0% found this document useful (0 votes)
20 views30 pages

1 Introduction

xla

Uploaded by

Kaito Chan
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
20 views30 pages

1 Introduction

xla

Uploaded by

Kaito Chan
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 30

Image Processing

HUYNH TRUNG TRU


Faculty of Information Technology No. 2
PTIT HCM
Mobile: 098.698.1177

Image Processing: Huynh Trung Tru, © 2023 PTIT HCM -- Introduction 1


Imaging

[Albrecht Dürer, 1525]

Image Processing: Huynh Trung Tru, © 2023 PTIT HCM -- Introduction 2


Imaging
X

y X

[Albrecht Dürer, 1525]

◼ Image: a visual representation in form of a function f (x,y)


where f is related to the brightness (or color) at point (x,y)
◼ Most images are defined over a rectangle
◼ Continuous in amplitude and space
Image Processing: Huynh Trung Tru, © 2023 PTIT HCM -- Introduction 3
Imaging

Dark chamber with lenses [Kircher 1646]

◼ Image: a visual representation in form of a function f (x,y)


where f is related to the brightness (or color) at point (x,y)
◼ Most images are defined over a rectangle
◼ Continuous in amplitude and space

Image Processing: Huynh Trung Tru, © 2023 PTIT HCM -- Introduction 4


Camera Obscura in San Francisco

Image Processing: Huynh Trung Tru, © 2023 PTIT HCM -- Introduction 5


Digital Images and Pixels
◼ Digital image: discrete samples f [x,y] representing continuous image f (x,y)
◼ Each element of the 2-d array f [x,y] is called a pixel or pel
(from “picture element“)

200x200 100x100 50x50 25x25

Image Processing: Huynh Trung Tru, © 2023 PTIT HCM -- Introduction 6


Color Components
Monochrome image

R[x,y] = G[x,y] = B[x,y]


20 μm

Red R[x,y] Green G[x,y] Blue B[x,y]

Image Processing: Huynh Trung Tru, © 2023 PTIT HCM -- Introduction 7


Why do we process images?
◼ Acquire an image
– Correct aperture and color balance
– Reconstruct image from projections
◼ Prepare for display or printing
– Adjust image size
– Color mapping, gamma-correction, halftoning
◼ Facilitate picture storage and transmission
– Efficiently store an image in a digital camera
– Send an image from space
◼ Enhance and restore images
– Touch up personal photos
– Color enhancement for security screening
◼ Extract information from images
– Read 2-d bar codes
– Character recognition
– Depth estimation
◼ Many more ... image processing is ubiquitous
Image Processing: Huynh Trung Tru, © 2023 PTIT HCM -- Introduction 8
Image Processing Examples
Mosaic from 33 source
images

Google Jump

facebook 360

Mosaic from 21 source images light.co


source: M. Borgmann, L. Meunier, EE368 class project, spring 2000.

Image Processing: Huynh Trung Tru, © 2023 PTIT HCM -- Introduction 9


Image Processing Examples
Face morphing

Source: Yi-Wen Liu and Yu-Li Hsueh, EE368 class project, spring 2000.

Image Processing: Huynh Trung Tru, © 2023 PTIT HCM -- Introduction 10


Image Processing Examples
Face Detection

source: Henry Chang, Ulises Robles, EE368 class project, spring 2000.

Image Processing: Huynh Trung Tru, © 2023 PTIT HCM -- Introduction 11


Image Processing Examples
Face Detection

source: Michael Bax, Chunlei Liu, and Ping Li, EE368 class project, spring 2003.

Image Processing: Huynh Trung Tru, © 2023 PTIT HCM -- Introduction 12


Image Processing Examples
Face Blurring for Privacy Protection

Image Processing: Huynh Trung Tru, © 2023 PTIT HCM -- Introduction 13


Image Processing Examples

http://cs.stanford.edu/group/roadrunner/stanley.html

Image Processing: Huynh Trung Tru, © 2023 PTIT HCM -- Introduction 14


Image Processing Examples
Visual Code Marker Recognition

EE368 Spring 2006 Project


Image Processing Examples
Painting Recognition

1 2 3 4

5 6 7 8

9 10 EE368 Spring 2007 Project

Image Processing: Huynh Trung Tru, © 2023 PTIT HCM -- Introduction 16


Image Processing Examples
Painting Recognition

EE368 Spring 2007 Project


Painting Recognition for Augmented Reality
Right-eye Left-eye
LCD LCD

Camera

Android
controller

Image Processing: Huynh Trung Tru, © 2023 PTIT HCM -- Introduction 18


Image Processing Examples
CD Cover Recognition

EE368 Spring 2007 Project

Image Processing: Huynh Trung Tru, © 2023 PTIT HCM -- Introduction 19


CD Cover Recognition on Cameraphone

Image Processing: Huynh Trung Tru, © 2023 PTIT HCM -- Introduction 20


Video See-through Augmented Reality on the Phone

Hershed Tilak & Robert Mahieu EE368, 2015/16


Image Processing Examples: Style Transfer
New art
Style
generated
examples
by algorihm

