Introduction to Computer and Human Vision

Slides:



Advertisements
Similar presentations
CS Spring 2009 CS 414 – Multimedia Systems Design Lecture 4 – Digital Image Representation Klara Nahrstedt Spring 2009.
Advertisements

Spatial Filtering (Chapter 3)
Topic 6 - Image Filtering - I DIGITAL IMAGE PROCESSING Course 3624 Department of Physics and Astronomy Professor Bob Warwick.
Chapter 3 Image Enhancement in the Spatial Domain.
July 27, 2002 Image Processing for K.R. Precision1 Image Processing Training Lecture 1 by Suthep Madarasmi, Ph.D. Assistant Professor Department of Computer.
EE 4780 Image Enhancement. Bahadir K. Gunturk2 Image Enhancement The objective of image enhancement is to process an image so that the result is more.
Digital Image Processing
Digital Image Processing In The Name Of God Digital Image Processing Lecture3: Image enhancement M. Ghelich Oghli By: M. Ghelich Oghli
CPSC 425: Computer Vision (Jan-April 2007) David Lowe Prerequisites: 4 th year ability in CPSC Math 200 (Calculus III) Math 221 (Matrix Algebra: linear.
1 © 2010 Cengage Learning Engineering. All Rights Reserved. 1 Introduction to Digital Image Processing with MATLAB ® Asia Edition McAndrew ‧ Wang ‧ Tseng.
Convolution. Spatial Filtering Operations g(x,y) = 1/M  f(n,m) (n,m) in  S Example 3 x 3 5 x 5.
The Fourier Transform Jean Baptiste Joseph Fourier.
Introduction to Computer and Human Vision Shimon Ullman, Ronen Basri, Michal Irani Assistants: Lena Gorelick Denis Simakov.
The Fourier Transform Jean Baptiste Joseph Fourier.
Introduction to Computer and Human Vision Shimon Ullman, Ronen Basri, Michal Irani Assistants: Mica Arie-Nachimson Denis Simakov.
Introduction to Computer and Human Vision Shimon Ullman, Ronen Basri, Michal Irani Assistants: Tal Hassner Eli Shechtman.
Digital Image Processing
1 Comp300a: Introduction to Computer Vision L. QUAN.
Introduction to Computer and Human Vision Shimon Ullman, Michal Irani Assistants: Shai Bagon Ira Kemelmacher Sharon Alpert.
1 Image Filtering Readings: Ch 5: 5.4, 5.5, 5.6,5.7.3, 5.8 (This lecture does not follow the book.) Images by Pawan SinhaPawan Sinha formal terminology.
Gholamreza Anbarjafari, PhD Video Lecturers on Digital Image Processing Digital Image Processing Spatial Domain Filtering: Part II.
Introduction to Computer and Human Vision Shimon Ullman, Ronen Basri, Michal Irani, Yaron Caspi Assistants: Shai Bagon Shira Kritchman.
2D Image Fourier Spectrum.
Topic 10 - Image Analysis DIGITAL IMAGE PROCESSING Course 3624 Department of Physics and Astronomy Professor Bob Warwick.
Digital Image Processing Lecture notes – fall 2008 Lecturer: Conf. dr. ing. Mihaela GORDAN Communications Department
University of Texas at Austin CS384G - Computer Graphics Fall 2010 Don Fussell Image processing.
Introduction to Computer Vision Ronen Basri, Michal Irani, Shimon Ullman Teaching Assistants Tal Amir Ita Lifshitz Michal Yarom.
Digital Image Processing (DIP) Lecture # 5 Dr. Abdul Basit Siddiqui Assistant Professor-FURC 1FURC-BCSE7.
Why is computer vision difficult?
Image Processing Part II. 2 Classes of Digital Filters global filters transform each pixel uniformly according to the function regardless of its location.
COMP322/S2000/L171 Robot Vision System Major Phases in Robot Vision Systems: A. Data (image) acquisition –Illumination, i.e. lighting consideration –Lenses,
Intelligent Vision Systems ENT 496 Image Filtering and Enhancement Hema C.R. Lecture 4.
Visual Computing Computer Vision 2 INFO410 & INFO350 S2 2015
Lecture # 19 Image Processing II. 2 Classes of Digital Filters Global filters transform each pixel uniformly according to the function regardless of.
2D Image Fourier Spectrum.
Introduction to Computer Vision Ronen Basri, Michal Irani, Shimon Ullman Teaching Assistants Tal Amir, Sima Sabah, Netalee Efrat, Nati Ofir, Yuval Bahat,
Introduction to Computer Vision Ronen Basri, Michal Irani, Shimon Ullman Primary Teaching Assistants Alon Faktor Ofer Bartal.
CS Spring 2010 CS 414 – Multimedia Systems Design Lecture 4 – Audio and Digital Image Representation Klara Nahrstedt Spring 2010.
EE 7730 Image Enhancement. Bahadir K. Gunturk2 Image Enhancement The objective of image enhancement is to process an image so that the result is more.
Introduction to Computer Vision Ronen Basri, Michal Irani, Shimon Ullman Teaching Assistants Uri Patish Alon Faktor Amir Rosenfeld.
Spatial Filtering (Chapter 3) CS474/674 - Prof. Bebis.
Image Enhancement in the Spatial Domain.
Lecture Six Figures from Gonzalez and Woods, Digital Image Processing, Second Edition, Copyright 2002.
Edge Detection Phil Mlsna, Ph.D. Dept. of Electrical Engineering Northern Arizona University.
ECE 692 – Advanced Topics in Computer Vision
IMAGE PROCESSING INTENSITY TRANSFORMATION AND SPATIAL FILTERING
Convolution.
Spatial Filtering - Enhancement
Image Enhancement.
- photometric aspects of image formation gray level images
Image Processing - in short
IMAGE PROCESSING AKSHAY P S3 EC ROLL NO. 9.
Histogram Histogram is a graph that shows frequency of anything. Histograms usually have bars that represent frequency of occuring of data. Histogram has.
Introduction to Computer Vision
Fundamentals of Image Processing A Seminar on By Alok K. Watve
Introduction Computer vision is the analysis of digital images
CIS 350 – 3 Image ENHANCEMENT SPATIAL DOMAIN
Image Enhancement in the Spatial Domain
Lecture 3 (2.5.07) Image Enhancement in Spatial Domain
CSC 381/481 Quarter: Fall 03/04 Daniela Stan Raicu
Histogram Probability distribution of the different grays in an image.
Digital Image Processing
Introduction to Computer Vision
Introduction to Computer Vision
Linear Operations Using Masks
Nov. 25 – Israeli Computer Vision Day
Introduction Computer vision is the analysis of digital images
Image Filtering Readings: Ch 5: 5. 4, 5. 5, 5. 6, , 5
Image Enhancement in the Spatial Domain
Convolution.
Presentation transcript:

