test.py 15.7 KB
Newer Older
Pedro TOME's avatar
Pedro TOME committed
1 2 3 4
#!/usr/bin/env python
# vim: set fileencoding=utf-8 :


5 6 7 8 9 10 11 12
"""Unit tests against references extracted from

Matlab code from Bram Ton available on the matlab central website:

https://www.mathworks.com/matlabcentral/fileexchange/35754-wide-line-detector

This code implements the detector described in [HDLTL10] (see the references in
the generated sphinx documentation)
Pedro TOME's avatar
Pedro TOME committed
13 14 15
"""

import os
16
import numpy
17
import numpy as np
18 19
import nose.tools

Pedro TOME's avatar
Pedro TOME committed
20 21
import pkg_resources

22 23
import bob.io.base
import bob.io.matlab
André Anjos's avatar
André Anjos committed
24
import bob.io.image
Pedro TOME's avatar
Pedro TOME committed
25

26
from ..preprocessor import utils as preprocessor_utils
27

Pedro TOME's avatar
Pedro TOME committed
28

29 30 31 32 33 34 35 36
def F(parts):
  """Returns the test file path"""

  return pkg_resources.resource_filename(__name__, os.path.join(*parts))


def test_finger_crop():

André Anjos's avatar
André Anjos committed
37 38
  input_filename = F(('preprocessors', '0019_3_1_120509-160517.png'))
  output_img_filename  = F(('preprocessors',
39
    '0019_3_1_120509-160517_img_lee_huang.mat'))
André Anjos's avatar
André Anjos committed
40
  output_fvr_filename  = F(('preprocessors',
41 42 43 44
    '0019_3_1_120509-160517_fvr_lee_huang.mat'))

  img = bob.io.base.load(input_filename)

45
  from bob.bio.vein.preprocessor.FingerCrop import FingerCrop
46
  preprocess = FingerCrop(fingercontour='leemaskMatlab', padding_width=0)
47

48
  preproc, mask = preprocess(img)
49
  #preprocessor_utils.show_mask_over_image(preproc, mask)
50

51 52 53 54 55
  mask_ref = bob.io.base.load(output_fvr_filename).astype('bool')
  preproc_ref = bob.core.convert(bob.io.base.load(output_img_filename),
      numpy.uint8, (0,255), (0.0,1.0))

  assert numpy.mean(numpy.abs(mask - mask_ref)) < 1e-2
56

57 58
 # Very loose comparison!
  #preprocessor_utils.show_image(numpy.abs(preproc.astype('int16') - preproc_ref.astype('int16')).astype('uint8'))
59
  assert numpy.mean(numpy.abs(preproc - preproc_ref)) < 1.3e2
60 61


62
def test_max_curvature():
63 64 65

  #Maximum Curvature method against Matlab reference

André Anjos's avatar
André Anjos committed
66 67 68
  input_img_filename  = F(('extractors', 'miuramax_input_img.mat'))
  input_fvr_filename  = F(('extractors', 'miuramax_input_fvr.mat'))
  output_filename     = F(('extractors', 'miuramax_output.mat'))
69 70 71 72 73 74

  # Load inputs
  input_img = bob.io.base.load(input_img_filename)
  input_fvr = bob.io.base.load(input_fvr_filename)

  # Apply Python implementation
75
  from bob.bio.vein.extractor.MaximumCurvature import MaximumCurvature
76
  MC = MaximumCurvature(5)
77 78 79 80 81 82 83 84
  output_img = MC((input_img, input_fvr))

  # Load Matlab reference
  output_img_ref = bob.io.base.load(output_filename)

  # Compare output of python's implementation to matlab reference
  # (loose comparison!)
  assert numpy.mean(numpy.abs(output_img - output_img_ref)) < 8e-3
Pedro TOME's avatar
Pedro TOME committed
85 86


87
def test_repeated_line_tracking():
88 89 90

  #Repeated Line Tracking method against Matlab reference

André Anjos's avatar
André Anjos committed
91 92 93
  input_img_filename  = F(('extractors', 'miurarlt_input_img.mat'))
  input_fvr_filename  = F(('extractors', 'miurarlt_input_fvr.mat'))
  output_filename     = F(('extractors', 'miurarlt_output.mat'))
94 95 96 97 98 99

