def cleaned2segmented(cleaned, average_size):
vertical_smoothing_threshold = defaults.VERTICAL_SMOOTHING_MULTIPLIER * average_size
horizontal_smoothing_threshold = defaults.HORIZONTAL_SMOOTHING_MULTIPLIER * average_size
(h, w) = cleaned.shape[:2]
if arg.boolean_value('verbose'):
print 'Applying run length smoothing with vertical threshold ' + str(vertical_smoothing_threshold) \
+' and horizontal threshold ' + str(horizontal_smoothing_threshold)
run_length_smoothed = rls.RLSO(cv2.bitwise_not(cleaned),
vertical_smoothing_threshold,
horizontal_smoothing_threshold)
components = cc.get_connected_components(run_length_smoothed)
text = np.zeros((h, w), np.uint8)
#text_columns = np.zeros((h,w),np.uint8)
#text_rows = np.zeros((h,w),np.uint8)
for component in components:
seg_thresh = arg.integer_value('segment_threshold', default_value=1)
(aspect, v_lines,
h_lines) = ocr.segment_into_lines(cv2.bitwise_not(cleaned),
component,
min_segment_threshold=seg_thresh)
if len(v_lines) < 2 and len(h_lines) < 2: continue
ocr.draw_2d_slices(text, [component], color=255, line_size=-1)
#ocr.draw_2d_slices(text_columns,v_lines,color=255,line_size=-1)
#ocr.draw_2d_slices(text_rows,h_lines,color=255,line_size=-1)
return text
def estimate_furigana(img, segmentation):
(w,h)=img.shape[:2]
if arg.boolean_value('verbose'):
print 'Estimateding furigana in ' + str(h) + 'x' + str(w) + ' image.'
text_areas = segmentation
#form binary image from grayscale
binary_threshold = arg.integer_value('binary_threshold',default_value=defaults.BINARY_THRESHOLD)
if arg.boolean_value('verbose'):
print 'binarizing images with threshold value of ' + str(binary_threshold)
binary = clean.binarize(img,threshold=binary_threshold)
binary_average_size = cc.average_size(binary)
if arg.boolean_value('verbose'):
print 'average cc size for binaryized grayscale image is ' + str(binary_average_size)
#apply mask and return images
text_mask = binary_mask(text_areas)
cleaned = cv2.bitwise_not(text_mask*binary)
cleaned_average_size = cc.average_size(cleaned)
if arg.boolean_value('verbose'):
print 'average cc size for cleaned, binaryized grayscale image is ' + str(cleaned_average_size)
columns = scipy.ndimage.filters.gaussian_filter(cleaned,(defaults.FURIGANA_VERTICAL_SIGMA_MULTIPLIER*binary_average_size,defaults.FURIGANA_HORIZONTAL_SIGMA_MULTIPLIER*binary_average_size))
columns = clean.binarize(columns,threshold=defaults.FURIGANA_BINARY_THRESHOLD)
furigana = columns*text_mask
#go through the columns in each text area, and:
#1) Estimate the standard column width (it should be similar to the average connected component width)
#2) Separate out those columns which are significantly thinner (>75%) than the standard width
boxes = cc.get_connected_components(furigana)
furigana_lines = []
non_furigana_lines = []
lines_general = []
for box in boxes:
line_width = cc_width(box)
line_to_left = find_cc_to_left(box, boxes, max_dist=line_width*defaults.FURIGANA_DISTANCE_MULTIPLIER)
if line_to_left is None:
non_furigana_lines.append(box)
continue
left_line_width = cc_width(line_to_left)
if line_width < left_line_width * defaults.FURIGANA_WIDTH_THRESHOLD:
furigana_lines.append(box)
else:
non_furigana_lines.append(box)
furigana_mask = np.zeros(furigana.shape)
for f in furigana_lines:
furigana_mask[f[0].start:f[0].stop,f[1].start:f[1].stop]=255
#furigana_mask[f]=1
furigana = furigana_mask #furigana * furigana_mask
if arg.boolean_value('debug'):
furigana = 0.25*(columns*text_mask) + 0.25*img + 0.5*furigana
return furigana
def filter_text_like_areas(img, segmentation, average_size):
#see if a given rectangular area (2d slice) is very text like
#First step is to estimate furigana like elements so they can be masked
furigana_areas = furigana.estimate_furigana(img, segmentation)
furigana_mask = np.array(furigana_areas == 0, 'B')
#binarize the image, clean it via the segmentation and remove furigana too
binary_threshold = arg.integer_value(
'binary_threshold', default_value=defaults.BINARY_THRESHOLD)
