def draw_missed_letters_figure(
input_dir='/datagrid/personal/TextSpotter/FastTextEval/ICDAR-Train',
color=0,
edgeThreshold=13,
inter=True,
scalingFactor=0.5,
segmList=[]):
ft = FASTex(process_color=color, edgeThreshold=edgeThreshold)
d = input_dir
subdirs = [
os.path.join(d, o) for o in os.listdir(d)
if os.path.isdir(os.path.join(d, o))
]
subdirs = np.sort(subdirs)
lastDir = ''
for dir_name in subdirs:
file_name = '{0}/evaluation.npz'.format(dir_name)
if not os.path.exists(file_name):
continue
vars_dict = np.load(file_name)
inputDir = vars_dict['inputDir']
lastDir = dir_name
if 'letterKeypointHistogram' in vars_dict.keys():
letterKeypointHistogram = vars_dict['letterKeypointHistogram']
letterKeypointHistogram = dict(letterKeypointHistogram.tolist())
print(lastDir)
missing_letters = vars_dict['missing_letters']
missing_letters = dict(missing_letters.tolist())
keys = []
ticks = []
values = []
values.append([])
values.append([])
values.append([])
values.append([])
ticks.append([])
ticks.append([])
ticks.append([])
ticks.append([])
listlen = 0
for letter in letterKeypointHistogram.keys():
keys.append(letter)
values[0].append(0)
ticks[0].append(listlen)
values[1].append(0)
ticks[1].append(listlen + 0.2)
values[2].append(0)
ticks[2].append(listlen + 0.4)
values[3].append(0)
ticks[3].append(listlen + 0.6)
for num in letterKeypointHistogram[letter].keys():
values[num][listlen] = letterKeypointHistogram[letter][num]
listlen += 1
indices = sorted(range(len(values[0])), key=lambda x: values[0][x])
indices.reverse()
missLetter = []
imagesMiss = {}
for letter in np.asarray(keys)[np.asarray(indices)]:
if not missing_letters.has_key(letter):
continue
arr = missing_letters[letter]
for i in range(len(arr)):
miss = arr[i]
if len(segmList) > 0:
base = os.path.basename(miss[0])
if not base in segmList:
continue
missLetter.append(miss)
if imagesMiss.has_key(miss[0]):
imagesMiss[miss[0]].append(miss[1])
else:
imagesMiss[miss[0]] = []
imagesMiss[miss[0]].append(miss[1])
for image in imagesMiss.keys():
f = plt.figure(num=250)
ax = f.add_subplot(111)
imgc2 = cv2.imread(image)
img = cv2.imread(image, cv2.IMREAD_GRAYSCALE)
imgc2 = cv2.cvtColor(imgc2, cv2.COLOR_BGR2RGB)
ax.imshow(imgc2)
segmentations = ft.getCharSegmentations(img)
keypoints = ft.getLastDetectionKeypoints()
octaves = np.unique(keypoints[:, 2])
maxOctave = np.max(octaves)
scales = ft.getImageScales()
for i in range(int(maxOctave) + 1):
octavePoints = keypoints[keypoints[:, 2] == i, :]
c = 'red'
if len(octavePoints) > 0 and octavePoints.shape[1] > 9:
for k in range(6):
maski = octavePoints[:, 9] == k + 1
if k == 1:
style = "rv"
if k == 2:
style = "ro"
if k == 4:
style = "bo"
c = 'blue'
if k == 5:
style = "yo"
continue
s = 10 / scales[i]
ax.scatter(octavePoints[maski, 0],
octavePoints[maski, 1],
c=c,
s=s)
for i in range(len(imagesMiss[image])):
gt0 = imagesMiss[image][i]
line = mlines.Line2D(
np.array([gt0[0], gt0[2], gt0[2], gt0[0], gt0[0]]),
np.array([gt0[1], gt0[1], gt0[3], gt0[3], gt0[1]]),
lw=5.,
alpha=0.6,
color='r')
ax.add_line(line)