Original photos

Elias Wang, Nicholas Tan, EE368, 2016/17

Image Processing: Huynh Trung Tru, © 2023 PTIT HCM -- Introduction 22


INT13146 Topics

◼ Point operations/combining images/histograms


◼ Color science
◼ Image thresholding/segmentation
◼ Morphological image processing
◼ Image filtering, deconvolution, template matching
◼ Eigenimages, Fisherimages
◼ Edge detection, keypoint detection
◼ Scale-space image processing
◼ Image matching, image registration

Image Processing: Huynh Trung Tru, © 2023 PTIT HCM -- Introduction 23


Image Processing and Related Fields
Artificial Robotics,
Intelligence Computer Inspection,
Machine
Vision Photogrammetry
Vision
Machine
learning
Statistics, M-d
Information
Theory Image Image Signal
coding Processing
Processing
Visual
Perception Imaging
Computational
Photography

Display Computer
Technology Graphics Optical Engineering

Image Processing: Huynh Trung Tru, © 2023 PTIT HCM -- Introduction 24


INT13146 Weekly Assignments
◼ Weekly problem sets
⚫ Handed out Mondays, correspond to the lectures of that particular week
⚫ About 8-12 hours of work, requires computer + Python
⚫ Discussions among students encouraged, however, individual solution must be submitted
⚫ Due 9 days later (Wednesday 1:30 pm).
⚫ Late submission: 30% penalty if submitted by Friday 1:30 pm. No credit afterwards.
◼ First assignment handed out on January 8 (first day of class)

Image Processing: Huynh Trung Tru, © 2023 PTIT HCM -- Introduction 25


INT13146 Midterm
◼ 24-hour take-home exam
◼ Problems similar to weekly assignments
◼ Typically requires 5-6 hours of work
◼ 3 slots during week after the last lecture, February 28 – March 3

Image Processing: Huynh Trung Tru, © 2023 PTIT HCM -- Introduction 26


INT13146 Final Project
◼ Group project, teams of 3-5 students, exceptions possible.
◼ Plan for about 50-60 hours per person
◼ Develop, implement and test/demonstrate an image processing algorithm
◼ Project proposal due: February 12, 11:59 p.m.
◼ Project presentation: Poster session, March 14, 4:30-6:30 p.m.
◼ Remote SCPD students can alternatively submit a narrated video presentation
◼ Submission of written report and source code: March 16, 11:59 p.m.

Image Processing: Huynh Trung Tru, © 2023 PTIT HCM -- Introduction 27


INT13146 Grading

◼ Online quizzes: 10%


◼ Homework problems: 10%
◼ Midterm: 20%
◼ Final project: 60%
◼ No final exam.

Image Processing: Huynh Trung Tru, © 2023 PTIT HCM -- Introduction 28


Mobile image processing (optional)
◼ Up-to-date tutorials on Android image processing online
◼ Programming in Java (C++ for OpenCV)
◼ Limited number of loaner tablets for students who don‘t have their own device

Image Processing: Huynh Trung Tru, © 2023 PTIT HCM -- Introduction 29


Reading
◼ Slides available as pdf files on the class website (click on for source code and data)
http://e-learning.ptithcm.edu.vn/
◼ Popular text books
⚫ William K. Pratt, „Introduction to Digital Image Processing,“ CRC Press, 2013.
⚫ R. C. Gonzalez, R. E. Woods, „Digital Image Processing,“ 4th edition, Pearson, 2018.
⚫ A. K. Jain, „Fundamentals of Digital Image Processing,“ Addison-Wesley, 1989. (older, more mathematical)
◼ Software-centric books
⚫ R. C. Gonzalez, R. E. Woods, S. L. Eddins, „Digital Image Processing using Matlab,“
2nd edition, Gatesmark Publishing, 2009.
⚫ G. Bradski, A. Kaehler, „Learning OpenCV,“ O‘Reilly Media, 2008.
◼ Comprehensive state-of-the-art compendium
⚫ Al Bovik (ed.), „The Essential Guide to Image Processing,“ Academic Press, 2009.
◼ Journals/Conference Proceedings
⚫ IEEE Transactions on Image Processing
⚫ IEEE International Conference on Image Processing (ICIP)
⚫ IEEE Computer Vision and Pattern Recognition (CVPR)
⚫ ....

Image Processing: Huynh Trung Tru, © 2023 PTIT HCM -- Introduction 30

You might also like

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy