Code No: 420456

OR
IV-B.Tech. II-Semester Supplementary Examinations July, 2003

IMAGE PROCESSING
(Electronics and Communication Engineering)
Time: 3 hours Max. Marks: 70
Answer any FIVE questions
All questions carry equal marks
---

1.a) Explain what is meant by feature mapping. Explain the problem with a real life
example from speech production.
b) Explain how recognition of hand written digits is close to a classification type
problem, where as recognition of vowel sounds in continuous speech is close to a
feature mapping type of problem.

2. Write about the following:

a) Newton’s Gradient search method
b) Method of steepest descent.

3.a) Explain LMS Algorithm.

b) What is stochastic approximation. Write about robbins and monro Algorithm.

4.a) State and prove perceptron training theorem.

b) Briefly explain pattern classification, pattern association and pattern mapping
tasks with an example.

5. Explain the different speech recognition techniques.

6.a) Write the FFT Algorithm and explain.

b) How many additions and multiplications would be required for computing two
dimensional FFT of NXN image.

7.a) Differentiate between spatial domain and frequency domain methods of image
enhancement.
b) Explain the histogram equivalization method of image enhancement. Illustrate
with an example.

Contd……2.
Code No: 420456 ::2:: OR

8.a) A binary image contains straight lines oriented horizontally, vertically at 45o and
at -45o respectively. Give a set of 3x3 masks that can be used to detect one pixel
long breaks in these lines. Assume that the gray level of the background is zero.
b) Find the edge corresponding to the minimum cost path in the sub image shown
below; where the numbers in the parenthesis indicate intensity. Assume that the
edge starts in the first column and ends in the last column.
0 1 2
• • •
0 (2) (1) (0)

• • •
1 (1) (1) (7 )

• • •
2 (6) (8) (2)

@@@@@