plt.subplots_adjust(top=1,
bottom=0,
right=1,
left=0,
hspace=0,
wspace=0)
plt.margins(0, 0)
ax.set_xlim([0, imgc2.shape[1]])
ax.set_ylim([imgc2.shape[0], 0])
ax.axes.get_xaxis().set_ticks([])
ax.axes.get_yaxis().set_ticks([])
plt.show()
def draw_missed_letters_figure(input_dir='/datagrid/personal/TextSpotter/FastTextEval/ICDAR-Train', color = 0, edgeThreshold = 13, inter = True, scalingFactor=0.5, segmList=[]):
ft = FASTex(process_color = color, edgeThreshold = edgeThreshold)
d=input_dir
subdirs = [os.path.join(d,o) for o in os.listdir(d) if os.path.isdir(os.path.join(d,o))]
subdirs = np.sort(subdirs)
lastDir = ''
for dir_name in subdirs:
file_name = '{0}/evaluation.npz'.format(dir_name)
if not os.path.exists(file_name):
continue
vars_dict = np.load(file_name)
inputDir = vars_dict['inputDir']
lastDir = dir_name
if 'letterKeypointHistogram' in vars_dict.keys():
letterKeypointHistogram = vars_dict['letterKeypointHistogram']
letterKeypointHistogram = dict(letterKeypointHistogram.tolist())
print(lastDir)
missing_letters = vars_dict['missing_letters']
missing_letters = dict(missing_letters.tolist())
keys = []
ticks = []
values = []
values.append([])
values.append([])
values.append([])
values.append([])
ticks.append([])
ticks.append([])
ticks.append([])
ticks.append([])
listlen = 0
for letter in letterKeypointHistogram.keys():
keys.append(letter)
values[0].append(0)
ticks[0].append(listlen)
values[1].append(0)
ticks[1].append(listlen + 0.2)
values[2].append(0)
ticks[2].append(listlen + 0.4)
values[3].append(0)
ticks[3].append(listlen + 0.6)
for num in letterKeypointHistogram[letter].keys():
values[num][listlen] = letterKeypointHistogram[letter][num]
listlen += 1
indices = sorted(range(len(values[0])),key=lambda x:values[0][x])
indices.reverse()
missLetter = []
imagesMiss = {}
for letter in np.asarray(keys)[np.asarray(indices)]:
if not missing_letters.has_key(letter):
continue
arr = missing_letters[letter]
for i in range(len(arr)):
miss = arr[i]
if len(segmList) > 0:
base = os.path.basename(miss[0])
if not base in segmList:
continue
missLetter.append(miss)
if imagesMiss.has_key(miss[0]):
imagesMiss[miss[0]].append( miss[1] )
else:
imagesMiss[miss[0]] = []
imagesMiss[miss[0]].append( miss[1] )
for image in imagesMiss.keys():
f = plt.figure(num = 250)
ax = f.add_subplot(111)
imgc2 = cv2.imread(image)
img = cv2.imread(image, cv2.IMREAD_GRAYSCALE)
imgc2 = cv2.cvtColor(imgc2, cv2.COLOR_BGR2RGB)
ax.imshow(imgc2)
segmentations = ft.getCharSegmentations(img)
keypoints = ft.getLastDetectionKeypoints()
octaves = np.unique( keypoints[:, 2])
maxOctave = np.max(octaves)
scales = ft.getImageScales()
for i in range(int(maxOctave) + 1):
octavePoints = keypoints[keypoints[:, 2] == i, :]
c = 'red'
if len(octavePoints) > 0 and octavePoints.shape[1] > 9:
for k in range(6):
maski = octavePoints[:, 9] == k + 1
if k == 1:
style = "rv"
if k == 2:
style = "ro"
if k == 4:
style = "bo"
c = 'blue'
if k == 5:
style = "yo"
continue
s = 10 / scales[i]
ax.scatter(octavePoints[maski, 0], octavePoints[maski, 1],c=c, s=s )
