CS631T – Spring 2018

project 2 – Enhancement and Binary Analysis Exercises




Part1: Matlab Coding


Save all solutions in a single m-file. Be sure to place semicolons wherever appropriate, to suppress unnecessary console output, such as when loading images into memory, or operating on them. You should submit only your m-file via the BB system. Please do not send any image!


Please include comments at the top of each m-file. The comments should contain at least the following: your name, your email, and project number. In your main function, place a message “—–Finish Solving Problem X—–” followed by a pause command (i.e., wait for a key to be pressed before continuing) at the end of each solution, where X is the question number (i.e., 1, 2, or 3).



Problem1: Exercises on Image Scaling and Histogram Equalization [10 points]


a) Use the Matlab function imadjust to scale the image Food.jpg into an appropriate range [NewMin, NewMax] so the original image is enhanced to a good quality. Save the scaled image into ScaledFood. Display the original image, and the scaled image side-by-side on figure 1 with appropriate titles.


b) Use the Matlab function imhist to calculate the histogram of image Food. Tune the parameters of num_bins to see the different results. Display the above calculated histogram and its normalized histogram side-by-side on figure 2 with appropriate titles on both axes.


c) Use the Matlab histogram equalization function histeq on Food image. Save the enhanced image as EqualizedFood. Display the original image, your scaled image ScaledFood, and your histogram enhanced image EqualizedFood with appropriate titles on figure 3.


d) Close all figures and all variables in the workspace.



Problem2: [8 points]


Load in Shapes.tif image. Apply appropriate morphological operation(s) on the original image to obtain the following three desired images, respectively. Display the three resultant images on figure 2 with appropriate titles.



image.png

Hint: Matlab functions imdilate, imerode, imopen, imclose, strel might be needed. Choose a proper size of structuring element so the unwanted parts could be closed or opened.



Problem3: [8 points]


Load in Wirebond.tif image. Apply appropriate morphological operation(s) on the original image to obtain the following three desired images, respectively. Display the three resultant images on figure 3 with appropriate titles.

image.png

Hint: Try erode the image with circle shape SE of different sizes.



Problem4: Morphological operations on gray image [4 points]


Morphological operations (same matlab functions) can be applied on gray image as well. Load in City.jpg image. Apply the dilation, save the resultant image as A; then apply the erosion operation on the original image, save the resultant image as B. Let C = A – B. Use a 3-by-3 square structuring element. Display the resultant image C on figure 4. Use Matlab display command to discuss the reason for such an appearance.




Part2: Exercise. Submit the answers of this part as a word file or a pdf file separately from the Matlab m-file above.


In lecture 2, we covered textbook 2.5, 9.1-9.5 and 10.3.



Problem1: Combination of foreground set B1 and background B2 in Hit-or-Miss Transformation. [10 points]


Read through the following link http://homepages.inf.ed.ac.uk/rbf/HIPR2/hitmiss.htm which explains a simple way that B1 and B2 in the Hit-or-Miss Transformation can be combined into one structuring element (SE). In such a situation, the value 0, 1, and blank in SE have different meanings. Draw the result of first image in Figure 3 after applying the following SE:



image.png

Submit both m-file and text file (word or pdf) to BB on the due date.