if arg.boolean_value('verbose'):
print 'binarizing images with threshold value of ' + str(
binary_threshold)
binary = clean.binarize(img, threshold=binary_threshold)
binary_average_size = cc.average_size(binary)
if arg.boolean_value('verbose'):
print 'average cc size for binaryized grayscale image is ' + str(
binary_average_size)
segmentation_mask = np.array(segmentation != 0, 'B')
cleaned = binary * segmentation_mask * furigana_mask
inv_cleaned = cv2.bitwise_not(cleaned)
areas = cc.get_connected_components(segmentation)
text_like_areas = []
nontext_like_areas = []
for area in areas:
#if area_is_text_like(cleaned, area, average_size):
if text_like_histogram(cleaned, area, average_size):
text_like_areas.append(area)
else:
nontext_like_areas.append(area)
return (text_like_areas, nontext_like_areas)
def clean_page(img, max_scale=defaults.CC_SCALE_MAX, min_scale=defaults.CC_SCALE_MIN):
#img = cv2.imread(sys.argv[1])
(h,w,d)=img.shape
gray = grayscale(img)
#create gaussian filtered and unfiltered binary images
sigma = arg.float_value('sigma',default_value=defaults.GAUSSIAN_FILTER_SIGMA)
if arg.boolean_value('verbose'):
print 'Binarizing image with sigma value of ' + str(sigma)
gaussian_filtered = scipy.ndimage.gaussian_filter(gray, sigma=sigma)
binary_threshold = arg.integer_value('binary_threshold',default_value=defaults.BINARY_THRESHOLD)
if arg.boolean_value('verbose'):
print 'Binarizing image with sigma value of ' + str(sigma)
gaussian_binary = binarize(gaussian_filtered, threshold=binary_threshold)
binary = binarize(gray, threshold=binary_threshold)
#Draw out statistics on average connected component size in the rescaled, binary image
average_size = cc.average_size(gaussian_binary)
#print 'Initial mask average size is ' + str(average_size)
max_size = average_size*max_scale
min_size = average_size*min_scale
#primary mask is connected components filtered by size
mask = cc.form_mask(gaussian_binary, max_size, min_size)
#secondary mask is formed from canny edges
canny_mask = form_canny_mask(gaussian_filtered, mask=mask)
#final mask is size filtered connected components on canny mask
final_mask = cc.form_mask(canny_mask, max_size, min_size)
#apply mask and return images
cleaned = cv2.bitwise_not(final_mask * binary)
return (cv2.bitwise_not(binary), final_mask, cleaned)
def clean_page(img, max_scale=defaults.CC_SCALE_MAX, min_scale=defaults.CC_SCALE_MIN):
#img = cv2.imread(sys.argv[1])
(h,w,d)=img.shape
gray = grayscale(img)
#create gaussian filtered and unfiltered binary images
sigma = arg.float_value('sigma',default_value=defaults.GAUSSIAN_FILTER_SIGMA)
if arg.boolean_value('verbose'):
print 'Binarizing image with sigma value of ' + str(sigma)
gaussian_filtered = scipy.ndimage.gaussian_filter(gray, sigma=sigma)
binary_threshold = arg.integer_value('binary_threshold',default_value=defaults.BINARY_THRESHOLD)
if arg.boolean_value('verbose'):
print 'Binarizing image with sigma value of ' + str(sigma)
gaussian_binary = binarize(gaussian_filtered, threshold=binary_threshold)
binary = binarize(gray, threshold=binary_threshold)
#Draw out statistics on average connected component size in the rescaled, binary image
average_size = cc.average_size(gaussian_binary)
#print 'Initial mask average size is ' + str(average_size)
max_size = average_size*max_scale
min_size = average_size*min_scale
#primary mask is connected components filtered by size
mask = cc.form_mask(gaussian_binary, max_size, min_size)
#secondary mask is formed from canny edges
canny_mask = form_canny_mask(gaussian_filtered, mask=mask)
#final mask is size filtered connected components on canny mask
final_mask = cc.form_mask(canny_mask, max_size, min_size)
#apply mask and return images
cleaned = cv2.bitwise_not(final_mask * binary)
return (cv2.bitwise_not(binary), final_mask, cleaned)
def estimate_furigana(img, segmentation):
(w,h)=img.shape[:2]
if arg.boolean_value('verbose'):
print('Estimateding furigana in ' + str(h) + 'x' + str(w) + ' image.')
