1. 嵌入式視覺 Pattern Recognition for Embedded Vision Template matching Statistical / Structural Pattern Recognition Neural networks

2. Embedded Vision System Image acquisition Image Processing Feature Extraction Decision Making(Pattern Recognition)

3. Pattern Recognition model 1. Template matching 2. Statistical Pattern Recognition: based on underlying statistical model of patterns and pattern classes. 3. Structural (or syntactic) Pattern Recognition : pattern classes represented by means of formal structures as grammars, automata, strings, etc. 4. Neural networks: classifier is represented as a network of cells modeling neurons of the human brain (connectionist approach).

4. Pattern Representation A pattern is represented by a set of d features, or attributes, viewed as a d-dimensional feature vector.

5. Preprocessing Feature Measurement Feature Measurement Classification test pattern Classification Mode Preprocessing Feature Extraction/ Selection Feature Extraction/ Selection Learning training pattern Training Mode Two Process for Pattern Recognition system

6. Generic concepts for PR Feature vector - A vector of observations (measurements). - is a point in feature space. Hidden state - Cannot be directly measured. - Patterns with equal hidden state belong to the same class. Task - To design a classifer (decision rule) which decides about a hidden state based on an onbservation. Patter n

7. Pattern Representation by Feature Vector for Character Recognition X=[x1, x2, …, xn], each xj a real number Xj may be object measurement Xj may be count of object parts Example: object rep. [#holes, Area, moments, ]

8. Example height weight Task: identity recognition. The set of hidden state is The feature space is Training examples Linear classifier:

9. Pattern Recognition system Image processing Feature extraction Classifier Class assignment Image acquisition and image processing. Feature extraction aims to create discriminative features good for classification. Classifier. Learning algorithm sets PR from training examples-- supervised learning Learning algorithm Objec t

10. Feature extraction Task: to extract features which are good for classification. Good features: Objects from the same class have similar feature values. Objects from different classes have different values. “Good” features“Bad” features

11. Feature extraction methods Feature extractionFeature selection Problem can be expressed as optimization of parameters of featrure extractor. Supervised methods: objective function is a criterion of separability (discriminability) of labeled examples, e.g., linear discriminat analysis (LDA). Unsupervised methods: lower dimesional representation which preserves important characteristics of input data is sought for, e.g., principal component analysis (PCA).

12. Classifier A classifier partitions feature space X into class-labeled regions such that and The classification consists of determining to which region a feature vector x belongs to. Borders between decision boundaries are called decision regions.

13. CSE803 Fall 2014 13 Decision-Tree Classifier Uses subsets of features in seq. Feature extraction may be interleaved with classification decisions Can be easy to design and efficient in execution

14. 14 Decision Trees #holes moment of inertia #strokes best axis direction #strokes - / 1 x w 0 A 8 B 0 1 2 < t  t 2 4 01 0 60 90 0 1

15. 15 Classification using nearest class mean Compute the Euclidean distance between feature vector X and the mean of each class. Choose closest class, if close enough (reject otherwise)

16. Unsupervised learning Input: training examples {x 1,…,x } without information about the hidden state. Clustering: goal is to find clusters of data sharing similar properties. Classifier Learning algorithm Classifier Learning algorithm (supervised) A broad class of unsupervised learning algorithms:

17. Example of unsupervised learning algorithm k-Means clustering: Classifier Goal is to minimize Learning algorithm