test.py 15.8 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
def F(parts):
  """Returns the test file path"""

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

34 35
def test_extractor():
  raise(SyntaxError)
36 37 38

def test_finger_crop():

André Anjos's avatar
André Anjos committed
39 40
  input_filename = F(('preprocessors', '0019_3_1_120509-160517.png'))
  output_img_filename  = F(('preprocessors',
41
    '0019_3_1_120509-160517_img_lee_huang.mat'))
André Anjos's avatar
André Anjos committed
42
  output_fvr_filename  = F(('preprocessors',
43 44 45 46
    '0019_3_1_120509-160517_fvr_lee_huang.mat'))

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

47
  from bob.bio.vein.preprocessor.FingerCrop import FingerCrop
48
  preprocess = FingerCrop(fingercontour='leemaskMatlab', padding_width=0, postprocessing = 'HE')
49
  preproc, mask = preprocess(img)
50
  #preprocessor_utils.show_mask_over_image(preproc, mask)
51

52 53 54 55 56
  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
57

58 59
 # Very loose comparison!
  #preprocessor_utils.show_image(numpy.abs(preproc.astype('int16') - preproc_ref.astype('int16')).astype('uint8'))
60
  assert numpy.mean(numpy.abs(preproc - preproc_ref)) < 1.3e2
61 62


63
def test_max_curvature():
64 65 66

  #Maximum Curvature method against Matlab reference

André Anjos's avatar
André Anjos committed
67 68 69
  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'))
70 71 72 73 74 75

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

  # Apply Python implementation
76
  from bob.bio.vein.extractor.MaximumCurvature import MaximumCurvature
77
  MC = MaximumCurvature(5)
78 79 80 81 82 83 84 85
  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
86 87


88
def test_repeated_line_tracking():
89 90 91

  #Repeated Line Tracking method against Matlab reference

André Anjos's avatar
André Anjos committed
92 93 94
  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'))
95 96 97 98 99 100

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

  # Apply Python implementation
101
  from bob.bio.vein.extractor.RepeatedLineTracking import RepeatedLineTracking
102 103 104 105 106 107 108 109 110 111 112
  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


113
def test_wide_line_detector():
114 115 116

  #Wide Line Detector method against Matlab reference

André Anjos's avatar
André Anjos committed
117 118 119
  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'))
120 121 122 123 124 125

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

  # Apply Python implementation
126
  from bob.bio.vein.extractor.WideLineDetector import WideLineDetector
127 128 129 130 131 132 133 134 135 136 137 138
  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
139 140 141 142 143
  #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'))
144 145 146 147 148

  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)

149
  from bob.bio.vein.algorithm.MiuraMatch import MiuraMatch
150 151 152 153 154 155 156
  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)
157 158 159 160 161 162 163


def test_assert_points():

  # Tests that point assertion works as expected
  area = (10, 5)
  inside = [(0,0), (3,2), (9, 4)]
164
  preprocessor_utils.assert_points(area, inside) #should not raise
165 166 167 168

  def _check_outside(point):
    # should raise, otherwise it is an error
    try:
169
      preprocessor_utils.assert_points(area, [point])
170 171 172 173 174 175 176 177 178 179 180 181 182 183
    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)]
184
  fixed = preprocessor_utils.fix_points(area, inside)
185 186
  assert numpy.array_equal(inside, fixed), '%r != %r' % (inside, fixed)

187
  fixed = preprocessor_utils.fix_points(area, [(-1, 0)])
188 189
  assert numpy.array_equal(fixed, [(0, 0)])

190
  fixed = preprocessor_utils.fix_points(area, [(10, 0)])
191 192
  assert numpy.array_equal(fixed, [(9, 0)])

193
  fixed = preprocessor_utils.fix_points(area, [(0, 5)])
194 195
  assert numpy.array_equal(fixed, [(0, 4)])

196
  fixed = preprocessor_utils.fix_points(area, [(10, 5)])
197 198
  assert numpy.array_equal(fixed, [(9, 4)])

199
  fixed = preprocessor_utils.fix_points(area, [(15, 12)])
200 201 202 203 204 205 206 207
  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
208
  mask = preprocessor_utils.poly_to_mask(area, polygon)
209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226
  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
227
  mask = preprocessor_utils.poly_to_mask(area, polygon)
228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253
  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):
254
    conv = preprocessor_utils.mask_to_image(sample, 'uint%d' % n)
255 256 257 258 259 260 261 262 263 264
    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):
265
    conv = preprocessor_utils.mask_to_image(sample, 'float%d' % n)
266 267 268 269 270 271 272 273 274 275
    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:
276
    conv = preprocessor_utils.mask_to_image(sample, 'int16')
277 278 279 280
  except TypeError as e:
    assert 'int16' in str(e)
  else:
    raise AssertionError('Conversion to int16 did not trigger a TypeError')
281 282 283 284 285 286 287 288 289 290 291 292 293 294 295


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],
    ])

296 297 298 299 300 301 302
  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)
303 304 305 306 307 308 309 310 311 312 313 314 315 316 317


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],
    ])

318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334
  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)


335
def test_correlation():
336

337
  # A test for convolution performance. Correlations are used on the Miura
338 339
  # Match algorithm, therefore we want to make sure we can perform them as fast
  # as possible.
340
  import numpy
341
  import scipy.signal
342
  import bob.sp
343

344
  # Rough example from Vera fingervein database
345 346
  Y = 250
  X = 600
347 348
  CH = 80
  CW = 90
349 350 351 352 353 354

  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

355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391

  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])))

392 393

  def scipy_function(a, b):
394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409
    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])))

410 411

  def scipy2_function(a, b):
412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441
    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])))
442 443

  a, b = gen_ab()
444 445

  assert numpy.allclose(bob_function(a, b), scipy_function(a, b))
446
  assert numpy.allclose(scipy_function(a, b), scipy2_function(a, b))
447
  assert numpy.allclose(scipy2_function(a, b), scipy3_function(a, b))
448

449 450
  # if you want to test timings, uncomment the following section
  '''
451 452 453 454 455 456
  import time

  start = time.clock()
  N = 10
  for i in range(N):
    a, b = gen_ab()
457
    bob_function(a, b)
458
  total = time.clock() - start
459
  print('bob implementation, %d iterations - %.2e per iteration' % (N, total/N))
460 461 462 463 464 465

  start = time.clock()
  for i in range(N):
    a, b = gen_ab()
    scipy_function(a, b)
  total = time.clock() - start
466
  print('scipy+convolve, %d iterations - %.2e per iteration' % (N, total/N))
467 468 469 470 471 472

  start = time.clock()
  for i in range(N):
    a, b = gen_ab()
    scipy2_function(a, b)
  total = time.clock() - start
473 474 475 476 477 478 479 480 481
  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))
  '''