MC4011 Digital Image Processing Syllabus:

MC4011 Digital Image Processing Syllabus – Anna University PG Syllabus Regulation 2021

COURSE OBJECTIVES:

 Learn digital image fundamentals.
 Be exposed to simple image processing techniques.
 Learn to represent image enhancement in the spatial and frequency domain.
 Be familiar with image segmentation and compression techniques

UNIT I DIGITAL IMAGE FUNDAMENTALS

Elements of visual perception, Image Acquisition Systems, Sampling and Quantization, Image Formation, Image Geometry, Different types of digital images. Relationship between pixels, Basic concepts of distance transform, Color Image fundamentals-RGB-HIS Models, Different color models-conversion.

UNIT II IMAGE TRANSFORMS

1D Discrete Fourier Transform (DFT), 2D transforms – DFT, Discrete Cosine Transform, Walsh and PCA

UNIT III IMAGE ENHANCEMENT

Gray Level transformations, Histogram Equalization, Spatial Domain: Basics of Spatial Filtering: smoothing and sharpening spatial filters. Frequency domain: smoothing and sharpening frequency domain filters, Ideal, Gaussian filters.

UNIT IV IMAGE SEGMENTATION AND FEATURE EXTRACTION

Segmentation: Point detection, line detection, edge detection, Region based segmentation, Region Splitting and Merging Technique. Thresholding Techniques: multilevel thresholding, optimal thresholding using Bayesian classification. Feature Extraction: GLCM, Hough Transform, Morphological operation

UNIT V IMAGE COMPRESSION

Lossy and lossless compression schemes, prediction based compression schemes, sub-band encoding schemes, JPEG compression standard, Fractal compression scheme, Wavelet compression scheme

TOTAL:45 PERIODS

SUGGESTED ACTIVITIES:

1. Compute the GLCM Gray Level Co-occurrence Matrix matrix at (d=1, θ=0°)for the image of size nxn and derive the possible features from the GLCM matrix.
2. For the given 3*3 input matrix, perform histogram equalization (Assume the image is 5 bit)
3. Classify an image 8×8 into 3 classes using K- means clustering.
4. Tools – OpenCV/ Python / Matlab Trial Version
5. To read, view any image and convert a color image (peppers.png) into greyscale image, binary Image.
6. To obtain Discrete Cosine transform of any grey scale image (eg: cameraman.tiff).
7. Apply Principal Component Analysis (PCA) transform of any color image (eg: peppers.png) and prove that it reduces the dimensionality of the data.
8. By using (GLCM), extract the different features of any image (cameraman.tiff) like energy feature
9. Segment any image (peppers.png) by using thresholding, and compute Euclidean distance for classifying using k-NN classifier.

COURSE OUTCOMES:

Upon completion of the course, the students will be able to
CO1:digitize the input image using appropriate sampling and quantizing techniques
CO2:Transform the input images to various domains and classify the images
CO3:enhance the images using spatial domain and frequency domain for better visual representation
CO4:To extract the features of a image by applying Morphological Image Processing techniques.
CO5:Analyze the different image compression techniques and its significance

REFERENCES

1. Rafael C.Gonzalez and Richard E.Woods, “Digital Image Processing”, 4th Edition, Pearson Education, New Delhi, 2018
2. Jain Anil K.,”Fundamentals of Digital Image Processing”, 1st Edition, Prentice Hall of India, New Delhi, 2002.
3. Kenneth R.Castleman, “Digital Image Processing”, 1st Edition, Prentice Hall of India, New Delhi, 2006.
4. John C.Russ, “The Image Processing Handbook”, 5thEdition, Prentice Hall, New Jersey, 2002.
5. Willliam K Pratt, “Digital Image Processing”, 3rd Edition, John Willey,2002.
6. Dr.S.Sridhar, Digital Image Processing, Second Edition, Oxford University Press, 2016.