1. Mention thematic bands in NASA's LANDSAT satellite, wavelength and uses. (05 Marks) Consider the image segment shown in Table Q1(b), compute the length of the shortest 4, 8 and m-path between P and Q for (v={2,3,4}) (06 Marks) 34120 0020 2234 P42
c. Explain the process of image acquisition using a single sensor with
motion to generate a 2-D image. (05 Marks) 2. OR Discuss the most commonly used distance measures in image processing. (06 Marks) Explain the process of generating a digital image. (05 Marks) With the mathematical equation, explain the bicubic interpolation. (05 Marks) Module-1 1. With the help of a neat diagram, explain the components of general purpose image processing system. (08 Marks) Explain how image is formed in human eye. Suppose a camera is focused at a pillar of height 2 meters and situated at a distance of 10 metres. The focal length of the image produced in camera. (06 Marks) Consider the two image subsets, (S_{1}) and (S_{2}) as shown in Fig. Q1(c). For V = {1}, determine whether these two subsets are: 4-adjacent 8-adjacent or m-adjacent. 1110 1000 1000 0000
Fig.Q1(c) (02 Marks)
2. OR Explain the following terms: False contouring Check board effect Distance measure. Compute shortest 4, 8 and m path between p and q for v = {1, 2}.
3 1 2 1 2 2 0 2 1 2 1 1 p 1 0 12
c. Find the time required in seconds to transmit a monochrome image
of size 2.5" x 2" scanned at 150 DPI sent at 28 kilo bits per sec. (08 Marks) 1 of 2
Module-2 4. OR Explain with block diagram the basic steps for image filtering in frequency domain. (08 Marks) Explain histogram matching. (08 Marks) Explain smoothing in spatial domain. (08 Marks) 15EC72 Module-2 3. For a given 4x4 image having gray scales between [0, 9] perform histogram equalization and draw the histogram of image before and after equalization. 4x4 image is shown in Fig. Q3 (a). 2332 4243 3235 2424
Fig. Q3 (a) (08 Marks)
b. Explain smoothing of images in frequency domain using ideal, Butterworth and Gaussian Low pass filter. (08 Marks) OR 4. Define 2D DFT, with respect to 2D DFT of an image and state the following properties: (05 Marks) Translation Rotation Periodicity Convolution theorem With necessary graphs, explain the log and power law transformation used for spatial image enhancement. (05 Marks) Explain image sharpening in spatial domain using second order Laplacian derivative. (06 Marks) Module-2 3. Explain the power law transformation and piece-wise linear contrast stretching with a neat graphical illustration. (10 Marks) Explain with a block diagram, the basic steps for image filtering in frequency domain. (06 Marks) 4. OR Perform histogram equalization of the 5 x 5 image whose data is shown in Table Q4(a). Gray level Number of pixels 0 0 6 14 5 6 7 0
Table Q4(a) (08 Marks)
b. Explain the smoothing of images in frequency domain using: (08 Marks) ideal low pass filter butter worth low pass filter Module-2 3. Explain the following enhancement techniques in image processing: (08 Marks) Image Negatives Power law transformation 4. Discuss homomorphic filtering transformations. (04 Marks) 5. Develop a method for second order derivative for enhancement in spatial domain. (06 Marks)
Module-2 3. Explain the following intensity transformation functions: (05 Marks) Image negatives ii. Log transformation iii. Power-law transformation OR
4. For the given 4 x 4 image of Table Q4(a) having gray scale between 0 to 9, perform histogram equalization and draw the histogram of image before and after equalization. 2332 4243 3235 2424
Table. Q4(a) 5. Explain the image smoothing in frequency domain using ideal low pass filter. (08 Marks) Module-2 3. Using 2nd order derivative, develop a laplacian mask. (06 Marks) What is linear filtering? (02 Marks) The following table gives the number of pixels at each of the gray levels 0 to 7 in an image. n_x 0 1 2 3 4 5 6 7 n_r 123 78 281 417 639 816 688
Draw the histogram corresponding to these gray levels. Perform
histogram equalization and draw resulting histogram. (08 Marks) 4. OR Explain Homomorphic filters for image enhancement with necessary equations, block diagram and transfer function. (08 Marks) Explain smoothing filters in frequency domain. (04 Marks) Compute median value of the marked pixels shown below using 3 x 3 mask. 18 22 33 25 32 24 22 34 26 33 26 22 31 28 22 32 31 28 29 19 31 28 28 22
Fig.Q4(c) (04 Marks)
Module-3 5. Explain the following noise models: (08 Marks) Gaussian noise Rayleigh noise Impulse noise Uniform noise Explain inverse filter and Wiener filter with the help of equations. Explain the advantages of Wiener filter over inverse filter. (08 Marks) 6. Define the process of image restoration. How is restoration different from enhancement? (05 Marks) What are order statistics filters? List any four such filters. (03 Marks) What are adaptive filters? Explain adaptive mean filter and its advantages. (08 Marks) Module-3 5. What are the most commonly used probability density functions in image processing applications and explain it with the help of plot. (08 Marks) With the mathematical equations, discuss the minimum Mean Square Error Filtering. (08 Marks) 6. OR Explain the process of restoration in the presence of noise only using spatial filtering for various mean filters. (08 Marks) What are the three principal