Хэв танилтын үндэс

(Introduction to Pattern Recognition )

Лекц 2. Дүрс боловсруулалт

Монгол Улсын Их Сургууль, ХШУИС

Д-р, дэд проф. Б.Сувдаа
Contents

Introduction to Digital Image Fundamentals (Chapter

2)
Elements of Visual Perception
Image Sensing and Acquisition
Image Sampling and Quantization
Basic relationships between pixels
Mathematical Tools used in DIP
IntensityTransformations and Spatial Filtering
(Chapter 3)
 Elements of Visual Perception
Structure of Human Eye
Average diameter - 20 mm
3 membranes enclose the eye:
• Cornea and sclera outer cover (transparent)
• The choroid (network of blood vessels)-> ciliary body, iris (diameter
varies 2 to 8 mm)
• The retina (inside of the wall’s )
Elements of Visual Perception (con’t)

Distribution of rods and cons in the retina

2 classes of receptors
•Cones (fovea) 6~7 million, high sensitive to color (Cone vision
called photopic or bright-light vision)
•Rods 75~120 million, not color, high sensitive to low levels of
illumination. (it called scotopic or dim-light vision)
Elements of Visual Perception (con’t)

Mach band effect

Ernst Mach first described phenomenon in 1985
Elements of Visual Perception (con’t)
 Image Sensing and Acquisition

 How to sense
 Incoming energy is transformed into a voltage by the combination of input
electrical power and sensor material that is responsive to the particular type
of energy being detected.
 The output voltage waveform is the response of the sensor(s) and a digital
quantity is obtained from each sensor by digitizing its response
Image Sensing and Acquisition (con’t)

 Simple image formation model

f(x,y)=i(x,y)r(x,y)+n(x,y)

Intensity – proportional to energy

0<f(x,y)<∞ radiated by a physical source

0<i(x,y)<∞ illumination

0<r(x,y)<1 reflectance

n(x,y) noise

l = f(xi,yi) Lmin ≤ l ≤ Lmax

Image Sampling and Quantization

 Convert the continuous

sensed data into digital
image
 Sampling – to sample the
function in both
coordinates and in
amplitude. (Digitizing the
coordinate values)
 Quantization – in order to
form a digital function, the
intensity values also must
be quantized into discrete
quantities.
Image Sampling and Quantization (con’t)
 Representing digital image
 As a surface
 As a visual intensity array
 As a 2-D numerical array
 The number of intensity levels typically is an integer power of 2:
 L=2K
 A digital image requires b number of bits:
 b=M x N x k
Image Sampling and Quantization (con’t)

 Spatial and Intensity Resolution

Image Sampling and Quantization (con’t)

Image interpolation
 Zooming :
 nearest neighbor
interpolation
 pixel replication
 bilinear interpolation
 to use more neighbors
 shrinking :
 the reverse of zooming
Basic relationships between pixels

Neighbors, adjacency
 neighbors of a pixel p
 4-neighbors
 four diagonal neighbors
 8-neighbors
 adjacency of two pixels
 4-adjacency
 8-adjacency
 m (mixed)-adjacency: without confusion
 adjacency of two image subsets
 path (or curve) from pixel p to pixel q
 length of path
 closed path
 Basic relationships between pixels (con’t)

Distance measures
Euclidean distance D8 distance For pixels p, q, and z , with coordinate s
(2-norm) (checkboard distance)
(x,y), (s,t), and (v,w), respective ly,
2 2 5 2 52 2 2 2 2 2 2
2 1 2 5 1
D is a distance function or metric if
5 2 1 1 2
2 1 0 1 2 2 1 0 1 2 (a) D ( p, q )  0 ( D ( p, q ) = 0 iff p = q )
5 2 1 2 5 2 1 1 1 2 (b) D ( p,q ) = D (q,p ), and
2 2 5 2 52 2 2 2 2 2 2 (c) D ( p,z )  D ( p,q ) + D (q,z )
D4 distance
(city-block distance)
De ( p, q ) = ( x − s ) 2 + ( y − t ) 2
4 3 2 3 4
3 2 1 2 3 D4 ( p, q ) = x − s + y − t
2 1 0 1 2
1
D8 ( p, q ) = max( x − s , y − t )
3 2 2 3
4 3 2 3 4 Dm = shortest m - path
Mathematical Tools used in DIP

 Arithmetic operations carried out between corresponding

pixel pairs
Mathematical Tools used in DIP (con’t)

Logical operations

 AND
 OR
 NOT
 XOR
Mathematical Tools used in DIP (con’t)

Spatial Operations
 Single-pixel operations
 Neighborhood operations
 Geometric spatial transformations
Chapter 3. Intensity Transformations and
Spatial Filtering
Contents

The Basics of Intensity Transformation and Spatial

Filtering
Histogram Processing
Fundamentals of Spatial Filtering
Smoothing Spatial Filters
Sharpening Spatial Filters
Combining Spatial Enhancement Methods
Intensity Transformation and Spatial Filtering

