Page 1 of 6 - Cover Page Submission ID trn:oid:::3618:73729610

22951A6728_IMA.pdf
Institute of Aeronautical Engineering (IARE)

Document Details

Submission ID

trn:oid:::3618:73729610 3 Pages

Submission Date 762 Words

Dec 11, 2024, 12:48 PM GMT+5:30

4,798 Characters

Download Date

Dec 11, 2024, 12:50 PM GMT+5:30

File Name

22951A6728_IMA.pdf

File Size

487.5 KB

Page 1 of 6 - Cover Page Submission ID trn:oid:::3618:73729610

 Page 2 of 6 - Integrity Overview Submission ID trn:oid:::3618:73729610

8% Overall Similarity
The combined total of all matches, including overlapping sources, for each database.

Filtered from the Report

Bibliography

Match Groups Top Sources

6 Not Cited or Quoted 8% 6% Internet sources

Matches with neither in-text citation nor quotation marks
6% Publications
0 Missing Quotations 0% 0% Submitted works (Student Papers)
Matches that are still very similar to source material

0 Missing Citation 0%
Matches that have quotation marks, but no in-text citation

0 Cited and Quoted 0%

Matches with in-text citation present, but no quotation marks

Integrity Flags
0 Integrity Flags for Review
Our system's algorithms look deeply at a document for any inconsistencies that
No suspicious text manipulations found. would set it apart from a normal submission. If we notice something strange, we flag
it for you to review.

A Flag is not necessarily an indicator of a problem. However, we'd recommend you

focus your attention there for further review.

Page 2 of 6 - Integrity Overview Submission ID trn:oid:::3618:73729610

 Page 3 of 6 - Integrity Overview Submission ID trn:oid:::3618:73729610

Match Groups Top Sources

6 Not Cited or Quoted 8% 6% Internet sources

Matches with neither in-text citation nor quotation marks
6% Publications
0 Missing Quotations 0% 0% Submitted works (Student Papers)
Matches that are still very similar to source material

0 Missing Citation 0%
Matches that have quotation marks, but no in-text citation

0 Cited and Quoted 0%

Matches with in-text citation present, but no quotation marks

Top Sources
The sources with the highest number of matches within the submission. Overlapping sources will not be displayed.

1 Publication

Minxian Shen, Tianyi Lv, Yi Liu, Jialiang Zhang, Mingye Ju. "A Comprehensive Revi… 2%

2 Internet

thesai.org 2%

3 Internet

dspace.univ-tiaret.dz 2%

4 Internet

www.ijraset.com 2%

5 Internet

www.slideshare.net 1%

Page 3 of 6 - Integrity Overview Submission ID trn:oid:::3618:73729610

 Page 4 of 6 - Integrity Submission Submission ID trn:oid:::3618:73729610

NAME:M.CHANDRIKA

ROLL NUMBER:22951A6728

BRANCH:CSD

SUBJECT:IMA

1. Explore the steps of specifications of Image Sensing and Acquisition for CT-
scan image application.
Image sensing and acquisition for CT-scan applications involve several steps to ensure high-
quality imaging for diagnostic purposes. These steps include:
- **Sensor Selection**: Choosing sensors capable of detecting X-ray radiation.
- **Signal Processing**: Converting analog signals from sensors to digital format.
- **Data Reconstruction**: Using algorithms like filtered back projection or iterative
methods to construct 3D images.
- **Calibration**: Ensuring accuracy through regular calibration of equipment.
- **Image Enhancement**: Applying techniques like noise reduction to improve image
quality.

3 2. List and explain applications of image processing.

Image processing has a wide range of applications, including:
- **Medical Imaging**: Enhancing images from X-rays, CT scans, and MRIs for diagnosis.
- **Remote Sensing**: Analyzing satellite images for environmental monitoring.
- **Face Recognition**: Identifying individuals using biometric features.
- **Industrial Automation**: Quality control through visual inspection.
- **Digital Art Restoration**: Reconstructing damaged artworks using algorithms.

5 3. Explain the steps in histogram equalization.