ways to estimate the degradation function for use in image restoration and explain it? (08 Marks) Module-3 5. Explain the model of image degradation/restoration. (08 Marks) Explain observation and experimentation ways to estimate the degradation function. (08 Marks) 6. OR Mention the probability density function, mean, variance of the following noise models: (08 Marks) Gaussian noise Rayleigh noise Gamma noise Exponential noise With relevant expressions, explain minimum mean square filtering (Wiener). (08 Marks) Module-3 5. Explain the basic model of image restoration process. Explain any four important noise probability density functions. (10 Marks) Explain minimum mean square error (Wiener) filtering in image processing. (06 Marks) 6. OR Explain adaptive mean filter and list its advantages. (08 Marks)
With necessary mathematical equations, explain estimate the degradation
function by modeling. (08 Marks) Module-3 5. With necessary equations and graph, explain any four noise probability density functions. (08 Marks) Explain minimum mean square error filtering method of restoring images. (08 Marks) 6. OR Explain how image degradation is estimated using, (08 Marks) Observation Mathematical modeling. Explain the order statistics filters used for restoring images in the presence of noise. (08 Marks) Wiener filter over inverse filter. Explain inverse filter and Wiener filter with the help of equations. Explain the advantages of Wiener filter over inverse filter. (08 Marks) Explain minimum mean square error filtering (Wiener). (08 Marks)
7. Write the equations for converting colors from HSI to RGB. (06 Marks) Explain how a color lookup table is constructed. (06 Marks) Explain the following morphological algorithms: (06 Marks) Thinning Thickening 8. What is Pseudo color image processing? Explain intensity slicing as applied to pseudo color image processing. (07 Marks) Explain Erosion and Dilation operations used for morphological processing. (07 Marks) Define wavelet function. (02 Marks) Module-4 7. Develop a procedure for converting: (08 Marks) RGB to HSI model HSI to RGB model. Obtain the Haar transform matrix for N = 4. (08 Marks) 8. OR Write a note on pseudocolor image processing. Explain intensity slicing as applied to pseudo color image processing. (08 Marks) Explain Erosion and Dilation in image processing. (08 Marks) Module-4 7. Classify color models and explain the following color models: (08 Marks) HSI color model RGB color model Explain Dilation and Erosion with respect to morphological image processing. (08 Marks) 8. Define multiresolution and explain the subband coding related to multiresolution. (08 Marks) Perform the following conversions in subband coding: (08 Marks) RGB to HSI HSI to RGB Module-4 7. Explain the process of generating RGB image. (08 Marks) Write the formulas used for converting RGB to HSI. Using these formula find the value of HSI for the given RGB = (0.683, 0.1608, 0.1922). (08 Marks) 8. OR Draw the block diagram for converting gray level intensity to color transformation and explain it. (08 Marks) What is image pyramids? Explain the system for creating approximation and prediction residual pyramids. (08 Marks) Module-4 7. Explain RGB color model in detail listing its applications. What are Web safe colors? (08 Marks) With the help of block diagram, explain two-band sub-band coding and deciding system with its spectrum. (08 Marks) 8. OR What is pseudo color image processing? Explain any one method of pseudo color image processing. (08 Marks) Explain erosion and dilation operations used for morphological processing. (08 Marks) Module-5 9. Explain Otsu's algorithm for global thresholding using suitable equations. (08 Marks) Explain chain codes for boundary representation. (08 Marks) OR Explain the concept of Fourier descriptor for boundary representation. (08 Marks)
What is Laplacian of a Gaussian (LoG)? Write a 5 x 5 LoG mask with the graph? (08 Marks) 10. Explain image gradient and gradient operators for Edge detection. (08 Marks) Discuss the process of region splitting and merging for region based segmentation. (08 Marks) OR Write the steps to be followed for developing an algorithm for a given binary region R and example it. (08 Marks) Mention the aberrations of Minimum Perimeter Polygons (MPP) algorithm and explain it. (08 Marks) Module-5 9. Define segmentation and explain segmentation based on discontinuity in intensity levels. (08 Marks) Explain Region Based Segmentation. (08 Marks) OR Briefly explain the basic edge detection and relate first and second order derivative to gray level profile. (08 Marks) Explain the following related to representation and description: (08 Marks) Chain codes Signatures Skeletons Module-5 9. Explain Marr-Wildreth edge detector in image processing. (08 Marks) Explain MPP algorithm in image representation (MPP - Minimum Perimeter Polygon). (08 Marks) 10. Explain basic global thresholding with iterative algorithm. (08 Marks) Explain simple descriptors and Fourier descriptors. (08 Marks) Module-5 9. Explain Marr-Hildreth edge detector. (10 Marks) Write short note on Boundary segments. (06 Marks) 10. Explain the following boundary descriptors: (i) Shape numbers (ii) Fourier descriptors. (08 Marks) Explain Global Thresholding using Otsu's method. (08 Marks)
