Pune University Exam Paper BE Electronics IMAGE Processing and
B.E. (Electronics Engineering) IMAGE PROCESSING AND MACHINE VISION (2008 Pattern)
(Elective – III) (Sem. – II)
Time :3 Hours] [Max. Marks :100
Instructions to the candidates:-
1) Answer any 3 questions from each section.
2) Answers to the two sections should be written in separate answer books.
3) Neat diagrams must be drawn wherever necessary.
4) Pigures to the right indicate full marks.
5) Use of logarithmic tables, slide rule, Mollier charts, electronic pocket calculator and steam tables is allowed.
6) Assume suitable data, if necessary.
SECTION – I
What is an image model? Explain image sampling 8 Quantization. 
Explain the applications of image processing in remote sensing 8 medical imaging. 
Explain the fundamntal steps in image processing with the help of suitable diagram. 
Write a short note on human visual system. 
With reference to relation between pixel explain the following: 
i) 4-connectivity. ii) 8-connectivity.
i) Mixed connectivity.
Explain following statistical parameters for an image 8 calculate all these parameters for segment of an image given below: 
ii) Variance iv) Histogram
i) Standard deviation
Explain the use of low pass filter and median filter in image smoothing.  Find the DFT of the image: 
Explain global processing in the image segmentation using haugh transform. How it is used for edge linking. 
Explain the following terms: 
i) Robert’s cross gradient operator.
ii) Prewit operator.
iii) Sobel operator.
Explain the importance of thresholding 8 non maximal suppression in the canny edge detection process. How do the two concept influence in the resulting edge image. 
Explain segmentation using region splitting 8 region merging. 
SECTION – II
Find a set of code words and average word length using Huffman coding
scheme for a set of input gray levels with probabilities as given below:
Gray levels GI G2 G3 G4 G5 G6 G7 G8
Probabilities 0.02 0.15 0.03 0.15 0.05 0.2 0.1 0.3
Calculate the average length of the code. 
What is difference between loss-less and lossy compression technique?
Explain the block transform coding in detail. 
Explain the different algorithms of region identification. 
Explain the contour based shape representation 8 description of an image.
Explain the region based shape descriptors. 
Explain the region decomposition considering shape recognition is hierarchal process. 
Explain the projective ambiguity 8 matching constraints with reference to scene reconstruction. 
Explain the support vector machine approach to pattern recognition. 
Explain the statistical pattern recognition. 
Explain the camera model of a single perceptive camera.