Skip to content

Digital Image Processing

CSE · Final · Spring 24

Batch 56

This browser can’t show the PDF here

Open it, and your phone’s PDF viewer takes it, or download it.

Read the questions as text

Read off the PDF by AI, so it may have mistakes. The PDF is the original.

Daffodil International University Faculty of Science & Information Technology Department of Computer Science and Engineering Final Examination, Spring-2024 Course Code: CSE427, Course Title: Digital Image Processing Level: 4 Term: 2 Batch: 56 Time: 2 Hours Marks: 40 Answer ALL Questions [The figures in the right margin indicate the full marks and corresponding course outcomes. All portions of each question must be answered sequentially] 1. a) Apply opening and closing morphological operations in the above image and also show the differences between the two output images where the structural element is [Figure: 2x2 binary matrix] 5 | CO4 1. b) Consider a sample image, Examine different morphological image operations to the image and explain the resultant effect. 5 2. a) Apply Huffman coding and generate the optimal code for the source symbols. Also find the average number of bits needed to represent the code. P(A)=0.3, P(B)=0.2, P(C)=0.3, P(D)=0.06, P(E)=0.04, P(F)=0.1 5 | CO4 2. b) The social media platform hosts millions of images uploaded by users daily. However, due to limited server capacity and the need for efficient data transfer, there's a requirement to compress these images without significant loss of quality. Now Construct a general image compression model for the platform. 3 2. c) Which compression is better "Lossy" or "Lossless"? Explain in your own words. 2 3. a) You're a software engineer working for a security company tasked with developing an automated system for facial recognition in surveillance footage. The system aims to identify and track individuals of interest in real-time from a large volume of video data captured by security cameras in public spaces, such as airports, train stations, and shopping malls. Explain the phases of pattern recognition in digital image processing within the context of developing an automated facial recognition system for surveillance footage. 4 | CO2 3. b) Explain the fuzzy based algorithm and hybrid algorithm in terms of pattern recognition. 4 4. a) Apply Region Split and Merge segmentation technique on above image. Assume the thresholding values as 3.After that also apply Region Growing Techniques. [Figure: 8x8 matrix with pixel values and quadrant lines] | CO3 4. b) Show the use of thresholding technique in image segmentation based on following image. [Figure: 4x4 matrix] 3 4. c) Define segmentation and mention four different segmentation techniques. 2