8
Coin Counter Andres Uribe

Coin Counter

  • Upload
    saki

  • View
    51

  • Download
    0

Embed Size (px)

DESCRIPTION

Coin Counter. Andres Uribe. what. Find out the amount of money in a coin picture. $4.10. How – Classifier. Build a coin classifier Bayes Classifier Nearest Neighbor SVMs Segment coins and create feature vectors. How - DATA. 80 images of standard US coins. 10 for each class: - PowerPoint PPT Presentation

Citation preview

Page 1: Coin Counter

Coin Counter

Andres Uribe

Page 2: Coin Counter

what

• Find out the amount of money in a coin picture.

$4.10

Page 3: Coin Counter

How – Classifier

• Build a coin classifier– Bayes Classifier– Nearest Neighbor– SVMs

• Segment coins and create feature vectors

Page 4: Coin Counter

How - DATA

• 80 images of standard US coins.• 10 for each class:– Quarter: front and back– Dime: front and back– Nickel: front and back– Penny: front and back

Page 5: Coin Counter

How – Segmentation

– Use of the Hough Transform to detect circles– Threshold selection to segment background

100 200 300 400 500 600 700 800 900

100

200

300

400

500

600

Page 6: Coin Counter

How – Features

– Radial edge distribution:• Detect edges in the coin image• Construct a normalized edge radial histogram with 2, 4,

8, 16 and 32 bins.

Page 7: Coin Counter

Results

– Classifier:• Bayes: 72.5%• SVM: yet to be implemented.• NNR: yet to be implemented.

– Money counter:• First approach uses too much memory for the circle

detection.• Will use the best performing classifier.

Page 8: Coin Counter

Questions?

?