text_areas = segmentation
#form binary image from grayscale
binary_threshold = arg.integer_value('binary_threshold',default_value=defaults.BINARY_THRESHOLD)
if arg.boolean_value('verbose'):
print('binarizing images with threshold value of ' + str(binary_threshold))
binary = clean.binarize(img,threshold=binary_threshold)
binary_average_size = cc.average_size(binary)
if arg.boolean_value('verbose'):
print('average cc size for binaryized grayscale image is ' + str(binary_average_size))
#apply mask and return images
text_mask = binary_mask(text_areas)
cleaned = cv2.bitwise_not(text_mask*binary)
cleaned_average_size = cc.average_size(cleaned)
if arg.boolean_value('verbose'):
print('average cc size for cleaned, binaryized grayscale image is ' + str(cleaned_average_size))
columns = scipy.ndimage.filters.gaussian_filter(cleaned,(defaults.FURIGANA_VERTICAL_SIGMA_MULTIPLIER*binary_average_size,defaults.FURIGANA_HORIZONTAL_SIGMA_MULTIPLIER*binary_average_size))
columns = clean.binarize(columns,threshold=defaults.FURIGANA_BINARY_THRESHOLD)
furigana = columns*text_mask
#go through the columns in each text area, and:
#1) Estimate the standard column width (it should be similar to the average connected component width)
#2) Separate out those columns which are significantly thinner (>75%) than the standard width
boxes = cc.get_connected_components(furigana)
furigana_lines = []
non_furigana_lines = []
lines_general = []
for box in boxes:
line_width = cc_width(box)
line_to_left = find_cc_to_left(box, boxes, max_dist=line_width*defaults.FURIGANA_DISTANCE_MULTIPLIER)
if line_to_left is None:
non_furigana_lines.append(box)
continue
left_line_width = cc_width(line_to_left)
if line_width < left_line_width * defaults.FURIGANA_WIDTH_THRESHOLD:
furigana_lines.append(box)
else:
non_furigana_lines.append(box)
furigana_mask = np.zeros(furigana.shape)
for f in furigana_lines:
furigana_mask[f[0].start:f[0].stop,f[1].start:f[1].stop]=255
#furigana_mask[f]=1
furigana = furigana_mask #furigana * furigana_mask
if arg.boolean_value('debug'):
furigana = 0.25*(columns*text_mask) + 0.25*img + 0.5*furigana
return furigana
def filter_text_like_areas(img, segmentation, average_size):
#see if a given rectangular area (2d slice) is very text like
#First step is to estimate furigana like elements so they can be masked
furigana_areas = furigana.estimate_furigana(img, segmentation)
furigana_mask = np.array(furigana_areas==0,'B')
#binarize the image, clean it via the segmentation and remove furigana too
binary_threshold = arg.integer_value('binary_threshold',default_value=defaults.BINARY_THRESHOLD)
if arg.boolean_value('verbose'):
print 'binarizing images with threshold value of ' + str(binary_threshold)
binary = clean.binarize(img,threshold=binary_threshold)
binary_average_size = cc.average_size(binary)
if arg.boolean_value('verbose'):
print 'average cc size for binaryized grayscale image is ' + str(binary_average_size)
segmentation_mask = np.array(segmentation!=0,'B')
cleaned = binary * segmentation_mask * furigana_mask
inv_cleaned = cv2.bitwise_not(cleaned)
areas = cc.get_connected_components(segmentation)
text_like_areas = []
nontext_like_areas = []
for area in areas:
#if area_is_text_like(cleaned, area, average_size):