  # Load inputs
  input_img = bob.io.base.load(input_img_filename)
  input_fvr = bob.io.base.load(input_fvr_filename)

  # Apply Python implementation
100
  from bob.bio.vein.extractor.RepeatedLineTracking import RepeatedLineTracking
101 102 103 104 105 106 107 108 109 110 111
  RLT = RepeatedLineTracking(3000, 1, 21, False)
  output_img = RLT((input_img, input_fvr))

  # Load Matlab reference
  output_img_ref = bob.io.base.load(output_filename)

  # Compare output of python's implementation to matlab reference
  # (loose comparison!)
  assert numpy.mean(numpy.abs(output_img - output_img_ref)) < 0.5


112
def test_wide_line_detector():
113 114 115

  #Wide Line Detector method against Matlab reference

André Anjos's avatar
André Anjos committed
116 117 118
  input_img_filename  = F(('extractors', 'huangwl_input_img.mat'))
  input_fvr_filename  = F(('extractors', 'huangwl_input_fvr.mat'))
  output_filename     = F(('extractors', 'huangwl_output.mat'))
119 120 121 122 123 124

  # Load inputs
  input_img = bob.io.base.load(input_img_filename)
  input_fvr = bob.io.base.load(input_fvr_filename)

  # Apply Python implementation
125
  from bob.bio.vein.extractor.WideLineDetector import WideLineDetector
126 127 128 129 130 131 132 133 134 135 136 137
  WL = WideLineDetector(5, 1, 41, False)
  output_img = WL((input_img, input_fvr))

  # Load Matlab reference
  output_img_ref = bob.io.base.load(output_filename)

  # Compare output of python's implementation to matlab reference
  assert numpy.allclose(output_img, output_img_ref)


def test_miura_match():

André Anjos's avatar
André Anjos committed
138 139 140 141 142
  #Match Ratio method against Matlab reference

  template_filename = F(('algorithms', '0001_2_1_120509-135338.mat'))
  probe_gen_filename = F(('algorithms', '0001_2_2_120509-135558.mat'))
  probe_imp_filename = F(('algorithms', '0003_2_1_120509-141255.mat'))
143 144 145 146 147

  template_vein = bob.io.base.load(template_filename)
  probe_gen_vein = bob.io.base.load(probe_gen_filename)
  probe_imp_vein = bob.io.base.load(probe_imp_filename)

148
  from bob.bio.vein.algorithm.MiuraMatch import MiuraMatch
149 150 151 152 153 154 155
  MM = MiuraMatch(ch=18, cw=28)
  score_gen = MM.score(template_vein, probe_gen_vein)

  assert numpy.isclose(score_gen, 0.382689335394127)

  score_imp = MM.score(template_vein, probe_imp_vein)
  assert numpy.isclose(score_imp, 0.172906739278421)
156 157 158 159 160 161 162


def test_assert_points():

  # Tests that point assertion works as expected
  area = (10, 5)
  inside = [(0,0), (3,2), (9, 4)]
163
  preprocessor_utils.assert_points(area, inside) #should not raise
164 165 166 167

  def _check_outside(point):
    # should raise, otherwise it is an error
    try:
168
      preprocessor_utils.assert_points(area, [point])
169 170 171 172 173 174 175 176 177 178 179 180 181 182
    except AssertionError as e:
      assert str(point) in str(e)
    else:
      raise AssertionError("Did not assert %s is outside of %s" % (point, area))

  outside = [(-1, 0), (10, 0), (0, 5), (10, 5), (15,12)]
  for k in outside: _check_outside(k)


def test_fix_points():

  # Tests that point clipping works as expected
  area = (10, 5)
  inside = [(0,0), (3,2), (9, 4)]
183
  fixed = preprocessor_utils.fix_points(area, inside)
184 185
  assert numpy.array_equal(inside, fixed), '%r != %r' % (inside, fixed)

186
  fixed = preprocessor_utils.fix_points(area, [(-1, 0)])
187 188
  assert numpy.array_equal(fixed, [(0, 0)])

189
  fixed = preprocessor_utils.fix_points(area, [(10, 0)])
190 191
  assert numpy.array_equal(fixed, [(9, 0)])

