Digital Image Processing Lecture 1: Introduction Prof. Charlene Tsai

Why digital image processing? Image is better than any other information form for human being to perceive. Humans are primarily visual creatures – above 90% of the information about the world (a picture is better than a thousand words) However, vision is not intuitive for machines  projection of 3D world to 2D images => loss of information  interpretation of dynamic scenes, such as a moving camera and moving objects

What is digital image processing? Image understanding, image analysis, and computer vision aim to imitate the process of human vision electronically  Image acquisition  Preprocessing  Segmentation  Representation and description  Recognition and interpretation

General procedures Goal: to obtain similar effect provided by biological systems Two-level approaches  Low level image processing. Very little knowledge about the content or semantics of images  High level image understanding. Imitating human cognition and ability to infer information contained in the image.

Low level image processing Very little knowledge about the content of the images. Data are the original images, represented as matrices of intensity values, i.e. sampling of a continuous field using a discrete grid. Focus of this course.

Low level image processing Origin (Ox,Oy) Spacing (Sy) Spacing (Sx) Pixel Value Pixel Region 3x3 neighborhood

Low level image processing Image compression Noise reduction Edge extraction Contrast enhancement Segmentation Thresholding Morphology Image restoration

Low level image processing Image compression Noise reduction Edge extraction Contrast enhancement Segmentation Thresholding Morphology Image restoration

Low level image processing Image compression Noise reduction Edge extraction Contrast enhancement Segmentation Thresholding Morphology Image restoration

Low level image processing Image compression Noise reduction Edge extraction Contrast enhancement Segmentation Thresholding Morphology Image restoration

Low level image processing Image compression Noise reduction Edge extraction Contrast enhancement Segmentation Thresholding Morphology Image restoration

Low level image processing Image compression Noise reduction Edge extraction Contrast enhancement Segmentation Thresholding Morphology Image restoration

Low level image processing Image compression Noise reduction Edge extraction Contrast enhancement Segmentation Thresholding Morphology Image restoration Erosion Dilation

Low level image processing Image compression Noise reduction Edge extraction Contrast enhancement Segmentation Thresholding Morphology Image restoration

High level image understanding To imitate human cognition according to the information contained in the image. Data represent knowledge about the image content, and are often in symbolic form. Data representation is specific to the high- level goal.

High level image understanding What are the high-level components? What tasks can be achieved? Landmarks (bifurcation/cross over) Traces (vessel centerlines)

Applications Medicine Defense Meteorology Environmental science Manufacture Surveillance Crime investigation

Applications: Medicine CT (computed Tomography) PET (Positron Emission Tomography PET/CT

Applications: Meteorology

Applications: Environmental Science

Applications: Manufacture

Application: Surveillance Courtesy of Simon Baker: Car Tracking Project from CMU: Tracking cars in the surrounding road scene and then generating a "bird's eye view" of the road.

Applications: Crime Investigation Fingerprint enhancement

What are the difficulties? Poor understanding of the human vision system Do you see a young or an old lady?

What are the difficulties? Human vision system tends to group related regions together, not odd mixture of the two alternatives. Attending to different regions or contours initiate a change of perception This illustrates once more that vision is an active process that attempts to make sense of incoming information.

What are the difficulties? The interpretation is based heavily on prior knowledge.

Just some fun visual perception games Can you count the dots?

More … Do you see squares? More at

Example: Detection of ozone layer hole Over the Antarctic, normal value around 300 DU

Class Format – Efficiency of Learning What we read10% What we hear20% What we see30% What we hear + see50% What we say ourselves70% What we do ourselves90%

Class Format – Efficiency of Learning This leads to in-class discussion and quizzes. 50-minute lecture Remaining for group discussion & in-class quiz

Course requirements In-class quizzes 10% 4 Homework assignments25% Final project25% Midtermexam20% Final exam20% Peer learning is encouraged BUT, NO PLAGIARISM!!! (20% deduction if caught)

Textbooks Problems in picking a good textbook:  Hard to find a textbook of the right level --- too easy or too hard.  Hard to find a textbook of the right price --- good books tend to be too expensive Prescribed:  Rafael C. Gonzalez, Richard E. Woods: Digital Image Processing. Prentice Hall; 2nd edition, 2002 Other references (used in 2005):  Alasdair McAndrew: Introduction to Digital Image Processing with Matlab, 2004.

Programming Tools Matlab with Image Processing Toolbox for homework exercises  MATLAB Tutorial:  MATLAB documentation:  User-contributed MATLAB IP functions: ory.do?objectType=category&objectId=26

More on Matlab University of Colorado Matlab Tutorials:  A decent collection of Matlab tutorials, including one focusing on image processing   ts/Matlab_tutorial/matlabimpr.html

Term project Group project of 2~3 people I decide the format of the term project You decide your own topic that interests you  So, starting thinking about it!!! You may implement your project with any programming language of your preference.

In-class quiz Goal: to enhance learning Open-book/open-notes format Group effort of 2~3 people to encourage discussion and peer learning

Looking ahead: lecture2 Image types File format Matlab programming.