if text_like_histogram(cleaned, area, average_size):
text_like_areas.append(area)
else:
nontext_like_areas.append(area)
return (text_like_areas, nontext_like_areas)
def cleaned2segmented(cleaned, average_size):
"cleaned是已经把图像中的字细化了"
vertical_smoothing_threshold = defaults.VERTICAL_SMOOTHING_MULTIPLIER*average_size
horizontal_smoothing_threshold = defaults.HORIZONTAL_SMOOTHING_MULTIPLIER*average_size
(h,w) = cleaned.shape[:2]
if arg.boolean_value('verbose'):
print 'Applying run length smoothing with vertical threshold ' + str(vertical_smoothing_threshold) \
+' and horizontal threshold ' + str(horizontal_smoothing_threshold)
run_length_smoothed = rls.RLSO( cv2.bitwise_not(cleaned), vertical_smoothing_threshold, horizontal_smoothing_threshold)
components = cc.get_connected_components(run_length_smoothed)
text = np.zeros((h,w),np.uint8)
#text_columns = np.zeros((h,w),np.uint8)
#text_rows = np.zeros((h,w),np.uint8)
for component in components:
seg_thresh = arg.integer_value('segment_threshold',default_value=1)
(aspect, v_lines, h_lines) = ocr.segment_into_lines(cv2.bitwise_not(cleaned), component,min_segment_threshold=seg_thresh)
if len(v_lines)<2 and len(h_lines)<2:continue
ocr.draw_2d_slices(text,[component],color=255,line_size=-1)
#ocr.draw_2d_slices(text_columns,v_lines,color=255,line_size=-1)
#ocr.draw_2d_slices(text_rows,h_lines,color=255,line_size=-1)
return text
action="store_true")
arg.value = parser.parse_args()
infile = arg.string_value('infile')
outfile = arg.string_value('outfile',
default_value=infile + '.text_areas.png')
if not os.path.isfile(infile):
print(
'Please provide a regular existing input file. Use -h option for help.'
)
sys.exit(-1)
img = cv2.imread(infile)
gray = clean.grayscale(img)
binary_threshold = arg.integer_value(
'binary_threshold', default_value=defaults.BINARY_THRESHOLD)
if arg.boolean_value('verbose'):
print('Binarizing with threshold value of ' + str(binary_threshold))
inv_binary = cv2.bitwise_not(
clean.binarize(gray, threshold=binary_threshold))
binary = clean.binarize(gray, threshold=binary_threshold)
segmented_image = seg.segment_image(gray)
segmented_image = segmented_image[:, :, 2]
components = cc.get_connected_components(segmented_image)
cc.draw_bounding_boxes(img, components, color=(255, 0, 0), line_size=2)
imsave(outfile, img)
if arg.boolean_value('display'):
cv2.imshow('segmented_image', segmented_image)
def segment_image(img,
max_scale=defaults.CC_SCALE_MAX,
min_scale=defaults.CC_SCALE_MIN):
(h, w) = img.shape[:2]
if arg.boolean_value('verbose'):
print 'Segmenting ' + str(h) + 'x' + str(w) + ' image.'
#create gaussian filtered and unfiltered binary images
binary_threshold = arg.integer_value(
'binary_threshold', default_value=defaults.BINARY_THRESHOLD)
if arg.boolean_value('verbose'):
print 'binarizing images with threshold value of ' + str(
binary_threshold)
binary = clean.binarize(img, threshold=binary_threshold)
binary_average_size = cc.average_size(binary)
if arg.boolean_value('verbose'):
print 'average cc size for binaryized grayscale image is ' + str(
binary_average_size)
'''
The necessary sigma needed for Gaussian filtering (to remove screentones and other noise) seems
to be a function of the resolution the manga was scanned at (or original page size, I'm not sure).
