Card recognition Justin Pinkul Blackjack Needed information - - PowerPoint PPT Presentation

▶
card recognition
SMART_READER_LITE
LIVE PREVIEW

Card recognition Justin Pinkul Blackjack Needed information - - PowerPoint PPT Presentation

Aug 30, 2023 32 likes •342 views

Card recognition Justin Pinkul Blackjack Needed information Position Value Orientation Scale Assumptions Same deck of cards Fixed viewing angle Comparable lighting The algorithm Grayscale template-matching

slide-1
SLIDE 1

Card recognition

Justin Pinkul

slide-2
SLIDE 2

Blackjack

Needed information

  • Position
  • Value
  • Orientation
  • Scale
slide-3
SLIDE 3

Assumptions

  • Same deck of cards
  • Fixed viewing angle
  • Comparable lighting
slide-4
SLIDE 4

The algorithm

Grayscale template-matching invariant to rotation scale, translation, brightness and contrast Three step filtering process

slide-5
SLIDE 5

The algorithm

Step 1: circular sampling

slide-6
SLIDE 6

Circular sampling

slide-7
SLIDE 7

Circular sampling

slide-8
SLIDE 8

Circular sampling

slide-9
SLIDE 9

The algorithm

Step 2: radial sampling

slide-10
SLIDE 10

Radial sampling

slide-11
SLIDE 11

Radial sampling

slide-12
SLIDE 12

Radial sampling

slide-13
SLIDE 13

Radial sampling

slide-14
SLIDE 14

Radial sampling

slide-15
SLIDE 15

The algorithm

Step 3: normal template matching

  • Probable scale known from circle sampling
  • Probable rotation known from radius

sampling

slide-16
SLIDE 16

Pseudo Code - circularTest

main

I = image G = template scales = 0.5, 0.55, 0.6, 0.65, 0.7, 0.75, 0.8, 0.85 radius = 0, 8, 16, 24, 32, 45 pass1, probScales = circularTest(I, G, scales, radius) pass2, probAngles = radialTest(I, G, scales, radius, pass1, probScales) templateMatch(I, G, pass2, probScales, probAngles)

slide-17
SLIDE 17

Pseudo Code

circularTest(I, G, scales, radius) for scale = all scales resizedQ = resize Q to the scale for len = all radius (xcen, ycen) = center of resizedQ qScore[scale, length] = getCircleAverage(resizedQ xcen, ycen ,len) end end for all (x,y) in I for len = all radius iScore[x, y, length] = getCircleAverage(I, x, y, len) end end

slide-18
SLIDE 18

Pseudo Code - circularTest cont.

for all (x,y) in I for scale = all scales iRadiusAvgs = iScore(x,y, ...) qRadiusAvgs = qScores(scale, ...) cor = correlate(iRadiusAvgs, qRadiusAvgs) add cor to correlations end pass1(x,y) = max(correlations) > threshold1 probableScale(x,y) = scales(index of max(correlations)) end end

slide-19
SLIDE 19

Pseudo Code - radiusTest

radiusTest(I, G, scales, radius, pass1, probScales) r = largest radius for theta = all test angels (cenx, ceny) = the center of Q qScores[theta] = getRadiusAverage(Q, theta, cenx, ceny, r) end for all (x,y) in I if pass1(x,y) iR = r * probScales(x,y) iScores[x,y,theta] = getRadiusAverage(Q, theta, x, y, iR) end end

slide-20
SLIDE 20

Pseudo Code - radiusTest cont.

for all (x,y) in I if pass1(x,y) for theta = all angels iAngAvgs = iScores(x,y,...) for all orientations shifted = shift qScores to the new orientation cor = correlate(iAngAvgs, shifted) add cor to correlations end pass2(x,y) = max(correlations) > threshold2 probRadius = radius(index of max(correlations)) end end end end

slide-21
SLIDE 21

Results

slide-22
SLIDE 22
slide-23
SLIDE 23
slide-24
SLIDE 24
slide-25
SLIDE 25
slide-26
SLIDE 26
slide-27
SLIDE 27
slide-28
SLIDE 28

Limitations

  • Template size
  • Speed
slide-29
SLIDE 29

Future work

  • Partially visible cards
  • Automated process for choosing scale and

radius samples

  • Variable viewing angles
  • Real time analysis with a video camera
slide-30
SLIDE 30

Questions?

slide-31
SLIDE 31

References

De Araújo, Sidnei. "Grayscale Template-Matching Invariant to Rotation, Scale, Translation, Brightness and Contrast." Advances in Image and Video Technology. By Hae Kim. Heidelberg: Springer Berlin, 2007. 100-13. Print.