for i in range(len(imagesMiss[image])):
gt0 = imagesMiss[image][i]
line = mlines.Line2D(np.array([gt0[0], gt0[2], gt0[2], gt0[0], gt0[0]]), np.array([gt0[1], gt0[1], gt0[3], gt0[3], gt0[1]]), lw=5., alpha=0.6, color='r')
ax.add_line(line)
plt.subplots_adjust(top = 1, bottom = 0, right = 1, left = 0, hspace = 0, wspace = 0)
plt.margins(0,0)
ax.set_xlim([0, imgc2.shape[1]])
ax.set_ylim([imgc2.shape[0], 0])
ax.axes.get_xaxis().set_ticks([])
ax.axes.get_yaxis().set_ticks([])
plt.show()
def draw_missed_letters(
input_dir='/datagrid/personal/TextSpotter/FastTextEval/ICDAR-Train',
color=0,
edgeThreshold=12,
inter=True,
scalingFactor=0.5):
ft = FASTex(process_color=color, edgeThreshold=edgeThreshold)
d = input_dir
subdirs = [
os.path.join(d, o) for o in os.listdir(d)
if os.path.isdir(os.path.join(d, o))
]
subdirs = np.sort(subdirs)
lastDir = ''
for dir_name in subdirs:
file_name = '{0}/evaluation.npz'.format(dir_name)
if not os.path.exists(file_name):
continue
vars_dict = np.load(file_name)
inputDir = vars_dict['inputDir']
lastDir = dir_name
if 'letterKeypointHistogram' in vars.keys():
letterKeypointHistogram = vars_dict['letterKeypointHistogram']
letterKeypointHistogram = dict(letterKeypointHistogram.tolist())
print(lastDir)
missing_letters = vars['missing_letters']
missing_letters = dict(missing_letters.tolist())
segmDir = '{0}/segmentations'.format(inputDir)
keys = []
ticks = []
values = []
values.append([])
values.append([])
values.append([])
values.append([])
ticks.append([])
ticks.append([])
ticks.append([])
ticks.append([])
listlen = 0
for letter in letterKeypointHistogram.keys():
keys.append(letter)
values[0].append(0)
ticks[0].append(listlen)
values[1].append(0)
ticks[1].append(listlen + 0.2)
values[2].append(0)
ticks[2].append(listlen + 0.4)
values[3].append(0)
ticks[3].append(listlen + 0.6)
for num in letterKeypointHistogram[letter].keys():
values[num][listlen] = letterKeypointHistogram[letter][num]
listlen += 1
indices = sorted(range(len(values[0])), key=lambda x: values[0][x])
indices.reverse()
border = 25
for letter in np.asarray(keys)[np.asarray(indices)]:
if not missing_letters.has_key(letter):
continue
arr = missing_letters[letter]
for i in range(len(arr)):
miss = arr[i]
gt0 = miss[1]
gt = [
gt0[0] - border, gt0[1] - border, gt0[2] + border,
gt0[3] + border
]
gt[0] = max(0, gt[0])
gt[1] = max(0, gt[1])
if color == 1:
img = cv2.imread(miss[0])
else:
img = cv2.imread(miss[0], 0)
gt[2] = min(img.shape[1], gt[2])
gt[3] = min(img.shape[0], gt[3])
baseName = os.path.basename(miss[0])
baseName = baseName[:-4]
segmImg = '{0}/{1}_GT.bmp'.format(segmDir, baseName)
segmImg = '{0}/{1}_GT.bmp'.format(segmDir, baseName)
if not os.path.exists(segmImg):
segmImg = '{0}/gt_{1}.png'.format(segmDir, baseName)
segmImg = cv2.imread(segmImg)
segmentations = ft.getCharSegmentations(img)
keypoints = ft.getLastDetectionKeypoints()
scales = ft.getImageScales()
centers = segmImg[keypoints[:, 1].astype(int),
keypoints[:, 0].astype(int)]
keypointsInsideMask = centers == (255, 255, 255)
keypointsInsideMask = np.invert(
