UNIQUE SERIES AKTU Syllabus
BCDS061

Image Analytics

L-T-P3-0-0 Credits3 Session2024-25 TypeTheory
Appears in 5 semesters · 5 branches

B.Tech Artificial Intelligence & Machine Learning · Sem 6 (Departmental Elective-III) · B.Tech Artificial Intelligence & Data Science · Sem 6 (Departmental Elective-III) · B.Tech CSE (Artificial Intelligence) · Sem 6 (Departmental Elective-III) · B.Tech CSE (AI & ML) · Sem 6 (Departmental Elective-III) · B.Tech CSE (Data Science) · Sem 6 (Departmental Elective-III)

Download PDF

Syllabus

5 units · 40 lecture hours
Unit1

Unit 1: Fundamentals

8 hrs
  • Introduction – Fundamental steps in Image Processing Systems – Image Acquisition – Sampling and Quantization – Pixel Relationships – Mathematical Tools Used in Digital Image Processing. Some Basic Intensity Transformation Functions: Image Negatives, Log Transformations, Power-Law Transformations – Histogram Processing. Color Fundamentals – Fundamentals of Spatial Filtering – Smoothing Spatial Filters – Sharpening Spatial Filters. Practical Component: Use Python/ MATLAB
  • Apply various intensity transformations functions.
  • Computing and plotting image histograms and use standard image processing toolbox Spatial filters.
  • Implement color image Smoothing and Sharpening.
Unit2

Unit 2: Morphological Image Processing

8 hrs
  • Morphological Image Processing: Fundamentals – Erosion and Dilation – Opening and Closing – Hit or Miss Transform – Some Basic Morphological Algorithms – Morphological Reconstruction – Grayscale Morphology Practical Component: Use Python/ MATLAB 1. Implement Morphological operations.
  • Implement Morphological Reconstruction.
  • Implement Grayscale Morphology.
Unit3

Unit 3: Colour Image Processing

8 hrs
  • Colour fundamentals, colour models, pseudo colour image processing, basics of full colour image processing, colour transformation, smoothing and sharpening. Image Segmentation based on colour, Active Contours: Snakes and Level Sets, noise in colour images, colour image compressions. Thresholding: Foundation, Basic Global thresholding, Optimum Global Thresholding using Otsu’s Method, Multiple Thresholds, Variable Thresholding –Segmentation by Region Growing and by Region Splitting and Merging. Practical Component: Use Python/ MATLAB
  • Implement Optimum Global Thresholding using Otsu’s Method.
  • Implement Image smoothing and sharpening. Implement Image Segmentation by Active Contours using anyone method Snakes and Level Sets.
Unit4

Unit 4

8 hrs
  • Feature Extraction Background – Representation – Boundary Preprocessing – Boundary Feature Descriptors: Some Basic Boundary Descriptors, Shape Numbers, Fourier Descriptors, Statistical Moments – Regional Feature Descriptors: Some Basic Descriptors, Topological and Texture Descriptors, Moment Invariants – Principal Components as Feature Descriptors – Whole-image Features Object – Scale-Invariant Feature Transform (SIFT). Practical Component: Use Python/ MATLAB
  • Implement Boundary Feature Descriptors
  • Implement Topological and Texture Descriptors
  • Implement Scale-Invariant Feature Transform (SIFT)
Unit5

Unit 5

8 hrs
  • Image Pattern Classification Background –Patterns and Pattern Classes – Pattern Classification by Prototype Matching: Minimum-Distance Classifier, Using Correlation for 2-D prototype matching, Matching SIFT Features, Matching Structural Prototypes – Optimum (Bayes) Statistical Classifiers – Neural Networks and Deep Learning: Background – The Perceptron – Multilayer Feedforward Neural Networks – Deep Convolutional Neural Networks Practical Component: Use Python/ MATLAB
  • Implement Minimum-Distance Classification Algorithm.
  • Implement Optimum (Bayes) Statistical Classification Algorithm.
  • Implement Deep Convolutional Neural Network.
Course Outcomes (COs)5 outcomes

After completion of the course student will be able to:

  1. CO1Infer the basics and fundamentals of digital image processing and Apply the various techniques for intensity transformations functions. Implement Color image Smoothing and Sharpening.K1, K2
  2. CO2Illustrate Morphological operation and Apply Some Basic Morphological Algorithms.K2, K3
  3. CO3Apply image segmentation techniques such as Optimum Global Thresholding using Otsu’s Method, Active Contours: Snakes and Level Sets for various real-time applications.K3, K4
  4. CO4Analysis various Feature Extraction methods and Implement for various real-time applications.K3, K4
  5. CO5Apply and Analysis various Image Pattern Classification methods such as MinimumDistance Classification, Optimum (Bayes) Statistical Classification, and Deep Convolutional Neural Network.K3, K4

Text Books

  1. Rafael C Gonzalez, Richard E Woods, “Digital Image Processing”, 4th Edition, Pearson, 2018.
  2. Kenneth R. Castleman, Digital Image Processing Pearson, 2006.
  3. Anil K.Jain, “Fundamentals of Digital Image Processing”, Person Education, 2003.

Official AKTU syllabus

This subject is on page 31, 32 of the original AKTU PDF.

Official AKTU syllabus PDF ↗