Download presentation
Presentation is loading. Please wait.
1
Computers and Photographs 1) Image Processing 2) Computer Vision Henry Schneiderman
2
Outline Digital Cameras Emerging Technology Research in Image Processing and Computer Vision Automatically Finding Faces and Cars in Photographs
3
Digital Cameras = Convenience Easy to capture photos Easy to store and organize photos Easy to duplicate photos Easy to edit photos
4
Digital Camera Usage Lyra research report, 1999 Exposures in billions
5
State of the Art: Digital Cameras Film is currently better in resolution and color. –Professional photographers Digital for low quality newspaper adds Film for portrait photos Computer storage limitations: 1 high resolution digital image = 25 MegaBytes Printing –home printers not comparable to commercial printers
6
Future of Digital Cameras Improved resolution and color “Smart” cameras More programmable features –Auto-focus on object of interest –“Everything in focus” photo –Capture photo when event X occurs
7
Photographs: Migration to Digital Format Others means of digitizing imagery –Scanners (photo and film) –Frame-grabber for video
8
Existing and Emerging Technology 1. Document scanning 2. Biometrics 3. Management of images on computers 4. Other: manufacturing, military, games,...
9
Optical Character Recognition (OCR) First patent in OCR in 19 th century First applications in post-office and banks State of the art not perfect. Examples of errors:
10
Handwriting Recognition Works if constraints on writer, e.g. palm pilot
11
Other document processing Not just for text... Examples: –Engineering document to CAD file –Maps to GIS format –Music score to MIDI representation
12
Existing and Emerging Technology 1. Document scanning 2. Biometrics 3. Management of images on computers 4. Other: manufacturing, military, games, etc
13
Biometrics Technology for identification –Finger/palm print –Iris –Face
14
Fingerprints Minutae – spits and merges of ridges
15
Face Identification Not quite reliable yet. –Performance degrades rapidly with uncontrolled lighting, facial expression, and size of database Several companies exist: –Visionics (Rockfeller Univesity spin-off) –EyeMatic (USC spin-off) –Miros (MIT spin-off) –Banque-Tec Intl (Australia) –C-VIS Computer Vision (Germany) –LAU Technologies Commercial systems installed in London and Brazil to catch criminals
16
Existing and Emerging Technology 1. Document scanning 2. Biometrics 3. Management of images on computers 4. Other: manufacturing, military, games, etc
17
Management of images on computers Compression – reducing storage size needed for images Watermarking – Protecting copyright Microsoft, Bell Labs, NEC, etc. Visible watermark
18
Photo-manipulation Adobe Photoshop, Corel PhotoPaint, Pixami, PhotoIQ, etc. –More automatic features
19
Searching Digital Image Collections Large collections of images exist –Corbis 67 million images –Getty 70 million stock photography images –AP collects 1000s of digitized images per day Search methods are inadequate –Rely on captions and colors IBM’s Query by Image Content (QBIC) system
20
Existing and Emerging Technology 1. Document scanning 2. Biometrics 3. Management of images on computers 4. Other: manufacturing, military, games, etc
21
Inspection for Manufacturing Occum – inspection of printed circuit boards ($100M / year) Cognex – Do-it-yourself toolkits for inspection (400 employees)
22
Automatic Target Recognition (ATR) Finding mines, tanks, etc. Billion dollar a year industry –Martin-Lockheed, TSR, Northrup-Grumman, other aerospace contractors. Various types of imagery: –Synthetic Aperture Radar (SAR), Sonar, hyper- spectral imagery (more than 3 colors)
23
Aerial Photo Interpretation / Automated Cartography Classification of land-use: forest, vegetation, water Identification of man-made objects: buildings, roads, etc
24
Better Security Cameras Cameras that are responsive to the environment –Track and zoom on moving objects –Automatic adjustment of contrast
25
Human-Computer Interaction Computer games that involve interaction with user Intelligent teleconferencing
26
Medical imagery Medical image libraries for study and diagnosis Image overlay to guide surgeons
27