192
  fixed = preprocessor_utils.fix_points(area, [(0, 5)])
193 194
  assert numpy.array_equal(fixed, [(0, 4)])

195
  fixed = preprocessor_utils.fix_points(area, [(10, 5)])
196 197
  assert numpy.array_equal(fixed, [(9, 4)])

198
  fixed = preprocessor_utils.fix_points(area, [(15, 12)])
199 200 201 202 203 204 205 206
  assert numpy.array_equal(fixed, [(9, 4)])


def test_poly_to_mask():

  # Tests we can generate a mask out of a polygon correctly
  area = (10, 9) #10 rows, 9 columns
  polygon = [(2, 2), (2, 7), (7, 7), (7, 2)] #square shape, (y, x) format
207
  mask = preprocessor_utils.poly_to_mask(area, polygon)
208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225
  nose.tools.eq_(mask.dtype, numpy.bool)

  # This should be the output:
  expected = numpy.array([
      [False, False, False, False, False, False, False, False, False],
      [False, False, False, False, False, False, False, False, False],
      [False, False, True,  True,  True,  True,  True,  True,  False],
      [False, False, True,  True,  True,  True,  True,  True,  False],
      [False, False, True,  True,  True,  True,  True,  True,  False],
      [False, False, True,  True,  True,  True,  True,  True,  False],
      [False, False, True,  True,  True,  True,  True,  True,  False],
      [False, False, True,  True,  True,  True,  True,  True,  False],
      [False, False, False, False, False, False, False, False, False],
      [False, False, False, False, False, False, False, False, False],
      ])
  assert numpy.array_equal(mask, expected)

  polygon = [(3, 2), (5, 7), (8, 7), (7, 3)] #trapezoid, (y, x) format
226
  mask = preprocessor_utils.poly_to_mask(area, polygon)
227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252
  nose.tools.eq_(mask.dtype, numpy.bool)

  # This should be the output:
  expected = numpy.array([
      [False, False, False, False, False, False, False, False, False],
      [False, False, False, False, False, False, False, False, False],
      [False, False, False, False, False, False, False, False, False],
      [False, False, True,  False, False, False, False, False, False],
      [False, False, True,  True,  True,  False, False, False, False],
      [False, False, False, True,  True,  True,  True,  True,  False],
      [False, False, False, True,  True,  True,  True,  True,  False],
      [False, False, False, True,  True,  True,  True,  True,  False],
      [False, False, False, False, False, False, False, True,  False],
      [False, False, False, False, False, False, False, False, False],
      ])
  assert numpy.array_equal(mask, expected)


def test_mask_to_image():

  # Tests we can correctly convert a boolean array into an image
  # that makes sense according to the data types
  sample = numpy.array([False, True])
  nose.tools.eq_(sample.dtype, numpy.bool)

  def _check_uint(n):
253
    conv = preprocessor_utils.mask_to_image(sample, 'uint%d' % n)
254 255 256 257 258 259 260 261 262 263
    nose.tools.eq_(conv.dtype, getattr(numpy, 'uint%d' % n))
    target = [0, (2**n)-1]
    assert numpy.array_equal(conv, target), '%r != %r' % (conv, target)

  _check_uint(8)
  _check_uint(16)
  _check_uint(32)
  _check_uint(64)

  def _check_float(n):
264
    conv = preprocessor_utils.mask_to_image(sample, 'float%d' % n)
265 266 267 268 269 270 271 272 273 274
    nose.tools.eq_(conv.dtype, getattr(numpy, 'float%d' % n))
    assert numpy.array_equal(conv, [0, 1.0]), '%r != %r' % (conv, target)

  _check_float(32)
  _check_float(64)
  _check_float(128)


  # This should be unsupported
  try:
275
    conv = preprocessor_utils.mask_to_image(sample, 'int16')
276 277 278 279
  except TypeError as e:
    assert 'int16' in str(e)
  else:
    raise AssertionError('Conversion to int16 did not trigger a TypeError')
280 281 282 283 284 285 286 287 288 289 290 291 292 293 294


def test_jaccard_index():

  # Tests to verify the Jaccard index calculation is accurate
  a = numpy.array([
    [False, False],
    [True, True],
    ])

  b = numpy.array([
    [True, True],
    [True, False],
    ])

