INTRODUCTION TO IMAGE PROCESSING
Politeknik Kota Malang Aditya Kurniawan, S.ST © 2011
WHAT IS THE DIFFERENCE ?
Image Processing Computer Vision Robot Vision 2 Aditya@poltekom.ac.id
IMAGE PROCESSING
A process to an image focusing on transforming, encoding and transmitting the image.
IMAGE
IMAGE
3 Aditya@poltekom.ac.id
COMPUTER VISION
Computer Vision => media to know the world visually supported by knowledge strength by computational instrument.
Description / humanized information
IMAGE
4 Aditya@poltekom.ac.id
ROBOT VISION
Robot Vision => a machine with ability to see his environment designed with workflow algorithm, so it can make a decision and finish the job automatically.
IMAGE
Action 5 Aditya@poltekom.ac.id
BLOCK DIAGRAM
Image Prosesing +
Computer Vision
Artificial Intelligent IT guys
+
Robot Vision
Hardware 6 Aditya@poltekom.ac.id
BLOK DIAGRAM
Image Prosesing +
Computer Vision
Artificial Intelligent
+
Robot Vision
Hardware MECHATRONIC guys 7 Aditya@poltekom.ac.id
INTRODUCTION
Modern digital technology has made it possible to manipulate multi-dimensional signals with systems that range from simple digital circuits to advanced parallel computers. The goal of this manipulation can be divided into three categories: Image Processing Image in image out
Image Analysis Image in measurements out
Image Understanding Image in high-level description out 8 Aditya@poltekom.ac.id
INTRODUCTION
Image Processing 9 Aditya@poltekom.ac.id
INTRODUCTION
Image Analysis
10 Aditya@poltekom.ac.id
INTRODUCTION
Image Understanding
11 Aditya@poltekom.ac.id
INTRODUCTION
We begin with certain basic definitions. An image defined in the “real world� is considered to be a function of two real variables, for example, a(x,y) with a as the amplitude (e.g. brightness) of the image at the real coordinate position (x,y).
12 Aditya@poltekom.ac.id
INTRODUCTION
An image may be considered to contain subimages sometimes referred to as regions–of–interest, ROIs, or simply regions. This concept reflects the fact that images frequently contain collections of objects each of which can be the basis for a region.
13 Aditya@poltekom.ac.id
INTRODUCTION
Coordinate Position
14 Aditya@poltekom.ac.id
INTRODUCTION
Y1
Y2
Regions X1 Of Interest
X2
15 Aditya@poltekom.ac.id
INTRODUCTION Y2
Y1
Regions Of Interest
Y3
Y4
Regions Of Interest X1 X2
16 Aditya@poltekom.ac.id
INTRODUCTION
In a sophisticated image processing system it should be possible to apply specific image processing operations to selected regions. Thus one part of an image (region) might be processed to suppress motion blur while another part might be processed to improve color rendition.
17 Aditya@poltekom.ac.id
INTRODUCTION Brightness enhancement
Contrast enhancement
18
Aditya@poltekom.ac.id
DIGITAL IMAGE DEFINITIONS
A digital image a[m,n] described in a 2D discrete space is derived from an analog image a(x,y) in a 2D continuous space through a sampling process that is frequently referred to as digitization. For now we will look at some basic definitions associated with the digital image. The effect of digitization is shown in Figure 1.
