CSET344/CMCA544

Image and Video Processing

Dr. Gaurav Kumar Dashondhi

Ph.D. From IIT Bombay

Overall Course Coordinator- Lect. Week

Dr. Gaurav Kumar Dashondhi 6th Jan to 10th Jan 2025
[email protected]
1
 CSET344
Image and Video Processing
Ass_Lec. Ass_Tut. Ass_Lab Ass_Total Faculty Name Faculty mail

4 0 8 12 Mr. Prashant Kapil [email protected]

4 0 0 4 Dr. Gaurav Kumar Dashondhi [email protected]

0 0 10 10 Dr. Kimmi Gupta [email protected]

0 0 10 10 Dr. Shallu Sharma [email protected]

Lect. Week
6th Jan to 10th Jan 2025 2
Motivation
• Three Major Motivation for Processing of Images.

1. Improvement of Pictorial information for human interpretation.

Like using Instagram and Snapchat filters.

2. Processing of Image data for storage, transmission and representation of autonomous

machine perception.

3. Processing is essential to analyze and extract the information.

3
Application of Image Processing

1. Remote sensing.

2. Medical Domain.

3. Security and Surveillance. Object detection and Tracking.

4. Industrial automation.

5. Film and entertainment industry. To add the special effects and create artificial
environment.

4
Application of Image Processing

Automate the Status of Bottle Filling Inspection

5
Application of Image Processing

Automate the IC Connection Inspection : Some connections are broken.

6
Application of Image Processing

Medical Domain

Original Image Processed Image1 Processed Image 2

7
Application of Image Processing
Remote Sensing

8
CSET344 - Syllabus

9
Course Overview : Module 1
1. Analog-to-Digital Image Conversion:
Sampling and Quantization

2. Spatial Domain Image Enhancement:

Histogram Processing: Techniques for modifying the image histogram to improve contrast and visual
appearance.

Histogram Equalization: A specific histogram processing method that aims to redistribute pixel
intensities to achieve a uniform distribution.

3. Convolution:
A fundamental operation in image processing where a kernel (filter) is slide over the image, and an
output pixel is computed as a weighted sum of the input pixels within the kernel's region.

4. Image Smoothing:
Mean Filter, Median Filter, Gaussian Filter

5. Edge Detection:
Prewitt Operator, Sobel Operator, Laplacian Operator, Laplacian of Gaussian (LoG) Operator
And Canny Edge Detector: 10
Course Overview: Module 2
1.Line and Circle Detection using the Hough Transform:

2. Harris Corner Detector:

Corner Detection: A technique for identifying image locations where two edges intersect,
forming a sharp corner.

3. Color Models and Color Transforms:

Color Models: Mathematical representations of color, defining how colors are represented
numerically. Common examples include RGB, HSV, and CIELAB.

Color Transforms: Algorithms for converting colors between different color models, enabling
tasks like color correction, image segmentation, and color analysis.

4. Morphological Operations

5. Texture analysis using GLCM

11
Course Overview: Module 3
1. Concept of Optical Flow:

A technique for estimating the apparent motion of objects between two consecutive image
frames. It involves calculating the pixel-wise displacement vectors that represent the motion
of objects in the scene.

2. Image Enhancement in the Frequency Domain

3. Image Compression using Lossless and Lossy Techniques

4. Discrete Cosine Transform (DCT):

A mathematical transformation that decomposes a signal into a sum of cosine functions at
different frequencies. It is widely used in image and video compression, particularly in the
JPEG standard, as it concentrates most of the signal energy into a few low-frequency
coefficients.

12
Course Overview: Module 4
1. Different Methods of Face Detection

Viola-Jones: A cascade classifier based on Haar-like features and boosting.

Histogram of Oriented Gradients (HOG)
Scale-Invariant Feature Transform (SIFT)

2. PCA for Dimensionality Reduction and other Feature Extractors like HOG, SIFT

3. Techniques related to Video Processing, Formation, Compression and Coding:

4. Silent Object and Human Action Reorganization

5. Detail of the Depth Cameras

Sensors that can measure the distance to objects in a scene, providing depth information.

13
CSET344 – Course Evaluation (Tentative)

1. Mid-Semester: 20 marks
2. End-Semester: 40 marks
3. Project Work: 20 marks
1. Presentation and Q&A (Individual Student) : 10 marks
2. Functionality and Working Condition: 10 marks
4. Laboratory Continuous Assessment: 20 marks
5. Programming Environment: All experiments will be conducted using the Python programming language
with OpenCV on the Google Colab platform or Visual Studio Code.
6. Module Coverage:
1. Before the Mid-Semester : Modules 1 and 2 will be completed.
2. After the Mid-Semester: Modules 3 and 4 will be covered.
7. Question Design: All questions will emphasize logical reasoning and problem-solving.

14
EM Spectrum

Refer: https://www.lumitex.com/blog/visible-light-spectrum

15
Image, Intensity or grey level and Pixel.

It’s a two dimensional function f(x , y) where x, y are the spatial coordinate and the amplitude at that particular
coordinate will be the intensity or grey level.
720 1080

x,y
HD 1920
FULL HD
1320
1320 x 720 1920 x 1080

2100

Image

3800
ULTRA 4k
3800 x 2100

16
Type of Images

0 0 0 0 0 0 0 0 0 0
0 1 1 1 0 0 255 255 255 0
0 0 0 1 0 0 0 0 255 0
0 1 1 1 0 0 255 255 255 0
R,G,B
0 0 0 1 0 0 0 0 255 0
0 1 1 1 0 0 255 255 255 0
0 0 0 0 0 0 0 0 0 0

Black and White Image Gray Scale Image Colour Image

Range 0 to 1 Range 0 to 255 Red Channel Range 0 to 255
Green Channel Range 0 to 255
Blue Channel Range 0 to 255

17