295 296 297 298 299 300 301
  nose.tools.eq_(preprocessor_utils.jaccard_index(a, b), 1.0/4.0)
  nose.tools.eq_(preprocessor_utils.jaccard_index(a, a), 1.0)
  nose.tools.eq_(preprocessor_utils.jaccard_index(b, b), 1.0)
  nose.tools.eq_(preprocessor_utils.jaccard_index(a, numpy.ones(a.shape, dtype=bool)), 2.0/4.0)
  nose.tools.eq_(preprocessor_utils.jaccard_index(a, numpy.zeros(a.shape, dtype=bool)), 0.0)
  nose.tools.eq_(preprocessor_utils.jaccard_index(b, numpy.ones(b.shape, dtype=bool)), 3.0/4.0)
  nose.tools.eq_(preprocessor_utils.jaccard_index(b, numpy.zeros(b.shape, dtype=bool)), 0.0)
302 303 304 305 306 307 308 309 310 311 312 313 314 315 316


def test_intersection_ratio():

  # Tests to verify the intersection ratio calculation is accurate
  a = numpy.array([
    [False, False],
    [True, True],
    ])

  b = numpy.array([
    [True, False],
    [True, False],
    ])

317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333
  nose.tools.eq_(preprocessor_utils.intersect_ratio(a, b), 1.0/2.0)
  nose.tools.eq_(preprocessor_utils.intersect_ratio(a, a), 1.0)
  nose.tools.eq_(preprocessor_utils.intersect_ratio(b, b), 1.0)
  nose.tools.eq_(preprocessor_utils.intersect_ratio(a, numpy.ones(a.shape, dtype=bool)), 1.0)
  nose.tools.eq_(preprocessor_utils.intersect_ratio(a, numpy.zeros(a.shape, dtype=bool)), 0)
  nose.tools.eq_(preprocessor_utils.intersect_ratio(b, numpy.ones(b.shape, dtype=bool)), 1.0)
  nose.tools.eq_(preprocessor_utils.intersect_ratio(b, numpy.zeros(b.shape, dtype=bool)), 0)

  nose.tools.eq_(preprocessor_utils.intersect_ratio_of_complement(a, b), 1.0/2.0)
  nose.tools.eq_(preprocessor_utils.intersect_ratio_of_complement(a, a), 0.0)
  nose.tools.eq_(preprocessor_utils.intersect_ratio_of_complement(b, b), 0.0)
  nose.tools.eq_(preprocessor_utils.intersect_ratio_of_complement(a, numpy.ones(a.shape, dtype=bool)), 1.0)
  nose.tools.eq_(preprocessor_utils.intersect_ratio_of_complement(a, numpy.zeros(a.shape, dtype=bool)), 0)
  nose.tools.eq_(preprocessor_utils.intersect_ratio_of_complement(b, numpy.ones(b.shape, dtype=bool)), 1.0)
  nose.tools.eq_(preprocessor_utils.intersect_ratio_of_complement(b, numpy.zeros(b.shape, dtype=bool)), 0)


334
def test_correlation():
335

336
  # A test for convolution performance. Correlations are used on the Miura
337 338
  # Match algorithm, therefore we want to make sure we can perform them as fast
  # as possible.
339
  import numpy
340
  import scipy.signal
341
  import bob.sp
342

343
  # Rough example from Vera fingervein database
344 345
  Y = 250
  X = 600
346 347
  CH = 80
  CW = 90
348 349 350 351 352 353

  def gen_ab():
    a = numpy.random.randint(256, size=(Y, X)).astype(float)
    b = numpy.random.randint(256, size=(Y-CH, X-CW)).astype(float)
    return a, b

354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390

  def bob_function(a, b):

    # rotate input image by 180 degrees
    b = numpy.rot90(b, k=2)

    # Determine padding size in x and y dimension
    size_a  = numpy.array(a.shape)
    size_b  = numpy.array(b.shape)
    outsize = size_a + size_b - 1

