Computational Intelligence II Lecturer Professor Pekka Toivanen Email

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

Segmentation

Sheep Vs. Goat • 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 Deny Allow • 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! Vision Systems Design, November 2007 (www. vision-systems. com)

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

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?

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

Inter-class Similarity Characters that look similar Identical twins

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 bestfitting model

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

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

Pattern Recognition Applications Problem Input Output Speech recognition Speech waveforms Spoken words, speaker identity Non-destructive testing Ultrasound, eddy current, acoustic emission waveforms Presence/absence of flaw, type of flaw Detection and diagnosis of disease EKG, EEG waveforms Types of cardiac conditions, classes of brain conditions Natural resource identification Multispectral images Terrain forms, vegetation cover Aerial reconnaissance Visual, infrared, radar images Tanks, airfields Character recognition (page readers, zip code, license plate) scanned image Alphanumeric characters

Pattern Recognition Applications Problem Input Output Identification and counting Slides of blood samples, microof cells sections of tissues Type of cells Inspection (PC boards, IC masks, textiles) Scanned image (visible, infrared) Acceptable/unacceptable Manufacturing 3 -D images (structured light, laser, stereo) Identify objects, pose, assembly Web search Key words specified by a user Text relevant to the user Fingerprint identification Input image from fingerprint sensors Owner of the fingerprint, fingerprint classes Online handwriting retrieval Query word written by a user Occurrence of the word in the database

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

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

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 realvalued numbers, ordered list of attributes, parts and their relations….

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

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

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

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

Segmentation: Face Detection Games Magazine, September 2001

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

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

Probability Densities

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

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

Complex Decision Boundary Generalization ability of the learned boundary

Boundary With Good Generalization Simple decision boundaries are preferred

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

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

Template Matching Template Prototype Input scene

Template Matching + =

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

Representation • Each pattern is represented as a point in ddimensional feature space • Choice of features and their desired invariance properties are domain-specific x 2 x 1 • Good representation implies (i) small intra-class variation, (ii) large interclass separation and (iii) simple decision boundary

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

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 Scene N L T M X Y Object Z D D Background E M E L T X Y Z N

45