def test_captcha_recognition():
c.clear_temp()
seq = None
# Below are all the training images that are partitioned falsely
# seq = 'YFF5M'
# seq = 'W1PM4'
# seq = 'W1R4R'
# seq = 'YTM6X'
# seq = 'W9WU4'
# seq = 'EFTWY'
# seq = '5WTGP'
# seq = '113W2'
# seq = 'UWFG1'
# Sticking together
# seq = 'WMQPQ'
# seq = '14FWX'
# seq = '4TJ3R'
# seq = '5PW9Y'
# seq = '6ML6X'
# seq = '48HXH'
# seq = 'Y581K'
# Isolation
# seq = 'QN4EL'
# Complicated
# seq = '2XML9'
# seq = 'W9WU4'
# image = dataset_manager.get_training_image(seq)
# image = dataset_manager.get_test_image(seq)
a = BilibiliCaptchaProvider()
image = a.fetch()
success, captcha = CaptchaRecognizer().recognize(image,
save_intermediate=True,
verbose=True,
reoptimize=False)
if success:
print(captcha)
print('Recognized captcha is ',
BilibiliCaptchaProvider().verify(captcha))
def test_captcha_recognition():
c.clear_temp()
seq = None
# Below are all the training images that are partitioned falsely
# seq = 'YFF5M'
# seq = 'W1PM4'
# seq = 'W1R4R'
# seq = 'YTM6X'
# seq = 'W9WU4'
# seq = 'EFTWY'
# seq = '5WTGP'
# seq = '113W2'
# seq = 'UWFG1'
# Sticking together
# seq = 'WMQPQ'
# seq = '14FWX'
# seq = '4TJ3R'
# seq = '5PW9Y'
# seq = '6ML6X'
# seq = '48HXH'
# seq = 'Y581K'
# Isolation
# seq = 'QN4EL'
# Complicated
# seq = '2XML9'
# seq = 'W9WU4'
# image = dataset_manager.get_training_image(seq)
# image = dataset_manager.get_test_image(seq)
a = BilibiliCaptchaProvider()
image = a.fetch()
success, captcha = CaptchaRecognizer().recognize(image,
save_intermediate=True,
verbose=True,
reoptimize=False)
if success:
print(captcha)
print('Recognized captcha is ', BilibiliCaptchaProvider().verify(captcha))
def __init__(self, captcha_provider=BilibiliCaptchaProvider(),
h_tol=6 / 360,
s_tol=36 / 100,
v_tol=40 / 100):
# Three parameters to be used in remove_noise_with_hsv
self.h_tolerance = h_tol
self.s_tolerance = s_tol
self.v_tolerance = v_tol
self.character_num = captcha_provider.seq_length
# Four parameters to be used in partition
self.char_width_min = 5
self.char_width_max = 30
self.char_height_min = 10
self.char_height_max = 30
with open(os.path.join(c.get('dataset'), c.get('fail_char.txt'))) as f:
_fail_char_set = set(f.read().splitlines())
_PARTITION_JSON = os.path.join(_dataset_dir, 'partition.json')
_NUM_TOTAL = '###total'
_NUM_FAIL = '##fail'
_NUM_SUCCESS = '##success'
_SUCCESS_RATE = '##success_rate'
_NUM_CHAR = '#{}'
_FAIL = 'fail'
_SUCCESS = 'success'
# the sequence that tells the program to skip a image when fetching
_SEQ_SKIP = '0'
_captcha_provider = BilibiliCaptchaProvider()
def _get_training_char_dir(char):
return os.path.join(_training_char_dir, char)
for _char in _captcha_provider.chars:
c.make_dirs(_get_training_char_dir(_char))
def _get_training_char_path(char, path):
return os.path.join(_get_training_char_dir(char), path)
# Fetch some CAPTCHA images from a CAPTCHA source to a directory
def test_recognize_http(show_img=False, num=1, reconstruct=False, force_partition=True):
time_start = time.time()
provider = BilibiliCaptchaProvider()
recognizer = CaptchaRecognizer()
fail = 0
right_strong = 0
right_weak = 0
wrong_strong = 0
wrong_weak = 0
for i in range(num):
image = time_func("fetch" if num == 1 else None, lambda: provider.fetch())
if show_img and num == 1:
show_image(image)
if num == 1:
success, seq, weak_confidence = recognizer.recognize(
image, save_intermediate=True, verbose=True, reconstruct=reconstruct, force_partition=force_partition
)
else:
if i == 0:
success, seq, weak_confidence = recognizer.recognize(