    # Determine 2D cross correlation in Fourier domain
    a2 = numpy.zeros(outsize)
    a2[0:size_a[0],0:size_a[1]] = a
    Fa = bob.sp.fft(a2.astype(numpy.complex128))

    b2 = numpy.zeros(outsize)
    b2[0:size_b[0],0:size_b[1]] = b
    Fb = bob.sp.fft(b2.astype(numpy.complex128))

    conv_ab = numpy.real(bob.sp.ifft(Fa*Fb))

    h, w = size_a - size_b + 1

    Nm = conv_ab[size_b[0]-1:size_b[0]-1+h, size_b[1]-1:size_b[1]-1+w]

    t0, s0 = numpy.unravel_index(Nm.argmax(), Nm.shape)

    # this is our output
    Nmm = Nm[t0,s0]

    # normalizes the output by the number of pixels lit on the input
    # matrices, taking into consideration the surface that produced the
    # result (i.e., the eroded model and part of the probe)
    h, w = b.shape
    return Nmm/(sum(sum(b)) + sum(sum(a[t0:t0+h-2*CH, s0:s0+w-2*CW])))

391 392

  def scipy_function(a, b):
393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408
    b = numpy.rot90(b, k=2)

    Nm = scipy.signal.convolve2d(a, b, 'valid')

    # figures out where the maximum is on the resulting matrix
    t0, s0 = numpy.unravel_index(Nm.argmax(), Nm.shape)

    # this is our output
    Nmm = Nm[t0,s0]

    # normalizes the output by the number of pixels lit on the input
    # matrices, taking into consideration the surface that produced the
    # result (i.e., the eroded model and part of the probe)
    h, w = b.shape
    return Nmm/(sum(sum(b)) + sum(sum(a[t0:t0+h-2*CH, s0:s0+w-2*CW])))

409 410

  def scipy2_function(a, b):
411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440
    b = numpy.rot90(b, k=2)
    Nm = scipy.signal.fftconvolve(a, b, 'valid')

    # figures out where the maximum is on the resulting matrix
    t0, s0 = numpy.unravel_index(Nm.argmax(), Nm.shape)

    # this is our output
    Nmm = Nm[t0,s0]

    # normalizes the output by the number of pixels lit on the input
    # matrices, taking into consideration the surface that produced the
    # result (i.e., the eroded model and part of the probe)
    h, w = b.shape
    return Nmm/(sum(sum(b)) + sum(sum(a[t0:t0+h-2*CH, s0:s0+w-2*CW])))


  def scipy3_function(a, b):
    Nm = scipy.signal.correlate2d(a, b, 'valid')

    # figures out where the maximum is on the resulting matrix
    t0, s0 = numpy.unravel_index(Nm.argmax(), Nm.shape)

    # this is our output
    Nmm = Nm[t0,s0]

    # normalizes the output by the number of pixels lit on the input
    # matrices, taking into consideration the surface that produced the
    # result (i.e., the eroded model and part of the probe)
    h, w = b.shape
    return Nmm/(sum(sum(b)) + sum(sum(a[t0:t0+h-2*CH, s0:s0+w-2*CW])))
441 442

  a, b = gen_ab()
443 444

  assert numpy.allclose(bob_function(a, b), scipy_function(a, b))
445
  assert numpy.allclose(scipy_function(a, b), scipy2_function(a, b))
446
  assert numpy.allclose(scipy2_function(a, b), scipy3_function(a, b))
447

448 449
  # if you want to test timings, uncomment the following section
  '''
450 451 452 453 454 455
  import time

  start = time.clock()
  N = 10
  for i in range(N):
    a, b = gen_ab()
456
    bob_function(a, b)
457
  total = time.clock() - start
458
  print('bob implementation, %d iterations - %.2e per iteration' % (N, total/N))
459 460 461 462 463 464

  start = time.clock()
  for i in range(N):
    a, b = gen_ab()
    scipy_function(a, b)
  total = time.clock() - start
465
  print('scipy+convolve, %d iterations - %.2e per iteration' % (N, total/N))
466 467 468 469 470 471

  start = time.clock()
  for i in range(N):
    a, b = gen_ab()
    scipy2_function(a, b)
  total = time.clock() - start
472 473 474 475 476 477 478 479 480
  print('scipy+fftconvolve, %d iterations - %.2e per iteration' % (N, total/N))

  start = time.clock()
  for i in range(N):
    a, b = gen_ab()
    scipy3_function(a, b)
  total = time.clock() - start
  print('scipy+correlate2d, %d iterations - %.2e per iteration' % (N, total/N))
  '''