Review

Dec 4, 2020

MSBD 5010
 Topic 1
• Image representation
– Pixel = picture element
– Sampling
– Quantization
• MATLAB programming

MSBD 5010
 Topic 2
• Spatial domain image enhancement
– Intensity transformation functions
• Inverse or Image Negatives
• Brightening, e.g., log
• Darkening, e.g., nth power
• Power-law transformation
• Intensity normalization
– Histogram Equalization
• Contrast stretching
• Contrast compressing
• Global vs local
MSBD 5010
 Topic 2
• Spatial domain image enhancement
– Image operations
• Addition, subtraction, multiplication, AND,
OR, Not, etc.
– Image averaging, effect to noise
– Filtering using a mask
– Low-pass spatial filtering
– Median spatial filtering
– High-pass spatial filtering
MSBD 5010
 Topic 3
• Frequency domain image enhancement
– Discrete Fourier transform and inverse
– Notch filter
– Low-pass filtering, e.g., Ideal, Butterworth
and Gaussian
– Image power
– High-pass filtering, e.g., Ideal, Butterworth
and Gaussian

MSBD 5010
 Topic 4
• Image restoration and filtering
– Random noise distributions and parameter
estimation
– Periodic noise
– Arithmetic and Geometric mean filters
– Harmonic and Contraharmonic mean filters
– Order-statistics filters
• Median, max&min, midpoint and alpha-trimmed
mean filters
– Adaptive filters
• Local noise reduction filter
• Median filter

MSBD 5010
 Topic 4
• Image restoration and filtering
– Frequency domain filtering
• Bandreject, bandpass, notch filters
– Restoration based on degradation
function
• Inverse filter, Wiener filter and Geometric
mean filter
– Geometric transformations for distortion
correction

MSBD 5010
 Topic 4
• Non-linear filtering
– linear diffusion filtering
– non-linear isotropic diffusion filtering
– non-linear anisotropic diffusion filtering
– edge-enhancing anisotropic diffusion
filtering (not examined)

MSBD 5010
 Topic 5
• Morphological image processing
– Set theory review
– Dilation and erosion
– Opening and closing
– Boundary extraction
– Region filling
– Connected components
– Skeletons
– Extensions to gray-scale images

MSBD 5010
 Topic 6
• Image segmentation
– Point, line and edge detection (Prewitt, Sobel
and Laplacian of Gaussian)
– Hough transform, e.g., straight line, circle, etc
– Thresholding (Global and Adaptive)
– Statistical mixture model
– Expectation-maximisation method
– Morphological Watersheds

MSBD 5010
 Topic 6
• Image segmentation
– Motion, e.g., difference image and
accumulative difference approaches
– Active contour models
• Snakes
• Quadratic energy functionals (not examined)
• Example using level set methods (not examined)

MSBD 5010
 Topic 7
• Image registration
– Geometric transformations, e.g., translation,
rotation, scale, shearing, affine
– Objective functions based on features and
voxel intensity
– Part-based matching (not examined)
• Single part registration
• Pairwise part registration

MSBD 5010
 Topic 8
• Image compression
– Coding, interpixel and psychovisual
redundancies
– Source encoder and decoder
– Channel encoder and decoder, e.g.,
Hamming coding
– Lossless compression
• Huffman encoding
• Lossless predictive coding

MSBD 5010
 Topic 8
• Image compression
– Lossy compression
• Lossy predictive coding
• Transform coding
• JPEG

MSBD 5010
 Topic 9 and Topic 10
• Face detection and recognition
– Face detection using image pyramid, integral
image and AdaBoost learning
– Face recognition using Eigenfaces
– Near-infrared images for face recognition (not
examined)

• Feature descriptors
– Local Binary Pattern (LBP)
– Corner Detection (not examined)

MSBD 5010
 Course outcomes
On successful completion of this course, students are expected to be
able to

1. Identify basic image enhancement techniques in both the spatial

MSBD 5010
 MSBD 5010 Final Examination
• Dec 11, 2020, Friday
• Time: 7:30 pm - 10:30 pm
• Venue and format:
– online proctored exam (details will be available, e.g., dry run)
– Virtual background and video filter, please disable
– Consent to be unmute
– Need to check ID
– Follow HKUST Academic Honor Code
• Coverage: Topic 1 – Topic 10, hand-written notes,
assignments, tutorial materials, some IP&CV related
topics.
• Closed notes and Closed books
• Welcome to make appointment if there are questions

MSBD 5010
 Examples

MSBD 5010
 Examples

MSBD 5010
 Examples

MSBD 5010
 Examples

MSBD 5010
 Examples

MSBD 5010
 Examples

MSBD 5010