image,
save_intermediate=False,
verbose=False,
reconstruct=reconstruct,
force_partition=force_partition,
)
else:
success, seq, weak_confidence = recognizer.recognize(
image, save_intermediate=False, verbose=False, reconstruct=False, force_partition=force_partition
)
if success:
print(seq)
result = time_func("verify" if num == 1 else None, lambda: provider.verify(seq))
if num == 1:
print("Recognized seq is {}".format(result))
if result:
if weak_confidence:
right_weak += 1
else:
right_strong += 1
else:
if weak_confidence:
wrong_weak += 1
else:
wrong_strong += 1
else:
fail += 1
right_total = right_strong + right_weak
wrong_total = wrong_strong + wrong_weak
print("Fail: ", fail)
print("Right weak: ", right_weak)
print("Right strong: ", right_strong)
print("Right total: ", right_total)
print("Wrong weak: ", wrong_weak)
print("Wrong strong: ", wrong_strong)
print("Wrong total: ", wrong_total)
print("Total success rate: ", (right_weak + right_strong) / num)
print("Success rate when confident: ", (right_strong + right_weak) / (num - fail) if num - fail > 0 else 0)
print(
"Success rate when strongly confident: ",
right_strong / (right_strong + wrong_strong) if right_strong + wrong_strong > 0 else 0,
)
print(
"Success rate when weakly confident: ",
right_weak / (right_weak + wrong_weak) if right_weak + wrong_weak > 0 else 0,
)
time_end = time.time()
print("Time used to test recognize http is: ", time_end - time_start)
def test_recognize_http(show_img=False,
num=1,
reconstruct=False,
force_partition=True):
time_start = time.time()
provider = BilibiliCaptchaProvider()
recognizer = CaptchaRecognizer()
fail = 0
right_strong = 0
right_weak = 0
wrong_strong = 0
wrong_weak = 0
for i in range(num):
image = time_func('fetch' if num == 1 else None,
lambda: provider.fetch())
if show_img and num == 1:
show_image(image)
if num == 1:
success, seq, weak_confidence = recognizer.recognize(
image,
save_intermediate=True,
verbose=True,
reconstruct=reconstruct,
force_partition=force_partition)
else:
if i == 0:
success, seq, weak_confidence = recognizer.recognize(
image,
save_intermediate=False,
verbose=False,
reconstruct=reconstruct,
force_partition=force_partition)
else:
success, seq, weak_confidence = recognizer.recognize(
image,
save_intermediate=False,
verbose=False,
reconstruct=False,
force_partition=force_partition)
if success:
print(seq)
result = time_func('verify' if num == 1 else None,
lambda: provider.verify(seq))
if num == 1:
print('Recognized seq is {}'.format(result))
if result:
if weak_confidence:
right_weak += 1
else:
right_strong += 1
else:
if weak_confidence:
wrong_weak += 1
else:
wrong_strong += 1
else:
fail += 1
right_total = right_strong + right_weak
wrong_total = wrong_strong + wrong_weak
print('Fail: ', fail)
print('Right weak: ', right_weak)
print('Right strong: ', right_strong)
print('Right total: ', right_total)
print('Wrong weak: ', wrong_weak)
print('Wrong strong: ', wrong_strong)
print('Wrong total: ', wrong_total)
print('Total success rate: ', (right_weak + right_strong) / num)
print('Success rate when confident: ',
(right_strong + right_weak) / (num - fail) if num - fail > 0 else 0)
print(
'Success rate when strongly confident: ',
right_strong / (right_strong + wrong_strong)
if right_strong + wrong_strong > 0 else 0)
print(
'Success rate when weakly confident: ', right_weak /
(right_weak + wrong_weak) if right_weak + wrong_weak > 0 else 0)
time_end = time.time()
print('Time used to test recognize http is: ', time_end - time_start)