github/dejavu
1
0
Fork 0
mirror of https://github.com/correl/dejavu.git synced 2024-11-23 11:09:52 +00:00
Code Issues Projects Releases Packages Wiki Activity

Added annotations for different fingerprinting parameters

Browse source
This commit is contained in:
Will Drevo 2014-07-03 00:43:40 -04:00
parent a779ca4cf9
commit 60d9d6758e
1 changed files with 48 additions and 7 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

47
dejavu/fingerprint.py
View file

@ -7,20 +7,60 @@ from scipy.ndimage.morphology import (generate_binary_structure,
import hashlib
from operator import itemgetter
IDX_FREQ_I = 0
IDX_TIME_J = 1
######################################################################
# Sampling rate, related to the Nyquist conditions, which affects
# the range frequencies we can detect.
DEFAULT_FS = 44100
######################################################################
# Size of the FFT window, affects frequency granularity
DEFAULT_WINDOW_SIZE = 4096
######################################################################
# Ratio by which each sequential window overlaps the last and the
# next window. Higher overlap will allow a higher granularity of offset
# matching, but potentially more fingerprints.
DEFAULT_OVERLAP_RATIO = 0.5
######################################################################
# Degree to which a fingerprint can be paired with its neighbors --
# higher will cause more fingerprints, but potentially better accuracy.
DEFAULT_FAN_VALUE = 15
######################################################################
# Minimum amplitude in spectrogram in order to be considered a peak.
# This can be raised to reduce number of fingerprints, but can negatively
# affect accuracy.
DEFAULT_AMP_MIN = 10
######################################################################
# Number of cells around an amplitude peak in the spectrogram in order
# for Dejavu to consider it a spectral peak. Higher values mean less
# fingerprints and faster matching, but can potentially affect accuracy.
PEAK_NEIGHBORHOOD_SIZE = 20
######################################################################
# Thresholds on how close or far fingerprints can be in time in order
# to be paired as a fingerprint. If your max is too low, higher values of
# DEFAULT_FAN_VALUE may not perform as expected.
MIN_HASH_TIME_DELTA = 0
MAX_HASH_TIME_DELTA = 200
######################################################################
# If True, will sort peaks temporally for fingerprinting;
# not sorting will cut down number of fingerprints, but potentially
# affect performance.
PEAK_SORT = True
######################################################################
# Number of bits to throw away from the front of the SHA1 hash in the
# fingerprint calculation. The more you throw away, the less storage, but
# potentially higher collisions and misclassifications when identifying songs.
FINGERPRINT_REDUCTION = 20
def fingerprint(channel_samples, Fs=DEFAULT_FS,
wsize=DEFAULT_WINDOW_SIZE,
wratio=DEFAULT_OVERLAP_RATIO,
@ -98,7 +138,8 @@ def generate_hashes(peaks, fan_value=DEFAULT_FAN_VALUE):
"""
fingerprinted = set() # to avoid rehashing same pairs
peaks.sort(key=itemgetter(1))
if PEAK_SORT:
peaks.sort(key=itemgetter(1))
for i in range(len(peaks)):
for j in range(1, fan_value):
@ -114,7 +155,7 @@ def generate_hashes(peaks, fan_value=DEFAULT_FAN_VALUE):
if t_delta >= MIN_HASH_TIME_DELTA and t_delta <= MAX_HASH_TIME_DELTA:
h = hashlib.sha1(
"%s|%s|%s" % (str(freq1), str(freq2), str(t_delta)))
yield (h.hexdigest()[0:20], t1)
yield (h.hexdigest()[0:FINGERPRINT_REDUCTION], t1)
# ensure we don't repeat hashing
fingerprinted.add((i, i + j))