np.bitwise_and(
np.bitwise_and(keypointsInsideMask[:, 0],
keypointsInsideMask[:, 1]),
keypointsInsideMask[:, 2]))
keypointsInside = keypoints[keypointsInsideMask, :]
octaves = np.unique(keypointsInside[:, 2])
maxOctave = 0
if octaves.shape[0] > 0:
maxOctave = np.max(octaves)
mask = (keypoints[:, 0] > gt[0]) * (keypoints[:, 0] < gt[2]) * (
keypoints[:, 1] > gt[1]) * (keypoints[:, 1] < gt[3])
images = []
octPoints = []
octScales = []
keypointsInRect = keypoints[mask, :]
for i in range(int(maxOctave) + 1):
scale = scales[i]
ft = FASTex(process_color=color, edgeThreshold=edgeThreshold)
octavePoints = keypointsInRect[keypointsInRect[:, 2] ==
i, :].copy()
if octavePoints.shape[0] > 0:
dst = ft.getImageAtScale(i)
images.append(dst)
octavePoints[:, 0] *= scales[i]
octavePoints[:, 1] *= scales[i]
octavePoints[:, 5] *= scales[i]
octavePoints[:, 6] *= scales[i]
octavePoints[:, 7] *= scales[i]
octavePoints[:, 8] *= scales[i]
octPoints.append(octavePoints)
octScales.append(scale)
f, axes = plt.subplots(1, 1 + len(images), figsize=(16, 3))
if len(images) > 0:
ax = axes[0]
else:
ax = axes
if color == 1:
img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
zoom = img[gt[1]:gt[3], gt[0]:gt[2]]
ax.imshow(zoom, cmap=pylab.gray(), interpolation='nearest')
kpMask = keypoints[mask]
kpMask[:, 0] = kpMask[:, 0] - gt[0]
kpMask[:, 1] = kpMask[:, 1] - gt[1]
kpMask[:, 7] = kpMask[:, 7] - gt[0]
kpMask[:, 8] = kpMask[:, 8] - gt[1]
ax.plot(kpMask[:, 0], kpMask[:, 1], 'ro')
for k in range(kpMask.shape[0]):
ax.plot([kpMask[k, 0], kpMask[k, 7]],
[kpMask[k, 1], kpMask[k, 8]], 'r-')
style = 'rx'
if kpMask.shape[1] > 9:
for k in range(3):
maski = kpMask[:, 9] == k + 1
if k == 1:
style = "rv"
if k == 2:
style = "rs"
if k == 4:
style = "bo"
if k == 5:
style = "yo"
ax.plot([kpMask[maski, 7]], [kpMask[maski, 8]], style)
mask = (keypointsInside[:, 0] >
gt[0]) * (keypointsInside[:, 0] < gt[2]) * (
keypointsInside[:, 1] > gt[1]) * (keypointsInside[:, 1]
< gt[3])
kpMask = keypointsInside[mask]
keypointsInside[:, 0] = keypointsInside[:, 0] - gt[0]
keypointsInside[:, 1] = keypointsInside[:, 1] - gt[1]
keypointsInside[:, 7] = keypointsInside[:, 7] - gt[0]
keypointsInside[:, 8] = keypointsInside[:, 8] - gt[1]
ax.plot(keypointsInside[:, 0], keypointsInside[:, 1], 'go')
for k in range(keypointsInside.shape[0]):
ax.plot([keypointsInside[k, 0], keypointsInside[k, 7]],
[keypointsInside[k, 1], keypointsInside[k, 8]], 'g-')
ax.set_xlim(0, gt[2] - max(0, gt[0]))
ax.set_ylim((gt[3] - max(0, gt[1]), 0))
line = mlines.Line2D(np.array([
gt0[0] - gt[0], gt0[2] - gt[0], gt0[2] - gt[0], gt0[0] - gt[0],
gt0[0] - gt[0]
]),
np.array([
gt0[1] - gt[1], gt0[1] - gt[1],
gt0[3] - gt[1], gt0[3] - gt[1],
gt0[1] - gt[1]
]),
lw=5.,
alpha=0.4,
color='b')
ax.add_line(line)
f.suptitle('Missing letter: {0} ({1})'.format(gt0[4], miss[0]))
for ai in range(len(images)):
ax = axes[ai + 1]
scale = octScales[ai]
gts = (gt[0] * scale, gt[1] * scale, gt[2] * scale,
gt[3] * scale)
ax.plot(octPoints[ai][:, 0] - gts[0],
octPoints[ai][:, 1] - gts[1], 'ro')