Introduction to Computer and Human Vision Shimon Ullman, Ronen Basri, Michal Irani Assistants: Tal Hassner <hassner@wisdom.weizmann.ac.il> Eli Shechtman <elishe @wisdom.weizmann.ac.il>

Misc... Course website: www.wisdom.weizmann.ac.il/~hassner/cv0203 To be added to course mailing-list: send email to <hassner@wisdom….> Other recommended courses (for credit): - Basic Topics - Statistical Machine Learning Vision & Robotics Seminar (not for credit): Thursdays at 11:00-12:00 (Ziskind 1) send email <leah@wisdom…> ask to be added to “seminar13” mailing list

Applications: - Manufacturing and inspection; QA - Robot navigation - Autonomous vehicles - Guiding tools for blind - Security and monitoring - Object/face recognition; OCR. - Medical Applications - Visualization; NVS - Visual communication - Digital libraries and video search - Video manipulation and editing How is an image formed? (geometry and photometry) What kind of operations can we apply to images? What do images tell us about the world? (analysis & interpretation)

Tentative Schedule Lessons 1-3 (Michal): Basic Image Processing Lessons 4-6 (Ronen): Stereo and Structure from Motion Lessons 7-9 (Michal): Motion and video analysis Lesson 10 (Ronen): Image Segmentation Lesson 11 (Ronen): Photometry Lesson 12 (Shimon): Object recognition Lessons 13-14 (Shimon): Human Vision 3 programming exercises (MATLAB) -- CAN SUBMIT IN PAIRS 3-4 theoretical exercises -- MUST SUBMIT INDIVIDUALLY EXAM

Digital Images today Image Formation: World Camera Digitizer 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

Digital Images PIXEL World Camera Digitizer Digital Image Typically: 0 10 10 15 50 70 80 0 0 100 120 125 130 130 0 35 100 150 150 80 50 0 15 70 100 10 20 20 0 15 70 0 0 0 15 5 15 50 120 110 130 110 5 10 20 50 50 20 250 PIXEL Typically: 0 = black 255 = white (picture element)

