1. Computational Intelligence II Lecturer: Professor Pekka Toivanen E-mail: Pekka.Toivanen@uef.fiPekka.Toivanen@uef.fi Exercises: Nina Rogelj E-mail: nina.rogelj@uef.finina.rogelj@uef.fi

2. Segmentation

3. Access control for water in areas with water shortage (e.g. Australian outback); wildlife vs. livestock Install a gate that opens only when livestock enters Identify livestock using a Pattern Recognition system – Rugged outdoor camera captures the image – Edge detection and outline tracing – Match to a library of existing shape templates – Open the gate when there is a match Prototype system by Dunn et al., U. South Queensland, Australia. Authors claim that Sheep & goats can be separated with ~100% accuracy! Sheep Vs. Goat Vision Systems Design, November 2007 (www.vision-systems.com ) AllowDeny

4. Pattern Recognition Given an input pattern, make a decision about the “category” or “class” of the pattern Pattern recognition is needed in designing almost all automated systems Other related disciplines: data mining, machine learning, computer vision, neural networks, statistical decision theory This course will present various techniques to solve P.R. problems and discuss their relative strengths and weaknesses

5. Pattern Class A collection of similar (not necessarily identical) objects A class is defined by class samples (paradigms, exemplars, prototypes, training/learning samples) Intra-class variability Inter-class similarity How do we define similarity?

6. Intra-class Variability The letter “T” in different typefaces Same face under different expression, pose, illumination

7. Inter-class Similarity Identical twins Characters that look similar

8. Pattern Class Model A mathematical or statistical description for each pattern class (population); it is this class description that is learned from samples Given a pattern, choose the best-fitting model for it; assign the pattern to the class associated with the best- fitting model

9. Pattern Recognition Having been shown a few positive examples (and perhaps a few negative examples) of a pattern class, the system learns to tell whether or not a new object belongs in this class (Watanabe) Inferring a generality from a few exemplars COGNITION= Formation of new classes RECOGNITION = known classes

10. Pattern Recognition in Practice NY Times, Jan 12, 2010 Vision System Design, Nov 2009

11. Pattern Recognition Applications ProblemInputOutput Speech recognitionSpeech waveformsSpoken words, speaker identity Non-destructive testingUltrasound, eddy current, acoustic emission waveforms Presence/absence of flaw, type of flaw Detection and diagnosis of disease EKG, EEG waveformsTypes of cardiac conditions, classes of brain conditions Natural resource identification Multispectral imagesTerrain forms, vegetation cover Aerial reconnaissanceVisual, infrared, radar imagesTanks, airfields Character recognition (page readers, zip code, license plate) scanned imageAlphanumeric characters

12. Pattern Recognition Applications ProblemInputOutput Identification and counting of cells Slides of blood samples, micro- sections of tissues Type of cells Inspection (PC boards, IC masks, textiles) Scanned image (visible, infrared) Acceptable/unacceptable Manufacturing3-D images (structured light, laser, stereo) Identify objects, pose, assembly Web searchKey words specified by a userText relevant to the user Fingerprint identificationInput image from fingerprint sensors Owner of the fingerprint, fingerprint classes Online handwriting retrieval Query word written by a userOccurrence of the word in the database

13. Pattern Recognition System Challenges – Representation – Matching A pattern recognition system involves – Training/design/learning – Testing

14. Difficulties of Representation John P. Frisby, Seeing. Illusion, Brian and Mind, Oxford University Press, 1980 How should we model a face to account for the large intra-class variability?

16. Difficulties of Representation “ How do you instruct someone (or some computer) to recognize caricatures in a magazine, let alone find a human figure in a misshapen piece of work?” “A program that could distinguish between male and female faces in a random snapshot would probably earn its author a Ph.D. in computer science.” (Penzias 1989) A representation could consist of a vector of real- valued numbers, ordered list of attributes, parts and their relations….

17. Good Representation Should have some invariant properties (e.g., w.r.t. rotation, translation, scale…) Account for intra-class variations Ability to discriminate pattern classes of interest Robustness to noise, occlusion,.. Lead to simple decision making strategies (e.g., linear decision boundary) Low measurement cost; real-time

18. Pattern Recognition System Domain-specific knowledge – Acquisition, representation Data acquisition – camera, ultrasound, MRI,…. Preprocessing – Image enhancement, segmentation Representation – Features: color, shape, texture,… Decision making – Statistical (geometric) pattern recognition – Syntactic (structural) pattern recognition – Artificial neural networks Post-processing; use of context

19. System Performance Error rate (Prob. of misclassification) Speed (throughput) Cost Robustness Reject option Return on investment

21. Segmentation: Face Detection *Theo Pavlidis, http://home.att.net/~t.pavlidis/comphumans/comphuman.htm

22. Games Magazine, September 2001 Segmentation: Face Detection

23. Fish Classification: Salmon v. Sea Bass Preprocessing involves image enhancement and segmentation; (i) separate touching or occluding fishes and (ii) extract fish contour

24. Representation: Fish Length As Feature Training (design or learning) Samples

25. Probability Densities

26. Fish Lightness As Feature Overlap of these histograms is small compared to length feature

27. Two-dimensional Feature Space Two features together are better than individual features Linear (simple) decision boundary; Cost of misclassification?

28. Complex Decision Boundary Generalization ability of the learned boundary

29. Boundary With Good Generalization Simple decision boundaries are preferred

30. Feature Selection & Extraction How many and which subset of features to use in constructing the decision boundary? Some features may be redundant Curse of dimensionality—Error rate may in fact increase with too many features in the case of small number of training samples

31. Models for Pattern Recognition Template matching Statistical (geometric) Syntactic (structural) Artificial neural networks Hybrid approach

32. Template Matching Template Input scene Prototype

33. += Template Matching

34. Statistical Pattern Recognition Preprocessing Feature extraction Classification Learning Feature selection Recognition Training pattern Patterns + Class labels Preprocessing

35. Each pattern is represented as a point in d- dimensional feature space Choice of features and their desired invariance properties are domain-specific Good representation implies (i) small intra-class variation, (ii) large interclass separation and (iii) simple decision boundary Representation x1x1 x2x2 x1x1 x2x2

36. Invariant Representation Invariant to Translation Rotation Scale Skew Deformation Color Not all invariant properties are needed for a given application

37. Structural Patten Recognition Instead of describing an object in terms of a feature vector, describe it by its structure Describe complicated objects in terms of simple primitives and their relationship Y N M L T X Z Scene ObjectBackground DE LTXYZ MN D E

45. 45