 Image enhancement seeks

 to improve the visual appearance of an image, or
 convert it to a form suited for analysis by a human or a
machine.
 Image enhancement does not
 seek to restore the image
 increase its information contents
Intensity Transformation and Spatial
Filtering (con’t)
Intensity transformation
Change the intensity of each pixel in order to enhance the
image:
where f(x, y): input image, g(x, y):
processed image, and T: operator

where r: input pixel, and s: output pixel

Intensity Transformation and Spatial
Filtering (con’t)
 3 types of functions for Image Enhancement:
 Linear (negative)
 Logarithmic (log and inverse-log)
 Power-law (nth power and nth root)
Intensity Transformation and Spatial
Filtering (con’t)
 Logarithmic transformation:
 where
 Logarithmic transformations are used for dynamic
range manipulation and are implemented using
 This transformation expands the values of dark pixels
in an image while compressing the higher level
values
 The opposite is true for the inverse log transform
Intensity Transformation and Spatial
Filtering (con’t)
 Power law (gamma) transformation has the basic form
 where c and γ are positive constants
 The transformation is entirely controlled by γ
 The transformation is similar to the log transformation but it
is easier to be tuned
Intensity Transformation and Spatial
Filtering (con’t)
 Contrast Stretching
Intensity Transformation and Spatial
Filtering (con’t)
 Gray-Level Slicing highlights range [A, B] of gray levels
 and reduces all others to a constant level
 but preserves all other levels
Intensity Transformation and Spatial
Filtering (con’t)
 Bit-plane slicing
Histogram Processing

 Histogram:

 Normalized Histogram
Histogram Processing (con’t)

 Monotonically Increasing Function

Histogram Processing (con’t)

 Histogram Equalization
 The intensity levels in an image may be viewed as random variables in the
interval [0, L-1].
 A fundamental descriptor of a random variable is its probability density
function (PDF)

 The transformation (mapping) in this equation is called a histogram

equalization transformation
Histogram Processing (con’t)

 Histogram Equalization
Example
Histogram Processing (con’t)

 Histogram Equalization
Example

Transformation functions
Histogram Processing (con’t)

 Histogram Matching (Specification)

 To generate a processed image that has a specified histogram is
called Histogram Matching or Histogram Specification
Histogram Processing (con’t)

 Histogram Matching
(Specification)
Example
 Histogram Processing (con’t)

 Local Enhancement
 Previous enhancement methods are global (an entire image)
 Global filters are useful for overall enhancement
 There are cases in which it is necessary to enhance details over small areas in
an image
 To map the intensity of the pixel centered in the neighborhood
 To reduce computation is to utilize nonoverlapping regions -> ‘blocky’ effect
Histogram Processing (con’t)

 Enhancement by Statistics
Histogram Processing (con’t)

 Enhancement using Arithmetic / Logic Operations

Fundamentals of Spatial Filtering

 Mechanics of Spatial Filtering

 Window sliding
 Edge pixels padding

window (kernel, mask)

Fundamentals of Spatial Filtering (con’t)

 Mechanics of Spatial Filtering

Fundamentals of Spatial Filtering (con’t)

 Spatial Correlation and Convolution

Smoothing Spatial Filters

 Smoothing Linear Filters

Smoothing Spatial Filters (con’t)

 Smoothing Linear Filters

 Example with different mask sizes

Original image
(500 x 500 pixels) 3 x 3 mask

5 x 5 mask
9 x 9 mask

15 x 15 mask 35 x 35 mask
Smoothing Spatial Filters (con’t)

 Smoothing Linear Filters

 Averaging
Smoothing Spatial Filters (con’t)

 First – Order Statistic (Nonlinear) Filters

 Median filter
Sharpening Spatial Filters

 Sharpening Linear Filters (Low-Pass Filter)

 First-Order derivatives

 Second-Order derivatives
Sharpening Spatial Filters

 Sharpening Linear Filters

Sharpening Spatial Filters (con’t)

 Using Second-Derivative for Image Sharpening - The

Laplacian
 Isotropic or rotation invariant filters
 Linear operator
Sharpening Spatial Filters (con’t)

 Using Second-Derivative for Image Sharpening - The Laplacian

 Example
Sharpening Spatial Filters (con’t)

 Unsharp Masking and Highboost Filtering

 Blur the original image
 Subtract the blurred image from the original image (the resulting
difference is called the mask)
 Add the mask to the original

If k>1, it is called high-boost filtering

Sharpening Spatial Filters (con’t)

 Unsharp Masking and High-boost Filtering

Sharpening Spatial Filters (con’t)

 Using First –Order Derivatives for (Nonlinear) Image Sharpening -

The Gradient
Sharpening Spatial Filters (con’t)

 Using First –Order Derivatives for (Nonlinear) Image Sharpening -

The Gradient

Roberts operators

Sobel operators
Sharpening Spatial Filters (con’t)

 Edge Enhancement by Gradient

Combining Spatial Enhancement Methods

 Combination of several filters

References
 http://www.cs.uregina.ca/Links/class-
info/425/Lab3/index.html
Any questions ?