64 60 69 100 149 151 176 182 179 65 62 68 97 145 148 175 183 181 65 66 70 95 142 146 176 185 184 66 66 68 90 135 140 172 184 184 66 64 64 84 129 134 168 181 182 59 63 62 88 130 128 166 185 180 60 62 60 85 127 125 163 183 178 62 62 58 81 122 120 160 181 176 63 64 58 78 118 117 159 180 176

Grayscale Image x = 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 210 209 204 202 197 247 143 71 64 80 84 54 54 57 58 206 196 203 197 195 210 207 56 63 58 53 53 61 62 51 201 207 192 201 198 213 156 69 65 57 55 52 53 60 50 216 206 211 193 202 207 208 57 69 60 55 77 49 62 61 221 206 211 194 196 197 220 56 63 60 55 46 97 58 106 209 214 224 199 194 193 204 173 64 60 59 51 62 56 48 204 212 213 208 191 190 191 214 60 62 66 76 51 49 55 214 215 215 207 208 180 172 188 69 72 55 49 56 52 56 209 205 214 205 204 196 187 196 86 62 66 87 57 60 48 208 209 205 203 202 186 174 185 149 71 63 55 55 45 56 207 210 211 199 217 194 183 177 209 90 62 64 52 93 52 208 205 209 209 197 194 183 187 187 239 58 68 61 51 56 204 206 203 209 195 203 188 185 183 221 75 61 58 60 60 200 203 199 236 188 197 183 190 183 196 122 63 58 64 66 205 210 202 203 199 197 196 181 173 186 105 62 57 64 63 y =

Three types of images: Gray-scale images Binary images Color images I(x,y)  [0..255] Binary images I(x,y)  {0 , 1} Color images IR(x,y) IG(x,y) IB(x,y)

Color Image

Effects of down-sampling (reducing number of pixels)

Effects of reducing number of gray levels (8 bits/pixel) 16 gray levels (4 bits/pixel) 8 gray levels (3 bits/pixel) 4 gray levels (2 bits/pixel) 2 gray levels (1 bit/pixel) BINARY IMAGE

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

The Image Histogram (Cont.) PI(k) 1 k PI(k) 1 0.5 k PI(k) 0.1 k

Histogram Stretching PI(k) k 0.1 PI(k) k 0.5 0.1

Histogram Equalization k k k

Histogram Equalization Original Equalized

Histogram Equalization 3000 3000 2500 2500 2000 2000 1500 1500 1000 1000 500 500 50 100 150 200 250 50 100 150 200 250 Original Equalized

Histogram Specification Transforms an image so that its histogram matches that of another image (e.g., for comparing two images of the same scene acquired under different lighting condition) Aa Ab k k

noisy image (salt & pepper noise) Image Enhancement 1) Gray value (histogram) Domain 2) Spatial Domain 3) Frequency Domain - Histogram stretching - Histogram equalization - Histogram specification - Gamma correction etc... noisy image (salt & pepper noise)

Spatial Operations g(x,y) = 1/M S f(n,m) Replace center pixel with average/median level: (averaging mask; weighted mask; median filter…) Examples of neighborhoods S: 3 x 3 5 x 5 S = neighborhood of pixel (x,y) M = number of pixels in neighborhood S e.g., g(x,y) = 1/M S f(n,m) (n,m) in S

Noise Cleaning Salt & Pepper Noise 3 X 3 Average 5 X 5 Average Median

Noise Cleaning Salt & Pepper Noise 3 X 3 Average 5 X 5 Average Median

Other spatial filters Are strong brightness variations always noise…?

Edge Detection

Edge Types Line Edge Step Edge gray value x edge edge gray value x

Edge Detection by Differentiation gray value 1D image f(x) x 1st derivative f'(x) threshold |f'(x)| Edge Pixels: |f'(x)| > Threshold

Original image x derivative y derivative Gradient magnitude

Edge Detection Image Vertical edges Horizontal edges

Edge Detection Image

Image Sharpening Blurry Image Laplacian Sharpened Image Also Laplacian; Zero-crossings; Edge sharpening; etc….

The End... Exercise#1: Noise Cleaning -- on course website (+ Matlab tutorial) DUE: Nov. 10 (in 2 weeks) Course mailing list: Send email to <hassner@wisdom….> Vision & Robotics Seminar: send email <leah@wisdom…> ask to be added to “seminar13” mailing list

Panoramic Mosaic Image Original video clip Generated Mosaic image

Video Removal Original Original Outliers Synthesized

Image Segmentation Note that the camouflaged Squirrel is detected. The background is still broken due the lack in oriented-texture measurements which we are currently adding into our algorithm.

Image Segmentation

Photometric Stereo

Photometric Stereo