MiuraMatch.py 3.1 KB
Newer Older
Pedro TOME's avatar
Pedro TOME committed
1 2 3 4 5 6 7 8 9 10
#!/usr/bin/env python
# vim: set fileencoding=utf-8 :

import bob.sp
import bob.ip.base

import numpy
import math
import scipy.signal

11
from bob.bio.base.algorithm import Algorithm
Pedro TOME's avatar
Pedro TOME committed
12

13 14 15 16 17 18 19 20

class MiuraMatch (Algorithm):
  """Finger vein matching: match ratio

  Based on N. Miura, A. Nagasaka, and T. Miyatake. Feature extraction of finger
  vein patterns based on repeated line tracking and its application to personal
  identification. Machine Vision and Applications, Vol. 15, Num. 4, pp.
  194--203, 2004
21 22


André Anjos's avatar
André Anjos committed
23
  Parameters:
24

André Anjos's avatar
André Anjos committed
25 26 27 28 29
  ch (:py:class:`int`, optional): Maximum search displacement in y-direction.
    Different default values based on the different features.

  cw (:py:class:`int`, optional): Maximum search displacement in x-direction.
    Different default values based on the different features.
30

Pedro TOME's avatar
Pedro TOME committed
31 32
  """

33
  def __init__(self,
Pedro TOME's avatar
Pedro TOME committed
34 35
      ch = 8,       # Maximum search displacement in y-direction
      cw = 5,       # Maximum search displacement in x-direction
36
      ):
Pedro TOME's avatar
Pedro TOME committed
37 38

    # call base class constructor
39
    Algorithm.__init__(
Pedro TOME's avatar
Pedro TOME committed
40 41 42 43 44 45 46 47 48 49 50 51
        self,

        ch = ch,
        cw = cw,

        multiple_model_scoring = None,
        multiple_probe_scoring = None
    )

    self.ch = ch
    self.cw = cw

52

Pedro TOME's avatar
Pedro TOME committed
53 54
  def enroll(self, enroll_features):
    """Enrolls the model by computing an average graph for each model"""
55

Pedro TOME's avatar
Pedro TOME committed
56 57 58 59 60 61 62 63 64
    # return the generated model
    return numpy.array(enroll_features)


  def convfft(self, t, a):
    # Determine padding size in x and y dimension
    size_t  = numpy.array(t.shape)
    size_a  = numpy.array(a.shape)
    outsize = size_t + size_a - 1
65

Pedro TOME's avatar
Pedro TOME committed
66 67 68 69 70 71 72
    # Determine 2D cross correlation in Fourier domain
    taux = numpy.zeros(outsize)
    taux[0:size_t[0],0:size_t[1]] = t
    Ft = bob.sp.fft(taux.astype(numpy.complex128))
    aaux = numpy.zeros(outsize)
    aaux[0:size_a[0],0:size_a[1]] = a
    Fa = bob.sp.fft(aaux.astype(numpy.complex128))
73

Pedro TOME's avatar
Pedro TOME committed
74
    convta = numpy.real(bob.sp.ifft(Ft*Fa))
75

Pedro TOME's avatar
Pedro TOME committed
76 77
    [w, h] = size_t-size_a+1
    output = convta[size_a[0]-1:size_a[0]-1+w, size_a[1]-1:size_a[1]-1+h]
78

Pedro TOME's avatar
Pedro TOME committed
79 80 81 82
    return output


  def score(self, model, probe):
Olegs NIKISINS's avatar
Olegs NIKISINS committed
83 84 85 86 87 88 89
    """
    Computes the score of the probe and the model.

    **Parameters:**

    score : :py:class:`float`
        Value between 0 and 0.5, larger value is better match
Pedro TOME's avatar
Pedro TOME committed
90 91 92
    """
    #print model.shape
    #print probe.shape
93

Pedro TOME's avatar
Pedro TOME committed
94
    I=probe.astype(numpy.float64)
95 96

    if len(model.shape) == 2:
Pedro TOME's avatar
Pedro TOME committed
97
      model = numpy.array([model])
98

Pedro TOME's avatar
Pedro TOME committed
99 100 101 102 103 104 105 106 107
    n_models = model.shape[0]

    scores = []
    for i in range(n_models):
      R=model[i,:].astype(numpy.float64)
      h, w = R.shape
      crop_R = R[self.ch:h-self.ch, self.cw:w-self.cw]
      rotate_R = numpy.zeros((crop_R.shape[0], crop_R.shape[1]))
      bob.ip.base.rotate(crop_R, rotate_R, 180)
108
      #FFT for scoring!
Pedro TOME's avatar
Pedro TOME committed
109
      #Nm=bob.sp.ifft(bob.sp.fft(I)*bob.sp.fft(rotate_R))
110 111
      Nm = self.convfft(I, rotate_R)
      #Nm2 = scipy.signal.convolve2d(I, rotate_R, 'valid')
112

Pedro TOME's avatar
Pedro TOME committed
113 114 115
      t0, s0 = numpy.unravel_index(Nm.argmax(), Nm.shape)
      Nmm = Nm[t0,s0]
      #Nmm = Nm.max()
116
      #mi = numpy.argwhere(Nmm == Nm)
Pedro TOME's avatar
Pedro TOME committed
117 118
      #t0, s0 = mi.flatten()[:2]
      scores.append(Nmm/(sum(sum(crop_R)) + sum(sum(I[t0:t0+h-2*self.ch, s0:s0+w-2*self.cw]))))
119

Pedro TOME's avatar
Pedro TOME committed
120
    return numpy.mean(scores)