zoom = images[ai][int(gt[1] * scale):int(gt[3] * scale),
int(gt[0] * scale):int(gt[2] * scale)]
ax.imshow(zoom, cmap=pylab.gray(), interpolation='nearest')
ax.set_xlim(0, gts[2] - max(0, gts[0]))
ax.set_ylim((gts[3] - max(0, gts[1]), 0))
plt.show()
def draw_missed_letters(input_dir='/datagrid/personal/TextSpotter/FastTextEval/ICDAR-Train', color = 0, edgeThreshold = 12, inter = True, scalingFactor=0.5):
ft = FASTex(process_color = color, edgeThreshold = edgeThreshold)
d=input_dir
subdirs = [os.path.join(d,o) for o in os.listdir(d) if os.path.isdir(os.path.join(d,o))]
subdirs = np.sort(subdirs)
lastDir = ''
for dir_name in subdirs:
file_name = '{0}/evaluation.npz'.format(dir_name)
if not os.path.exists(file_name):
continue
vars_dict = np.load(file_name)
inputDir = vars_dict['inputDir']
lastDir = dir_name
if 'letterKeypointHistogram' in vars.keys():
letterKeypointHistogram = vars_dict['letterKeypointHistogram']
letterKeypointHistogram = dict(letterKeypointHistogram.tolist())
print(lastDir)
missing_letters = vars['missing_letters']
missing_letters = dict(missing_letters.tolist())
segmDir = '{0}/segmentations'.format(inputDir)
keys = []
ticks = []
values = []
values.append([])
values.append([])
values.append([])
values.append([])
ticks.append([])
ticks.append([])
ticks.append([])
ticks.append([])
listlen = 0
for letter in letterKeypointHistogram.keys():
keys.append(letter)
values[0].append(0)
ticks[0].append(listlen)
values[1].append(0)
ticks[1].append(listlen + 0.2)
values[2].append(0)
ticks[2].append(listlen + 0.4)
values[3].append(0)
ticks[3].append(listlen + 0.6)
for num in letterKeypointHistogram[letter].keys():
values[num][listlen] = letterKeypointHistogram[letter][num]
listlen += 1
indices = sorted(range(len(values[0])),key=lambda x:values[0][x])
indices.reverse()
border = 25
for letter in np.asarray(keys)[np.asarray(indices)]:
if not missing_letters.has_key(letter):
continue
arr = missing_letters[letter]
for i in range(len(arr)):
miss = arr[i]
gt0 = miss[1]
gt = [gt0[0] - border, gt0[1] - border, gt0[2] + border, gt0[3] + border ]
gt[0] = max(0, gt[0])
gt[1] = max(0, gt[1])
if color == 1:
img = cv2.imread(miss[0])
else:
img = cv2.imread(miss[0], 0)
gt[2] = min(img.shape[1], gt[2])
gt[3] = min(img.shape[0], gt[3])
baseName = os.path.basename(miss[0])
baseName = baseName[:-4]
segmImg = '{0}/{1}_GT.bmp'.format(segmDir, baseName)
segmImg = '{0}/{1}_GT.bmp'.format(segmDir, baseName)
if not os.path.exists(segmImg):
segmImg = '{0}/gt_{1}.png'.format(segmDir, baseName)
segmImg = cv2.imread(segmImg)
segmentations = ft.getCharSegmentations(img)
keypoints = ft.getLastDetectionKeypoints()
scales = ft.getImageScales()
centers = segmImg[keypoints[:, 1].astype(int), keypoints[:, 0].astype(int)]
keypointsInsideMask = centers == (255, 255, 255)
keypointsInsideMask = np.invert(np.bitwise_and(np.bitwise_and(keypointsInsideMask[:, 0], keypointsInsideMask[:, 1]), keypointsInsideMask[:, 2]))
keypointsInside = keypoints[keypointsInsideMask, :]
octaves = np.unique( keypointsInside[:, 2])
maxOctave = 0
