SSIM and the MSE in both cases and show that the SSIM is a better measure of the distortion. Produce a display that shows similar results to this: Also, calculate the MSE and SSIM for an image with a very ‘tiny’ amount of noise to see that you get the expected values for a nearly perfect image: 10 pts. 10 pts.
2. a) Write Python code to read 10 frames of the ‘foreman’ clip from our website. You can use code similar to the following: cap = cv2.VideoCapture('Foreman360p.mp4') if (cap.isOpened()== False): print("Error opening file") vid = [] for x in range(10): ret, frame = cap.read() frame = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY) if ret == True: vid.append(frame) print(frame.shape, ' ', frame[0][0].shape) cap.release() b) Add Gaussian noise to vid to create a noisy video. c) Also create a version with structural distortions. d) Calculate the MSSIM for the two videos and compare. The MSSIM is described in the final slides of our SSIM lecture. There are some parameters that you can decide on so you may not get the same results as others but the values of the MSSIM should reflect the quality of the videos. 5 pts. 5 pts. 5 pts. 15 pts.
Your preview ends here
Eager to read complete document? Join bartleby learn and gain access to the full version
  • Access to all documents
  • Unlimited textbook solutions
  • 24/7 expert homework help