History 1980’s ~100 companies – manufacturing applications mostly Early 1990’s less than 10 companies Late 1990’s ~100 companies – face recognition, intelligent teleconferencing, inspection, digital libraries
28
Computer Vision and Image Processing Research
29
Image processing Computer vision chair, face, shape, etc. “Symbolic” descriptionimage
30
1. Image Processing: Filtering
31
2. Image Processing: Compression Lossless – No loss in quality, gif, tiff Lossy – Original image cannot be reconstructed, jpeg
32
3. Image Processing: Watermarking Information hiding –Protecting Copyright
33
4. Image Processing: Transformation Transforming image can make it easier to analyze Wavelet transform of image
34
Decomposition in Resolution/Frequency fine coarseintermediate
35
Wavelet Decomposition Vertical subbands (LH)
36
Wavelet Decomposition Horizontal subbands (HL)
37
1. Computer Vision: 3D Shape Reconstruction Use images to build 3D model of object or site 3D site model built from laser range scans collected by CMU autonomous helicopter
38
2. Computer Vision: To guide Motion Visually guided locomotion –robotic vehicles Visually guided manipulation –Hand-eye coordination CMU NavLab II
39
3. Computer Vision: Recognition and Classification
40
Challenges in Object Recognition 245 267 234 142 22 28 38 121 156 187 98 73 32 12 123 21 21 38 209 237 121 99 87 59 197 216 244
41
Challenges in Object Detection Intra-class variation
42
Lighting variation
43
Geometric variation
44
Simpler Problem: Classification Fixed size input Fixed object size, orientation, and alignment “Object is present” (at fixed size and alignment) “Object is NOT present” (at fixed size and alignment) Decision
45
1) Apply Local Operators f 1 (0, 1) = #3214 f 1 (0, 0) = #5710 f k (n, m) = #723
46
2) Look-Up Probabilities f 1 (0, 1) = #3214 f 1 (0, 0) = #5710 f k (n, m) = #723 P 1 ( #5710, 0, 0 | obj) = 0.53 P 1 ( #5710, 0, 0 | non-obj) = 0.56 P 1 ( #3214, 0, 1 | obj) = 0.57 P 1 ( #3214, 0, 1 | non-obj) = 0.48 P k ( #723, n, m | obj) = 0.83 P k ( #723, n, m | non-obj) = 0.19
47
Probabilities Estimated Off-Line f 1 (0, 0) = #567H 1 (#567, 0, 0) = H 1 (567, 0, 0) + 1 f k (n, m) = #350H k (#350, 0, 0) = H k (#350, 0, 0) + 1 P 1 (#567, 0, 0) = H 1 (#i, 0, 0) H 1 (#567, 0, 0) P k (#350, 0, 0) = H k (#i, 0, 0) H k (#350, 0, 0)
48
3) Make Decision P 1 ( #5710, 0, 0 | obj) = 0.53 P 1 ( #5710, 0, 0 | non-obj) = 0.56 P 1 ( #3214, 0, 1 | obj) = 0.57 P 1 ( #3214, 0, 1 | non-obj) = 0.48 P k ( #723, n, m | obj) = 0.83 P k ( #723, n, m | non-obj) = 0.19 0.53 * 0.57 *... * 0.83 0.56 * 0.48 *... * 0.19 >
49
Overall Algorithm f 1 (0, 1) = #3214 f 1 (0, 0) = #5710 f k (n, m) = #723 P 1 ( #5710,0,0 | obj) = 0.53 P 1 ( #5710, 0, 0 | non-obj) = 0.56 P 1 ( #3214,0,1 | obj) = 0.57 P 1 ( #3214,0,1 | non-obj) = 0.48 P k ( #723, n, m | obj) = 0.83 P k ( #723, n, m | non-obj) = 0.19 0.53 * 0.57 *... * 0.83 0.56 * 0.48 * … * 0.19
50
Detection: Apply Classifier Exhaustively Search in position Search in scale
51
View-based Classifiers Face Classifier #1 Face Classifier #2 Face Classifier #3
52
2 classifiers trained for faces. 8 classifiers trained for cars.
53
Training Classifiers Cars: 300-500 images per viewpoint Faces: 2,000 images per viewpoint ~1,000 synthetic variations of each original image –background scenery, orientation, position, frequency 2000 non-object images –Samples selected by bootstrapping Minimization of classification error on training set –AdaBoost algorithm (Freund & Shapire ‘97, Shapire & Singer ‘99) Iterative method Determines weights for samples
61
Applications of Face Detection Automatic red-eye removal from photographs Automatic color balancing in photo- finishing Intelligent teleconferencing Component in face identification system
62
Difficulty Increases with Complexity of Object 2D vs. 3D Specific objects – e.g. my coffee mug A category of objects – e.g. all coffee mugs Amount of intra-category variation –Rigid or semi-rigid structure, e.g. face –Articulated objects, e.g. human body –Functionally defined objects, e.g. chairs
63
Summary: Image Processing & Computer Vision Not as mature as speech recognition –Technology not as reliable –Fewer companies, fewer products Success on limited problems, e.g., documents More applicable to fault tolerant problems Technology will grow –Emergence of digital camera –Improved methods
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.