Scribd Logo
Upload

Welcome to Scribd!

  • 238 views

    Assignment 01 - F19

    Uploaded by

    Maria
    This document provides instructions for an assignment on computer vision tasks including image manipulation, filtering, and edge detection. Students must: 1) Load and analyze an image file, apply brightness scaling, and histogram equalization. 2) Write a function to convolve an image with a filter, handling boundary conditions. 3) Write a function to detect edges in an image by smoothing, calculating gradients, and performing non-maximum suppression. Students must submit code, results, and a report in a zip file by the due date. Late submissions and plagiarized work will not be accepted.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd

    Assignment 01 - F19

    Uploaded by

    Maria
    238 views2 pages
    This document provides instructions for an assignment on computer vision tasks including image manipulation, filtering, and edge detection. Students must: 1) Load and analyze an image file, apply brightness scaling, and histogram equalization. 2) Write a function to convolve an image with a filter, handling boundary conditions. 3) Write a function to detect edges in an image by smoothing, calculating gradients, and performing non-maximum suppression. Students must submit code, results, and a report in a zip file by the due date. Late submissions and plagiarized work will not be accepted.

    Original Description:

    solve this to improve your knowledge

    Original Title

    ASSIGNMENT 01_F19

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    This document provides instructions for an assignment on computer vision tasks including image manipulation, filtering, and edge detection. Students must: 1) Load and analyze an image file, apply brightness scaling, and histogram equalization. 2) Write a function to convolve an image with a filter, handling boundary conditions. 3) Write a function to detect edges in an image by smoothing, calculating gradients, and performing non-maximum suppression. Students must submit code, results, and a report in a zip file by the due date. Late submissions and plagiarized work will not be accepted.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    238 views2 pages

    Assignment 01 - F19

    Uploaded by

    Maria
    This document provides instructions for an assignment on computer vision tasks including image manipulation, filtering, and edge detection. Students must: 1) Load and analyze an image file, apply brightness scaling, and histogram equalization. 2) Write a function to convolve an image with a filter, handling boundary conditions. 3) Write a function to detect edges in an image by smoothing, calculating gradients, and performing non-maximum suppression. Students must submit code, results, and a report in a zip file by the due date. Late submissions and plagiarized work will not be accepted.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    You are on page 1of 2

    COMPUTER VISION

    ASSIGNMENT 01

    Due Date: 12th November 2019 Total Marks: 60

    INSTRUCTIONS:

     Late submissions will not be accepted.


     You can complete this assignment in a group of 2 students.
     You should write your own code. Code copied from online or from fellow members will not be accepted. Plagiarism
    will not be tolerated.
     What do you hand in: A Zip file that has:
    a. Images (input and output) clearly labeled
    b. Code you used for each question.
    c. Finally a report in PDF file with clearly mentioned group members’ names and registration number. The report
    must shows all the results you acquired for the problem set.
    d. You must upload the assignment on FOIT.LMS in a compressed file.
    e. Only one member of the group must upload the files.

    IMAGE MANIPULATION
    1. Load the image “Q1.tif” into MATLAB. Originally, it will be in the form of a 2D-array of unsigned integers.
    Check and report
    a. how many bits per integer the image has, and
    b. what is its width and height?
    2. We would like to bring the image to a more typical average brightness. Apply a scaling factor to all pixels,
    so that the minimum pixel value becomes 0 and the max pixel value becomes 255. Include the final image
    in your report, as well as the MATLAB code you used to produce it.
    3. Next perform the histogram equalization on the image “Q1.tif” and compare the results acquired in the
    previous question.
    4. Next, we would like to double the contrast of the pixels in the middle brightness range. Specifically, take
    your result from Question 03 and replace each pixel's intensity i with a new intensity i  , where

    i  2   i  128  128

    Threshold i  so that 0  i  255 (you can use the “uint8” function). Include your MATLAB code and the
    resulting contrast-boosted image in your report.
    IMAGE FILTER

    5. Write a function that convolves an image with a given correlation filter


    function [img1] = myImageFilter(img0, h)
    As input, the function takes a greyscale image (img0) and a correlation filter stored in matrix h. The
    output of the function should be an image img1 of the same size as img0 which results from correlating
    img0 with h. You can assume that the filter h is odd sized along both dimensions. You will need to handle
    boundary cases on the edges of the image. For example, when you place a correlation mask on the top
    left corner of the image, most of the filter mask will lie outside the image. One solution is to output a zero
    value at all these locations. The better thing to do is to pad the image such that pixels lying outside the
    image boundary have the same intensity value as the nearest pixel that lies inside the image. You can
    call MATLAB's function to pad array. However, your code can not call on MATLAB's imfilter, conv2,
    convn, filter2 functions, or any other similar functions.

    EDGE DETECTION

    6. Write a function that finds edge intensity and orientation in an image.


    function [img1] = myEdgeFilter(img0, sigma)
    The function will input a greyscale image (img0) and scalar (sigma). Sigma is the standard deviation of
    the Gaussian smoothing kernel to be used before edge detection. The function will output img1, the edge
    magnitude image.
    First, use your convolution function to smooth out the image with the specified Gaussian kernel.
    This helps reduce noise and spurious fine edges in the image. Use fspecial to get the kernel for the
    Gaussian filter. The size of the Gaussian filter should depend on sigma (e.g., hsize = 2 * ceil(3 *
    sigma) + 1). The edge magnitude image img1 can be calculated from image gradients in the x direction
    and y direction. To find the image gradient imgx in the x direction, convolve/correlate the smoothed
    image with the x-oriented Sobel filter. Similarly, find image gradient imgy in the y direction by convolving
    the smoothed image with the y-oriented Sobel filter. You can also output imgx and imgy if needed. In
    many cases, the high gradient magnitude region along an edge will be quite thick. For finding lines its
    best to have edges that are a single pixel wide.
    Towards this end, make your edge filter implement non-maximum suppression that is for each
    pixel look at the two neighboring pixels along the gradient direction and if either of those pixels has a
    larger gradient magnitude then set the edge magnitude at the center pixel to zero. Map the gradient angle
    to the closest of 4 cases, where the line is sloped at almost 0, 45, 90, and 135. For example, 30 would
    map to 45. Your code cannot call on Matlab's edge function, or any other similar functions.

    You might also like