Assuming 'normal' page size for a phonebook style Manga is 17.5cmx11.5cm (6.8x4.5in).
A scan of 300dpi will result in an image about 1900x1350, which requires a sigma of 1.5 to 1.8.
I'm encountering many smaller images that may be nonstandard scanning dpi values or just smaller
magazines. Haven't found hard info on this yet. They require sigma values of about 0.5 to 0.7.
I'll therefore (for now) just calculate required (nonspecified) sigma as a linear function of vertical
image resolution.
'''
sigma = (0.8 / 676.0) * float(h) - 0.9
sigma = arg.float_value('sigma', default_value=sigma)
if arg.boolean_value('verbose'):
print 'Applying Gaussian filter with sigma (std dev) of ' + str(sigma)
gaussian_filtered = scipy.ndimage.gaussian_filter(img, sigma=sigma)
gaussian_binary = clean.binarize(gaussian_filtered,
threshold=binary_threshold)
#Draw out statistics on average connected component size in the rescaled, binary image
average_size = cc.average_size(gaussian_binary)
if arg.boolean_value('verbose'):
print 'Binarized Gaussian filtered image average cc size: ' + str(
average_size)
max_size = average_size * max_scale
min_size = average_size * min_scale
#primary mask is connected components filtered by size
mask = cc.form_mask(gaussian_binary, max_size, min_size)
#secondary mask is formed from canny edges
canny_mask = clean.form_canny_mask(gaussian_filtered, mask=mask)
#final mask is size filtered connected components on canny mask
final_mask = cc.form_mask(canny_mask, max_size, min_size)
#apply mask and return images
cleaned = cv2.bitwise_not(final_mask * binary)
text_only = cleaned2segmented(cleaned, average_size)
#if desired, suppress furigana characters (which interfere with OCR)
suppress_furigana = arg.boolean_value('furigana')
if suppress_furigana:
if arg.boolean_value('verbose'):
print 'Attempting to suppress furigana characters which interfere with OCR.'
furigana_mask = furigana.estimate_furigana(cleaned, text_only)
furigana_mask = np.array(furigana_mask == 0, 'B')
cleaned = cv2.bitwise_not(cleaned) * furigana_mask
cleaned = cv2.bitwise_not(cleaned)
text_only = cleaned2segmented(cleaned, average_size)
(text_like_areas,
nontext_like_areas) = filter_text_like_areas(img,
segmentation=text_only,
average_size=average_size)
if arg.boolean_value('verbose'):
print '**********there are ' + str(
len(text_like_areas)) + ' text like areas total.'
text_only = np.zeros(img.shape)
cc.draw_bounding_boxes(text_only,
text_like_areas,
color=(255),
line_size=-1)
if arg.boolean_value('debug'):
text_only = 0.5 * text_only + 0.5 * img
#text_rows = 0.5*text_rows+0.5*gray
#text_colums = 0.5*text_columns+0.5*gray
#text_only = filter_text_like_areas(img, segmentation=text_only, average_size=average_size)
segmented_image = np.zeros((h, w, 3), np.uint8)
segmented_image[:, :, 0] = img
segmented_image[:, :, 1] = text_only
segmented_image[:, :, 2] = text_only
return segmented_image
#outfile = arg.string_value('outfile',default_value=infile + '.text_areas.png')
if not os.path.isfile(infile):
print 'Please provide a regular existing input file. Use -h option for help.'
sys.exit(-1)
img = cv2.imread(infile)
cv2.imshow('srcimg', img)
gray = clean.grayscale(img)
binary_threshold = arg.integer_value('binary_threshold', default_value=defaults.BINARY_THRESHOLD)
if arg.boolean_value('verbose'):
print 'Binarizing with threshold value of ' + str(binary_threshold)
inv_binary = cv2.bitwise_not(clean.binarize(gray, threshold=binary_threshold))
#cv2.imshow('inv_binary', inv_binary)
binary = clean.binarize(gray, threshold=binary_threshold)
#cv2.imshow('binary', binary)
segmented_image = seg.segment_image(gray)
cv2.imshow('segmented_image', segmented_image)
def segment_image(img, max_scale=defaults.CC_SCALE_MAX, min_scale=defaults.CC_SCALE_MIN):
(h,w)=img.shape[:2]
if arg.boolean_value('verbose'):
print 'Segmenting ' + str(h) + 'x' + str(w) + ' image.'
