Pattern Recognition Concepts

1
Chapter 4

• Pattern Recognition Concepts
• continued

2
Using features

• Ex. Recognizing characters
• Area
• Height
• Width
• of holes
• of strokes
• Centroid
• Best axis (of least inertia)
• Second moments (about axis of least and most
  inertia)

3
Decision tree
4
(No Transcript)
5
(No Transcript)
6
Classifying using nearest class mean

• Some problems are more fuzzy and cant be
  solved using simple decision trees.
• To classify an candidate, c, compute its distance
  from all know class means and assign it to the
  same class as the class of the nearest mean.

7
Classifying using nearest class mean (with good
results)
8
Euclidean distance (and scaled Euclidean distance)
9
Classifying using nearest class mean (with poor
results)
10
Classifying using nearest neighbor

• To classify an candidate, c, compute its distance
  to all member of all know classes and assign it
  to the same class as the class of the nearest
  element.

11
(No Transcript)
12
Precision vs. recall

• Say we have an image db we wish to query.
• Show me all images of tanks.
• Precision of relevant documents retrieved
  divided by the total number of documents
  retrieved
• Precision TP / (TPFP)
• PPV positive predictive value
• Probability that the target is is actually
  present when the observer says that is it
  present.

13
Precision vs. recall

• Say we have an image db we wish to query.
• Show me all images of tanks.
• Recall of relevant documents retrieved
  divided by the total number of relevant documents
  in the db.
• Recall TP / (TPFN) TPF
• Negative predictive value
• NPV TN / (TNFN)
• Probability that the target is actually absent
  when the observer says that it is absent.

14
Structural (pattern recognition) techniques

• Simple features may not be enough for
  recognition.
• So relationships between these primitive features
  are used (in structural techniques).

15

• Same bounding box, holes, strokes, centroid, 2nd
  moments in row and column directions, and similar
  major axis direction.

16
bayintrusion of background
17
bayintrusion of background
lidvirtual line segment that close the bay
18
Structural graph

• G(V,E)
• where is a vertex set and E is an edge set
• V
• S side
• L lake
• B bay
• E
• CON connection of 2 strokes
• ADJ stroke region is immediately adjacent to a
  lake or bay region
• ABOVE 1 hole (lake or bay) lies above another

19
(No Transcript)
20
Structural conclusions

• Graph-matching techniques can be used for
  recognition.
• Or we can count occurrences of relationships and
  use these counts as a feature vector for
  statistical PR.

21
Confusion matrix
22

• Empirical error rate misclassified
• Empirical reject rate rejected

23

• Empirical error rate misclassified 25/1000
  overall (does not include rejects) 5/100 for 9s
• Empirical reject rate rejected 7/1000
• Can ROC analysis be applied?

24

• Recall ROC analysis
• TP true positive present and detected
• TN true negative not present and not detected
• FP false positive not present but detected
• FN false negative present but not detected
• True positive fraction
• TPF TP / (TPFN)
• true abnormals called abnormal by the observer
• False positive fraction
• FPF FP / (FPTN)

25

• Ex. ROC analysis for the classification of 3
• TP present and detected
• TN not present and not detected
• FP not present but detected
• FN present but not detected

26
Skip remainder of Chapter 4
27
(No Transcript)
28
(No Transcript)
29
(No Transcript)
30
(No Transcript)
31
(No Transcript)
32
(No Transcript)
33
(No Transcript)
34
(No Transcript)
35
(No Transcript)
36
(No Transcript)
37
(No Transcript)