19 Aditya@poltekom.ac.id
DIGITAL IMAGE DEFINITIONS
0,2 nM
3,2 nM
Sample range of colour in reality world is an analog signal
20 Aditya@poltekom.ac.id
DIGITAL IMAGE DEFINITIONS
0,2 nM
3,2 nM
The idea of digitization Is taking sample of a range or an analog value
21 Aditya@poltekom.ac.id
DIGITAL IMAGE DEFINITIONS
0,2 nM
3,2 nM 00
01
10
11
2 bit colour representation
The idea of digitization Is taking sample of a range or an analog value 22
Aditya@poltekom.ac.id
DIGITAL IMAGE DEFINITIONS
23 Aditya@poltekom.ac.id
DIGITAL IMAGE DEFINITIONS
The 2D continuous image a(x,y) is divided into N rows and M columns. The intersection of a row and a column is termed a pixel (pixel comes from “picture element”). The value assigned to the integer coordinates [m,n] with {m=0,1,2,…,M–1} and {n=0,1,2,…,N–1} is a[m,n]. In fact, in most cases a(x,y) which we might consider to be the physical signal that impinges on the face of a 2D sensor is actually a function of many variables including depth (z), color (l), and time (t). Unless otherwise stated, we will consider the case of 2D, monochromatic, static images in this chapter. 24 Aditya@poltekom.ac.id
DIGITAL IMAGE DEFINITIONS A pixel contain these information : a (x, y, z, l, t)
a = illumination / light exposure in a certain pixel X = horizontal coordinate Y = vertical coordinate Z = depth L = colour T = time frame
25 Aditya@poltekom.ac.id
DIGITAL IMAGE DEFINITIONS A pixel contain these information : a (x, y, z, l, t) a = illumination / light exposure in a certain pixel
Low Light exposure
High Light exposure
26 Aditya@poltekom.ac.id
DIGITAL IMAGE DEFINITIONS A pixel contain these information : a (x, y, z, l, t) X, Y = 2 dimensional coordinate Y1
Y2
X1
X2
27 Aditya@poltekom.ac.id
DIGITAL IMAGE DEFINITIONS A pixel contain these information : a (x, y, z, l, t) Z = depth
bottom
surface
28 Aditya@poltekom.ac.id
DIGITAL IMAGE DEFINITIONS A pixel contain these information : a (x, y, z, l, t) l = colour
Yellow colour
Red colour
29 Aditya@poltekom.ac.id
DIGITAL IMAGE DEFINITIONS A pixel contain these information : a (x, y, z, l, t) Picture taken in a different time frame
t = time frame t1
t2
t3
t4
30
Introduction to Image Processing
Aditya@poltekom.ac.id
DIGITAL IMAGE DEFINITIONS
The image shown in Figure 1 has been divided into N = 16 rows and M = 16 columns. The value assigned to every pixel is the average brightness in the pixel rounded to the nearest integer value. The process of representing the amplitude of the 2D signal at a given coordinate as an integer value with L different gray levels is usually referred to as amplitude quantization or simply quantization.
31 Aditya@poltekom.ac.id
COMMON VALUES
There are standard values for the various parameters encountered in digital image processing. These values can be caused by video standards, by algorithmic requirements, or by the desire to keep digital circuitry simple. Table 1 gives some commonly encountered values.
32 Aditya@poltekom.ac.id
COMMON VALUES
Quite frequently we see cases of M=N=2K where {K = 8,9,10}. This can be motivated by digital circuitry or by the use of certain algorithms such as the (fast) Fourier transform. The number of distinct gray levels is usually a power of 2, that is, L=2B where B is the number of bits in the binary representation of the brightness levels. When B>1 we speak of a gray-level image; when B=1 we speak of a binary image. In a binary image there are just two gray levels which can be referred to, for example, as “black” and “white” or “0” and “1”. 33 Aditya@poltekom.ac.id
CHARACTERISTIC OF IMAGE OPERATIONS There is a variety of ways to classify and characterize image operations. The reason for doing so is to understand what type of results we might expect to achieve with a given type of operation or what might be the computational burden associated with a given operation.
34 Aditya@poltekom.ac.id
ADVANTAGES OF IMAGE PROCESSING
Medical Sharpen X-Ray result, Analysis of MRI, etc
Technology and Communications Reduce noise from satellite image, video streaming
Game Shadow effect on water surface, light effect, etc
Photography and Films Contrast, brightness, illegal photo manipulations, etc
35 Aditya@poltekom.ac.id
MEDICAL APPLICATION
36 Aditya@poltekom.ac.id
TECHNOLOGY AND COMMUNICATIONS
37 Aditya@poltekom.ac.id
DIGITAL IMAGE ACQUISITION PROCESS
38 Aditya@poltekom.ac.id