#create gaussian filtered and unfiltered binary images
binary_threshold = arg.integer_value('binary_threshold',default_value=defaults.BINARY_THRESHOLD)
if arg.boolean_value('verbose'):
print 'binarizing images with threshold value of ' + str(binary_threshold)
binary = clean.binarize(img,threshold=binary_threshold)
binary_average_size = cc.average_size(binary)
if arg.boolean_value('verbose'):
print 'average cc size for binaryized grayscale image is ' + str(binary_average_size)
'''
The necessary sigma needed for Gaussian filtering (to remove screentones and other noise) seems
to be a function of the resolution the manga was scanned at (or original page size, I'm not sure).
Assuming 'normal' page size for a phonebook style Manga is 17.5cmx11.5cm (6.8x4.5in).
A scan of 300dpi will result in an image about 1900x1350, which requires a sigma of 1.5 to 1.8.
I'm encountering many smaller images that may be nonstandard scanning dpi values or just smaller
magazines. Haven't found hard info on this yet. They require sigma values of about 0.5 to 0.7.
I'll therefore (for now) just calculate required (nonspecified) sigma as a linear function of vertical
image resolution.
'''
sigma = (0.8/676.0)*float(h)-0.9
sigma = arg.float_value('sigma',default_value=sigma)
if arg.boolean_value('verbose'):
print 'Applying Gaussian filter with sigma (std dev) of ' + str(sigma)
gaussian_filtered = scipy.ndimage.gaussian_filter(img, sigma=sigma)
gaussian_binary = clean.binarize(gaussian_filtered,threshold=binary_threshold)
#Draw out statistics on average connected component size in the rescaled, binary image
average_size = cc.average_size(gaussian_binary)
if arg.boolean_value('verbose'):
print 'Binarized Gaussian filtered image average cc size: ' + str(average_size)
max_size = average_size*max_scale
min_size = average_size*min_scale
#primary mask is connected components filtered by size
mask = cc.form_mask(gaussian_binary, max_size, min_size)
#secondary mask is formed from canny edges
canny_mask = clean.form_canny_mask(gaussian_filtered, mask=mask)
#final mask is size filtered connected components on canny mask
final_mask = cc.form_mask(canny_mask, max_size, min_size)
#apply mask and return images
cleaned = cv2.bitwise_not(final_mask * binary)
text_only = cleaned2segmented(cleaned, average_size)
#if desired, suppress furigana characters (which interfere with OCR)
suppress_furigana = arg.boolean_value('furigana')
if suppress_furigana:
if arg.boolean_value('verbose'):
print 'Attempting to suppress furigana characters which interfere with OCR.'
furigana_mask = furigana.estimate_furigana(cleaned, text_only)
furigana_mask = np.array(furigana_mask==0,'B')
cleaned = cv2.bitwise_not(cleaned)*furigana_mask
cleaned = cv2.bitwise_not(cleaned)
text_only = cleaned2segmented(cleaned, average_size)
(text_like_areas, nontext_like_areas) = filter_text_like_areas(img, segmentation=text_only, average_size=average_size)
if arg.boolean_value('verbose'):
print '**********there are ' + str(len(text_like_areas)) + ' text like areas total.'
text_only = np.zeros(img.shape)
cc.draw_bounding_boxes(text_only, text_like_areas,color=(255),line_size=-1)
if arg.boolean_value('debug'):
text_only = 0.5*text_only + 0.5*img
#text_rows = 0.5*text_rows+0.5*gray
#text_colums = 0.5*text_columns+0.5*gray
#text_only = filter_text_like_areas(img, segmentation=text_only, average_size=average_size)
segmented_image = np.zeros((h,w,3), np.uint8)
segmented_image[:,:,0] = img
segmented_image[:,:,1] = text_only
segmented_image[:,:,2] = text_only
return segmented_image