if octaves.shape[0] > 0:
maxOctave = np.max(octaves)
mask = (keypoints[:, 0] > gt[0]) * (keypoints[:, 0] < gt[2]) * (keypoints[:, 1] > gt[1]) * (keypoints[:, 1] < gt[3])
images = []
octPoints = []
octScales = []
keypointsInRect = keypoints[mask, :]
for i in range(int(maxOctave) + 1):
scale = scales[i]
ft = FASTex(process_color = color, edgeThreshold = edgeThreshold)
octavePoints = keypointsInRect[keypointsInRect[:, 2] == i, :].copy()
if octavePoints.shape[0] > 0:
dst = ft.getImageAtScale(i)
images.append(dst)
octavePoints[:, 0] *= scales[i]
octavePoints[:, 1] *= scales[i]
octavePoints[:, 5] *= scales[i]
octavePoints[:, 6] *= scales[i]
octavePoints[:, 7] *= scales[i]
octavePoints[:, 8] *= scales[i]
octPoints.append(octavePoints)
octScales.append(scale)
f, axes = plt.subplots(1, 1 + len(images), figsize=(16, 3))
if len(images) > 0:
ax = axes[0]
else:
ax = axes
if color == 1:
img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
zoom = img[gt[1]:gt[3], gt[0]:gt[2]]
ax.imshow(zoom, cmap=pylab.gray(), interpolation='nearest')
kpMask = keypoints[mask]
kpMask[:, 0] = kpMask[:, 0] - gt[0]
kpMask[:, 1] = kpMask[:, 1] - gt[1]
kpMask[:, 7] = kpMask[:, 7] - gt[0]
kpMask[:, 8] = kpMask[:, 8] - gt[1]
ax.plot(kpMask[:, 0], kpMask[:, 1], 'ro')
for k in range(kpMask.shape[0]):
ax.plot([kpMask[k,0], kpMask[k,7]], [kpMask[k,1], kpMask[k,8]], 'r-')
style = 'rx'
if kpMask.shape[1] > 9:
for k in range(3):
maski = kpMask[:, 9] == k + 1
if k == 1:
style = "rv"
if k == 2:
style = "rs"
if k == 4:
style = "bo"
if k == 5:
style = "yo"
ax.plot([kpMask[maski,7]], [kpMask[maski,8]], style)
mask = (keypointsInside[:, 0] > gt[0]) * (keypointsInside[:, 0] < gt[2]) * (keypointsInside[:, 1] > gt[1]) * (keypointsInside[:, 1] < gt[3])
kpMask = keypointsInside[mask]
keypointsInside[:, 0] = keypointsInside[:, 0] - gt[0]
keypointsInside[:, 1] = keypointsInside[:, 1] - gt[1]
keypointsInside[:, 7] = keypointsInside[:, 7] - gt[0]
keypointsInside[:, 8] = keypointsInside[:, 8] - gt[1]
ax.plot(keypointsInside[:, 0], keypointsInside[:, 1], 'go')
for k in range(keypointsInside.shape[0]):
ax.plot([keypointsInside[k,0], keypointsInside[k,7]], [keypointsInside[k,1], keypointsInside[k,8]], 'g-')
ax.set_xlim(0, gt[2] - max(0, gt[0]))
ax.set_ylim((gt[3] - max(0, gt[1]), 0))
line = mlines.Line2D(np.array([gt0[0] - gt[0], gt0[2] - gt[0], gt0[2] - gt[0], gt0[0] - gt[0], gt0[0] - gt[0]]), np.array([gt0[1] - gt[1], gt0[1] - gt[1], gt0[3] - gt[1], gt0[3] - gt[1], gt0[1] - gt[1]]), lw=5., alpha=0.4, color='b')
ax.add_line(line)
f.suptitle('Missing letter: {0} ({1})'.format(gt0[4], miss[0]))
for ai in range(len(images)):
ax = axes[ai + 1]
scale = octScales[ai]
gts = (gt[0] * scale, gt[1] * scale, gt[2] * scale, gt[3] * scale)
ax.plot(octPoints[ai][:, 0] - gts[0], octPoints[ai][:, 1] - gts[1], 'ro')
zoom = images[ai][int(gt[1] * scale):int(gt[3] * scale), int(gt[0] * scale):int(gt[2] * scale)]
ax.imshow(zoom, cmap=pylab.gray(), interpolation='nearest')
ax.set_xlim(0, gts[2] - max(0, gts[0]))
ax.set_ylim((gts[3] - max(0, gts[1]), 0))
plt.show()
