def get_deviations_to_notoriginal(oPandasData, sReferenceCollectionName):
""" used for FAR test """
oPandasFullHashTypeDataset = None
for sHashType in oPandasData.hashalgorithm.unique():
for i, sImageBaseName in enumerate(
oPandasData[oPandasData.collection ==
sReferenceCollectionName].image.unique()):
sImageBaseName = sImageBaseName.split(".")[-2]
oPandasHashData = oPandasData[
(oPandasData.hashalgorithm == sHashType)
& (oPandasData.image.str.contains(sImageBaseName))]
# choose a deterministic ref image that is not the original
np.random.seed(i)
oRefHash = np.random.choice(oPandasData[
(oPandasData.collection == sReferenceCollectionName)
& (oPandasData.hashalgorithm == sHashType) &
(~oPandasData.image.str.contains(sImageBaseName))].hash.values)
oPandasHashData = oPandasHashData[
oPandasHashData.collection != sReferenceCollectionName]
oPandasHashData["deviation"] = oPandasHashData.apply(
lambda row: deviation.hamming_distance(row["hash"], oRefHash),
axis=1)
if isinstance(oPandasFullHashTypeDataset, pd.DataFrame):
oPandasFullHashTypeDataset = pd.concat(
[oPandasFullHashTypeDataset, oPandasHashData])
else:
oPandasFullHashTypeDataset = oPandasHashData
return oPandasFullHashTypeDataset
def calculate_stats(oSensitivityTestData,
lTestDatasetSize,
lRandomDataSplitSeed=None):
dicResult = {}
# do it for every single hash algorithm
for sHashAlgo in oSensitivityTestData.hashalgorithm.unique():
# filter dataset by hashalgo
oFilteredSensitivityTestData = oSensitivityTestData[
oSensitivityTestData.hashalgorithm == sHashAlgo]
# split the data in a testset and a big reference set
oBigDataset, oTestDataset = train_test_split(
oFilteredSensitivityTestData,
test_size=lTestDatasetSize,
random_state=lRandomDataSplitSeed)
# DEBUG
print(sHashAlgo)
print(len(oBigDataset.image.unique()))
print(len(oTestDataset.image.unique()))
# create deviation array having size of
# nr. of test_images * # nr. of reference_images
lNumberOfTestReferenceRelationsTotal = oTestDataset.shape[0] * \
oBigDataset.shape[0]
aHashDeviations = np.zeros(lNumberOfTestReferenceRelationsTotal)
# iterate over every image in the test dataset
i = 0
for aTestImageHash in oTestDataset["hash"].values:
# iterate over all images in the big reference dataset
for aReferenceImageHash in oBigDataset["hash"].values:
aHashDeviations[i] = deviation.hamming_distance(
aTestImageHash, aReferenceImageHash)
i += 1
# calculate metrics
dicMetrics = {
"min": np.min(aHashDeviations),
"p25": np.percentile(aHashDeviations, 25),
"p75": np.percentile(aHashDeviations, 75),
"max": np.max(aHashDeviations),
"mean": np.mean(aHashDeviations)
}
# calculate FAR error rate for every threshold step
aErrorRate = []
for dThreshold in aThresholdSteps:
lCountOfValuesSmallerThreshold = np.sum(
np.array(aHashDeviations) < dThreshold)
aErrorRate.append(lCountOfValuesSmallerThreshold /
lNumberOfTestReferenceRelationsTotal)
dicResult[sHashAlgo] = {"metrics": dicMetrics, "errorrate": aErrorRate}
return dicResult
def get_deviations_to_original(oPandasData, sReferenceCollectionName):
oPandasFullHashTypeDataset = None
for sHashType in oPandasData.hashalgorithm.unique():
for sImageBaseName in oPandasData[
oPandasData.collection ==
sReferenceCollectionName].image.unique():
sImageBaseName = sImageBaseName.split(".")[-2]
oPandasHashData = oPandasData[
(oPandasData.hashalgorithm == sHashType)
& (oPandasData.image.str.contains(sImageBaseName))]
oRefHash = oPandasHashData[oPandasHashData.collection ==
sReferenceCollectionName].hash.values[0]
oPandasHashData = oPandasHashData[
oPandasHashData.collection != sReferenceCollectionName]
oPandasHashData["deviation"] = oPandasHashData.apply(
lambda row: deviation.hamming_distance(row["hash"], oRefHash),
axis=1)
if isinstance(oPandasFullHashTypeDataset, pd.DataFrame):
oPandasFullHashTypeDataset = pd.concat(
[oPandasFullHashTypeDataset, oPandasHashData])
else:
oPandasFullHashTypeDataset = oPandasHashData
return oPandasFullHashTypeDataset