Solution for Image & Video Processing December-2015 Index Q.1) a). 2-3 b). 4 (N.A.) c). 4 (N.A.) d). 4 (N.A.) e). 4-5 Q.2) a). 5 to 7 b). 7 (N.A.) Q.3) a). 8-9 b). 9 to 12 Q.4) a). 12-13 b). 13 to 16 Q.5) a). 16 to 20 b). 20-21 Q.6) a). 22-23 b). 24 c). 24 to 26 d). 26 to 29 1 www.brainheaters.in
Q1) Attempt (Any Four) (20) (a) Explain RGB and HSI colour models. Ans: RGB colour model 2 www.brainheaters.in
HSI colour model 3 www.brainheaters.in
(b) Quality of picture depends on the number of pixels and grey level that represent the picture.justify or contradict. Ans :- N.A. (c) What are the different types of order statistics filters? Discuss its advantages. Ans :- N.A. (d) Discuss the classification of video frames. Ans :- N.A. (e) Explain opening and closing of digital image. Ans: Opening :- 4 www.brainheaters.in
Closing :- Q2) (a) Write an example of two dimensional DCT. Also find the DCT of the imag Ans :- N. A. Same Sum :- Find the DCT of the given 4X4 image 1 2 2 1 2 1 2 1 1 2 2 1 2 1 2 1 5 www.brainheaters.in
end 6 www.brainheaters.in
final-dct=c*x*c (b) Why fourier transform and frequency domain tools are so useful for image enhancement? With the help of neat block diagram explain the basic of filtering in the frequency domain.give the reason for shifting the origin. Ans :- N.A. 7 www.brainheaters.in
Q3) (a) Perform histogram equalization foe the following image. Plot the original and equalized histogram. Intensity 0 1 2 3 4 5 6 7 No. of Pixels 70 100 40 60 10 70 10 40 Ans :- N.A. Same Sum :- Equalize the given histogram Gray level 0 1 2 3 4 5 6 7 Number of 790 1023 850 656 329 245 122 81 pixels L = 8 (Number of grey levels We first plot the original histogram Original dark histogram 8 www.brainheaters.in
Equilizer histogram (b) Discuss region based segmentation Ans :- 9 www.brainheaters.in
Region based segmentation can be carried out in four different ways: 1) Region growing: 10 www.brainheaters.in
2) Region merging: 3) Region Splitting: 4) Split and merge: 11 www.brainheaters.in
Q4) (a) What are the required sampling rates for video signal? Explain video sampling in three dimension. (10) Ans: Sampling of video Signal 12 www.brainheaters.in
(b) Explain HIT and MISS transform using an example. (10) Ans: HIT MISS Transform: 13 www.brainheaters.in
Example: 14 www.brainheaters.in
Solution :- 15 www.brainheaters.in
Q5) (a) Explain the working of Weiner filter in image restoration. (10) Ans: 16 www.brainheaters.in
17 www.brainheaters.in
18 www.brainheaters.in
5) No Blur only Additive noise: From the equation we realize that, when the signal to noise ratio is large,hr (u,v) ==1 and when signal to noise ratio is small. Hr (u,v) =SSNR 19 www.brainheaters.in
6) No noise only blur (b) Discuss the concept of optical flow for motion estimation. Ans: 20 www.brainheaters.in
21 www.brainheaters.in
Q6) Write short note on (Any two) (a) KL transform. Ans: 22 www.brainheaters.in
23 www.brainheaters.in
(b) Exhaustive block matching algorithm. Ans: Search techniques: Exhaustive Search Block Matching Algorithm (EMBA) (c) Hough transform AnS: 24 www.brainheaters.in
25 www.brainheaters.in
d) Point processing Ans:- In point processing. We work with single pixel i.e. 1 x 1 operator. It means that the new value f(x,y) depends on the operator T and the present f(x,y). This statement will be clear as we start some examples. Some of the common examples of point processing are (1) Digital negative (2) Contrast stretching (3) Thresholding (4) Grey level slicing (5) Bit plane slicing (6) Dynamic range compression (7) Power law transformation 26 www.brainheaters.in
27 www.brainheaters.in
28 www.brainheaters.in
29 www.brainheaters.in