def main():
glassLabel = 255
thicknessForEvaluation = 20
objects=('bank', 'bottle', 'bucket', 'glass', 'wineglass')
basePath = '/media/2Tb/transparentBases/fixedOnTable/base/'
base = utils.TODBase(basePath, objects)
patchSizes = (5, 10, 20, 40, 100, 200, 400)
fks = (10, 20, 50, 100, 200, 400, 800, 1600)
allSamples = base.getSamples()
evaluator = utils.Evaluator(len(patchSizes))
# evaluator = utils.Evaluator(len(fks))
for sample in allSamples:
print sample.imageFilename
groundTruthMask = sample.getGlassMask()
if (groundTruthMask == None):
continue
[groundTruthDT, groundTruthEdgelsCount] = utils.mask2dtAndEdgelsCount(groundTruthMask)
glassMask = groundTruthMask.copy()
glassContours, hierarchy = cv2.findContours(glassMask, cv2.RETR_LIST, cv2.CHAIN_APPROX_NONE)
glassContoursImage = np.zeros(glassMask.shape, np.uint8)
cv2.drawContours(glassContoursImage, glassContours, -1, (255), thicknessForEvaluation)
image = sample.getImage()
for idx, size in enumerate(patchSizes):
segmentation = computeVeksler(image, size)
# for idx, k in enumerate(fks):
# segmentation = computeFelzenszwalb(image, k)
minSegmentation = cv2.erode(segmentation.astype(np.float32), None)
maxSegmentation = cv2.dilate(segmentation.astype(np.float32), None)
boundaries = 255 * (maxSegmentation - minSegmentation != 0).astype(np.uint8)
boundaries[glassContoursImage == 0] = 0
boundariesEdgelsCount = len(np.nonzero(boundaries == 255)[0])
boundariesDT = cv2.distanceTransform(~boundaries, cv2.cv.CV_DIST_L1, cv2.cv.CV_DIST_MASK_PRECISE)
[recallEdgels, precisionEdgels] = utils.computeRecallPrecisionEdgels(groundTruthDT, boundariesDT)
evaluator.addObservation(idx, recallEdgels, groundTruthEdgelsCount, precisionEdgels, boundariesEdgelsCount)
evaluator.computeStatistics()
evaluator.printStatistics()
evaluator.plot('veksler')
# evaluator.plot('felz')
utils.plt.show()
groundTruthFilename = imageFilename.replace(
'/image_', '/' + groundTruthPrefix + '_')
testFolder = imageFilename.replace('/image_' + fullImageIndex + '.png',
'/')
call([
segmentImage, testFolder, fullImageIndex, classifierFilename,
segmentationListFilename, propagationScalingsList, algorithmName
])
groundTruth = cv2.imread(groundTruthFilename,
cv2.CV_LOAD_IMAGE_GRAYSCALE)
glassLabel = 255
groundTruthGlassMask = (groundTruth == glassLabel).astype(np.uint8)
[groundTruthDT, groundTruthEdgelsCount
] = utils.mask2dtAndEdgelsCount(groundTruthGlassMask)
for (index, temporaryFile) in enumerate(segmentationTemporaryFiles):
segmentationImage = cv2.imread(temporaryFile[1],
cv2.CV_LOAD_IMAGE_GRAYSCALE)
[segmentationImageDT, segmentationImageEdgelsCount
] = utils.mask2dtAndEdgelsCount(segmentationImage)
[recallEdgelsCount, precisionEdgelsCount
] = utils.computeRecallPrecisionEdgels(groundTruthDT,
segmentationImageDT)
trueGlassArea = len(np.nonzero(groundTruth == glassLabel)[0])
predictedGlassArea = len(
np.nonzero(segmentationImage == glassLabel)[0])
validPredictedGlassArea = len(
np.nonzero(
if (match == None):
match = re.search('_(0000(0))\.', imageFilename)
assert match != None, 'Cannot parse an image index'
fullImageIndex = match.group(1)
imageIndex = match.group(2)
groundTruthFilename = imageFilename.replace('/image_', '/' + groundTruthPrefix + '_')
testFolder = imageFilename.replace('/image_' + fullImageIndex + '.png', '/')
call([segmentImage, testFolder, fullImageIndex, classifierFilename, segmentationListFilename, propagationScalingsList, algorithmName])
groundTruth = cv2.imread(groundTruthFilename, cv2.CV_LOAD_IMAGE_GRAYSCALE)
glassLabel = 255
groundTruthGlassMask = (groundTruth == glassLabel).astype(np.uint8)
[groundTruthDT, groundTruthEdgelsCount] = utils.mask2dtAndEdgelsCount(groundTruthGlassMask)
for (index, temporaryFile) in enumerate(segmentationTemporaryFiles):
segmentationImage = cv2.imread(temporaryFile[1], cv2.CV_LOAD_IMAGE_GRAYSCALE)
[segmentationImageDT, segmentationImageEdgelsCount] = utils.mask2dtAndEdgelsCount(segmentationImage)
[recallEdgelsCount, precisionEdgelsCount] = utils.computeRecallPrecisionEdgels(groundTruthDT, segmentationImageDT)
trueGlassArea = len(np.nonzero(groundTruth == glassLabel)[0])
predictedGlassArea = len(np.nonzero(segmentationImage == glassLabel)[0])
validPredictedGlassArea = len(np.nonzero(np.logical_and(groundTruth == glassLabel, segmentationImage == groundTruth))[0])
boundaryEvaluator.addObservation(index, recallEdgelsCount, groundTruthEdgelsCount, precisionEdgelsCount, segmentationImageEdgelsCount)
areaEvaluator.addObservation(index, validPredictedGlassArea, trueGlassArea, validPredictedGlassArea, predictedGlassArea)
areaEvaluator.computeStatistics()
areaEvaluator.printStatistics()