1 Comp300a: Introduction to Computer Vision L. QUAN.

Slides:



Advertisements
Similar presentations
Digital Image Fundamentals Selim Aksoy Department of Computer Engineering Bilkent University
Advertisements

Chapter 3 Image Enhancement in the Spatial Domain.
Digital Image Fundamentals Selim Aksoy Department of Computer Engineering Bilkent University
Digital Image Fundamentals Selim Aksoy Department of Computer Engineering Bilkent University
5/13/2015CAM Talk G.Kamberova Computer Vision Introduction Gerda Kamberova Department of Computer Science Hofstra University.
July 27, 2002 Image Processing for K.R. Precision1 Image Processing Training Lecture 1 by Suthep Madarasmi, Ph.D. Assistant Professor Department of Computer.
Digital Imaging and Image Analysis
Image (and Video) Coding and Processing Lecture 5: Point Operations Wade Trappe.
Image Processing IB Paper 8 – Part A Ognjen Arandjelović Ognjen Arandjelović
Digital Image Processing
DIGITAL IMAGE PROCESSING CMSC 150: Lecture 14. Conventional Cameras  Entirely chemical and mechanical processes  Film: records a chemical record of.
Bit Depth and Spatial Resolution SIMG-201 Survey of Imaging Science © 2002 CIS/RIT.
Capturing and optimising digital images for research Gilles Couzin.
Zhengya Xu, Hong Ren Wu, Xinghuo Yu, Fellow, IEEE, Bin Qiu, Senior Member, IEEE Colour Image Enhancement by Virtual Histogram Approach IEEE Transactions.
Multimedia for the Web: Creating Digital Excitement Multimedia Element -- Graphics.
Introduction to Computer and Human Vision Shimon Ullman, Ronen Basri, Michal Irani Assistants: Lena Gorelick Denis Simakov.
3. Introduction to Digital Image Analysis
Introduction to Computer and Human Vision Shimon Ullman, Ronen Basri, Michal Irani Assistants: Tal Hassner Eli Shechtman.
CS248 Midterm Review. CS248 Midterm Mon, November 3, 7-9 pm, Gates B01 Mostly “short answer” questions – Keep your answers short and sweet! Covers lectures.
Image Forgery Detection by Gamma Correction Differences.
Image Enhancement.
Introduction of the intrinsic image. Intrinsic Images The method of Finlayson & Hordley ( 2001 ) Two assumptions 1. the camera ’ s sensors are sufficiently.
CSc 461/561 CSc 461/561 Multimedia Systems Part A: 2. Image.
CS248 Midterm Review. CS248 Midterm Mon, November 5, 7-9 pm, Terman Aud Mon, November 5, 3-5 pm, Gates 392 Mostly “short answer” questions Covers through.
Digital Images The nature and acquisition of a digital image.
1/22/04© University of Wisconsin, CS559 Spring 2004 Last Time Course introduction Image basics.
Spectral contrast enhancement
A Brief Overview of Computer Vision Jinxiang Chai.
SCCS 4761 Introduction What is Image Processing? Fundamental of Image Processing.
Image processing Second lecture. Image Image Representation We have seen that the human visual system (HVS) receives an input image as a collection of.
Image Formation. Input - Digital Images Intensity Images – encoding of light intensity Range Images – encoding of shape and distance They are both a 2-D.
1 Image Basics Hao Jiang Computer Science Department Sept. 4, 2014.
Objective Understand concepts used to create digital graphics. Course Weight : 15% Part Three : Concepts of Digital Graphics.
CS654: Digital Image Analysis Lecture 17: Image Enhancement.
Digital Image Fundamentals Selim Aksoy Department of Computer Engineering Bilkent University
Math 3360: Mathematical Imaging Prof. Ronald Lok Ming Lui Department of Mathematics, The Chinese University of Hong Kong Lecture 1: Introduction to mathematical.
Digital Cameras, Digital Video and Scanners Vince DiNoto
1 Lecture 1 1 Image Processing Eng. Ahmed H. Abo absa
Introduction to Computer Vision Ronen Basri, Michal Irani, Shimon Ullman Teaching Assistants Tal Amir Ita Lifshitz Michal Yarom.
Computer Graphics & Image Processing Lecture 1 Introduction.
Lecture 3 The Digital Image – Part I - Single Channel Data 12 September
Image Representation. Digital Cameras Scanned Film & Photographs Digitized TV Signals Computer Graphics Radar & Sonar Medical Imaging Devices (X-Ray,
Digital Image Processing (DIP) Lecture # 5 Dr. Abdul Basit Siddiqui Assistant Professor-FURC 1FURC-BCSE7.
G52IIP, School of Computer Science, University of Nottingham 1 G52IIP Summary Topic 1 Overview of the course Related topics Image processing Computer.
Digital Image Processing NET 404) ) Introduction and Overview
Computer Vision Introduction to Digital Images.
Digital Imaging Fundamentals Ms. Hema C.R. School of Mechatronic Engineering.
Visual Computing Computer Vision 2 INFO410 & INFO350 S2 2015
CS 101 – Sept. 14 Review Huffman code Image representation –B/W and color schemes –File size issues.
Applying Pixel Values to Digital Images
Lesson 2: Introduction to Digital Imaging Digital Photography MITSAA IAP 2003 Rob Zehner.
Introduction to Image Processing Course Notes Anup Basu, Ph.D. Professor, Dept of Computing Sc. University of Alberta.
HOW SCANNERS WORK A scanner is a device that uses a light source to electronically convert an image into binary data (0s and 1s). This binary data can.
Robotics Chapter 6 – Machine Vision Dr. Amit Goradia.
Machine Vision. Image Acquisition > Resolution Ability of a scanning system to distinguish between 2 closely separated points. > Contrast Ability to detect.
Lecture 02 Point Based Image Processing Lecture 02 Point Based Image Processing Mata kuliah: T Computer Vision Tahun: 2010.
An Introduction to Digital Image Processing Dr.Amnach Khawne Department of Computer Engineering, KMITL.
Lecture 22 Image Restoration. Image restoration Image restoration is the process of recovering the original scene from the observed scene which is degraded.
Introduction to Digital Image Analysis Kurt Thorn NIC.
Lecture 10 Chapter 5: Image Restoration. Image restoration Image restoration is the process of recovering the original scene from the observed scene which.
IT – 472 Digital Image Processing
Digital 2D Image Basic Masaki Hayashi
Image Enhancement.
Introduction to Computer and Human Vision
Digital Image Fundamentals
Nuts and Bolts of Digital Imaging
Ceng466 Fundamentals of Image Processing
Digital Image Processing
Basic Concepts of Digital Imaging
Presentation transcript:

