MU4251 Digital Image Processing Syllabus:

MU4251 Digital Image Processing Syllabus – Anna University PG Syllabus Regulation 2021

COURSE OBJECTIVES:

 To study fundamental concepts of digital image processing.
 To understand and learn image processing operations and restoration.
 To use the concepts of Feature Extraction
 To study the concepts of Image Compression.
 To expose students to current trends in the field of image segmentation.

UNIT I INTRODUCTION

Examples of fields that use digital image processing, fundamental steps in digital image processing, components of image processing system. Digital Image Fundamentals: A simple image formation model, image sampling and quantization, basic relationships between pixels. Image enhancement in the spatial domain: Basic gray-level transformation, histogram processing, enhancement using arithmetic and logic operators, basic spatial filtering, smoothing, and sharpening spatial filters, combining the spatial enhancement methods.
Suggested Activities:
 Discussion of Mathematical Transforms.
 Numerical problem solving using Fourier Transform.
 Numerical problem solving in Image Enhancement.
 External learning – Image Noise and its types.
Suggested Evaluation Methods:
 Tutorial – Image transforms.
 Assignments on histogram specification, histogram equalization and spatial filters.
 Quizzes on noise modeling.

UNIT II IMAGE RESTORATION

A model of the image degradation/restoration process, noise models, restoration in the presence of noise–only spatial filtering, Weiner filtering, constrained least squares filtering, geometric transforms; Introduction to the Fourier transform and the frequency domain, estimating the degradation function. Color Image Processing: Color fundamentals, color models, pseudo color image processing, basics of full–color image processing, color transforms, smoothing and sharpening, color segmentation
Suggested Activities:
 Discussion on Image Artifacts and Blur.
 Discussion of Role of Wavelet Transforms in Filter and Analysis.
 Numerical problem solving in Wavelet Transforms.
 External learning – Image restoration algorithms.
Suggested Evaluation Methods:
 Tutorial – Wavelet transforms.
 Assignment problems on order statistics and multi-resolution expansions.
 Quizzes on wavelet transforms.

UNIT III FEATURE EXTRACTION

Detection of discontinuities – Edge linking and Boundary detection- Thresholding- -Edge based segmentation-Region based Segmentation- matching-Advanced optimal border and surface detection- Use of motion in segmentation. Image Morphology – Boundary descriptors- Regional descriptors.
Suggested Activities:
 External learning – Feature selection and reduction.
 External learning – Image salient features.
 Assignment on numerical problems in texture computation.
Suggested Evaluation Methods:
 Assignment problems on feature extraction and reduction.
 Quizzes on feature selection and extraction.

UNIT IV IMAGE COMPRESSION

Fundamentals, image compression models, error-free compression, lossy predictive coding, image compression standards Morphological Image Processing: Preliminaries, dilation, erosion, open and closing, hit or miss transformation, basic morphological algorithms
Suggested Activities:
 Flipped classroom on different image coding techniques.
 Practical – Demonstration of EXIF format for given camera.
 Practical – Implementing effects quantization, color change.
 Case study of Google’s WebP image format.
Suggested Evaluation Methods:
 Evaluation of the practical implementations.
 Assignment on image file formats

UNIT V IMAGE SEGMENTATION

Detection of discontinuous, edge linking and boundary detection, thresholding, region–based segmentation. Object Recognition: Patterns and patterns classes, recognition based on decision– theoretic methods, matching, optimum statistical classifiers, neural networks, structural methods – matching shape numbers, string matching.
Suggested Activities:
 Flipped classroom on importance of segmentation.
Suggested Evaluation Methods:
 Tutorial – Image segmentation and edge detection.

COURSE OUTCOMES:

CO1: Apply knowledge of Mathematics for image processing operations
CO2: Apply techniques for image restoration.
CO3: Identify and extract salient features of images.
CO4: Apply the appropriate tools (Contemporary) for image compression and analysis.
CO5: Apply segmentation techniques and do object recognition.

TOTAL: 45 PERIODS

REFERENCES

1. Digital Image Processing, Rafeal C.Gonzalez, Richard E.Woods, Second Edition, Pearson Education/PHI., 2002
2. Digital Image Processing, Sridhar S, Second Edition, Oxford University Press, 2016
3. Introduction to Digital Image Processing with Matlab, Alasdair McAndrew, Thomson Course Technology, .Brooks/Cole 2004
4. Milan Sonka, Vaclav Hlavac, Roger Boyle, “Image Processing, Analysis and Machine Vision”, Second Edition, Thompson Learning, 2007.
5. Digital Image Processing using Matlab, Rafeal C.Gonzalez, Richard E.Woods, Steven L. Eddins, Pearson Education.Second Edition, 2017