Histogram equalization is a technique to enhance image contrast. Steps include:
2 1. Calculate the histogram of the image.
2. Compute the cumulative distribution function (CDF) of pixel intensities.
3. Normalize the CDF to scale pixel intensities between 0 and 255.
1 4. Map original pixel values to new values based on the normalized CDF.
1 5. Replace original pixel values with the new values to produce the enhanced image.

4. List the salient features of image histogram.

An image histogram represents the distribution of pixel intensities. Salient features include:
- **Shape**: Indicates the brightness distribution.
- **Peaks and Valleys**: Identify frequently occurring intensity levels.
- **Range**: Shows the contrast levels in the image.
- **Symmetry**: Suggests balanced intensity levels.
- **Modal Value**: The most common intensity value.

Page 4 of 6 - Integrity Submission Submission ID trn:oid:::3618:73729610

 Page 5 of 6 - Integrity Submission Submission ID trn:oid:::3618:73729610

5. Show effect of Closing Operations and Distance Transforms with example

image.
Closing operations are morphological techniques used to fill small holes and gaps in images,
while distance transforms compute the minimum distance of each pixel from the nearest
boundary. For example:

1. **Closing Operations**:
- Input: An image with small gaps.
- Output: Gaps are filled while retaining the object shape.

2. **Distance Transform**:
- Input: A binary image.
- Output: A grayscale image where pixel intensity corresponds to distance from the nearest
boundary.

6. Describe inverse filtering for removal of blur caused by any motion and
describe how it restores the image.
Inverse filtering is a method to restore blurred images caused by motion. Steps include:
- **Blur Model**: Assume the image is blurred using a known motion kernel.
- **Frequency Domain**: Transform the blurred image to the frequency domain using
Fourier Transform.
- **Deconvolution**: Divide the blurred image's spectrum by the motion kernel's spectrum.
- **Reconstruction**: Apply Inverse Fourier Transform to obtain the restored image.

This method is sensitive to noise, so additional techniques like Wiener filtering may be
required.

7. Explain edge linking using Hough transform.

The Hough transform is a feature extraction technique used to detect edges and link them
into meaningful shapes like lines. Steps include:
- **Edge Detection**: Apply an edge detection algorithm (e.g., Canny) to identify potential
edge pixels.
- **Hough Space Transformation**: Transform edge pixels into a parameter space (e.g., for
lines, it’s rho and theta).
- **Peak Detection**: Identify peaks in the Hough space corresponding to probable shapes.
- **Edge Linking**: Map the identified shapes back to the spatial domain.

8. Show that an invariant feature transformation separable while the whole-

image features object is need to be separable.
Invariant feature transformation ensures that extracted features remain consistent despite
changes in scale, rotation, or translation. For whole-image feature objects to be separable, it
must satisfy the following conditions:
- Features must not overlap.

Page 5 of 6 - Integrity Submission Submission ID trn:oid:::3618:73729610

 Page 6 of 6 - Integrity Submission Submission ID trn:oid:::3618:73729610

- Features must retain their distinctiveness after transformation.

4 - Examples include Scale-Invariant Feature Transform (SIFT) and Histogram of Oriented
Gradients (HOG).

9. How an image is pixel-based JPEG in image segmentation?

In pixel-based JPEG image segmentation, segmentation is performed by analyzing the
Discrete Cosine Transform (DCT) coefficients used in JPEG compression. Steps include:
- Decode the JPEG image into pixel blocks.
- Analyze DCT coefficients to classify each block based on intensity, texture, or color.
- Combine classified blocks to form segments.
This approach is efficient for compressed images.

10. Explore the feature-based registration which source from rigid body
visualization with examples.
Feature-based registration aligns two or more images by matching corresponding features.
In rigid body visualization, the transformation includes only translation and rotation,
preserving the object's structure. Steps include:
- Detect features using algorithms like SIFT or Harris Corner Detector.
- Match features between images using descriptors.
- Estimate transformation parameters using methods like RANSAC.
- Apply the transformation to align images.

Example: Aligning medical images like CT scans from different angles.

Page 6 of 6 - Integrity Submission Submission ID trn:oid:::3618:73729610