1 Comp300a: Introduction to Computer Vision L. QUAN

2 Course organisation Lectures on Tuesday and Thursday 4 labs (or mini-projects) Mid-term and final 30% labs+30% midterm+40%final

3 What is Computer Vision about? These fields are all closely related to 2d images, but different: Image processing: 2D images  2D images, well-defined pb. Computer vision: 2D images  3D reconstruction, hard ill-posed inverse pb. Computer graphics: 3D  2D, well-posed forward pb (+analysis & Interpretation)

4 What are applications? modeling for graphics visualization photo/video manipulation and editing robot navigation autonomous vehicules guiding tools for blind security and monitoring object/face recognition, OCR medical applications visual communication digital libraries …

5 What am I doing? Some examples

6 Overview Introduction –intersection of vision, graphics and image-based modeling and rendring –some basic mathematical tools (linear algebra, homogeneous coordinates, and optimisation) Modeling –Digital photography –Basic radiometry –Geometric modeling of camera –Camera calibration and pose estimation Image features –Filtering –Edge detection, polygonal approximation –Points of interest detection 3D reconstruction by multiple views: stereovision –Epipolar geometry –Computing correspondences –3D reconstruction

7 On-line computer vision courses

8 1. Basic Digital photography and image manipulations

9

10 Digital Images WorldCameraDigitizer Digital Image Image Formation: (i) What determines where the image of a 3D point appears on the 2D image? (ii) What determines how bright that image point is? (iii) How is a digital image represented? (iv) Some simple operations on 2D images? today Reflectance, radiometry geometry

x = What is a digital image? y = Pixel: picture element Typically: 0 = black 255 = white Black/white = grayscale image

12 Color Image

13 Three types of images: –Gray-scale images I(x,y)  [0..255] –Binary images I(x,y)  {0, 1} –Color images I R (x,y) I G (x,y) I B (x,y)

14 Image qualtiy: resolution (size, #pixels, aspect ratio) color depth compression

15 This graphic shows the relative sizes of a frame of 35mm film (red), the D60 image sensor (yellow), and a 1/1.8 CCD used in another digital camera (blue). Resolution:

16 ImageWidth x heightAspect Ratio 35 mm film36 x 24 mm1.50 Display monitor1024 x Nikon Coolpix x Photo paper4 x 6 inches1.50 Photo paper8 x 10 inches1.25 Cannon EOS D x HDTV16 x Aspect ratio:

17 Effects of down-sampling (reducing number of pixels): 4 x 4 32 x x 128

18 Resolution isn't the only factor, equally important is color depth, pixel-depth, or bit-depth. Color depth: #bit for each pixel in each channel

19 2 gray levels (1 bit/pixel) BINARY IMAGE 8 gray levels (3 bits/pixel) 256 gray levels (8 bits/pixel) Effects of reducing number of bits for each pixel:

20 A heavily compressed image A less compressed one Compression:

21 Image processing 1) Basic (global and nonlinear) operators 2) Spatial Domain 3) Frequency Domain - Histogram equalization - Gamma correction etc... later

22 A histogram is a graph that shows how the 256 possible levels of brightness are distributed in the image. Image histograme:

23 Occurrence (# of pixels) Gray Level H(k) = #pixels with gray-level k Normalized histogram: H norm (k)=H(k)/N (N = # pixels in the image) Histogram = The gray-level distribution: Continuous probability density function:

24 P I (k) k k P I (k) k 0.1

25 P I (k) k P I (k) k 0.1 Histogram Stretching

26 kk Histogram Equalization

27 OriginalEqualized

28 Gamma correction: Gamma correction controls the overall brightness of an image. Images which are not properly corrected can look either bleached out, or too dark. Trying to reproduce colors accurately also requires some knowledge of gamma. Varying the amount of gamma correction changes not only the brightness, but also the ratios of red to green to blue.

29 Correction L' = L ^ (1/2.5) Graph of Output L = V ^ 2.5 Sample Input to Monitor Graph of Input Output from Monitor