def test_interactive_classifier():
# We assume the XML reading/writing itself is fine (given
# test_xml), but we should test the wrappers in classify anyway
image = load_image("data/testline.png")
ccs = image.cc_analysis()
classifier = knn.kNNInteractive([],features=featureset)
assert classifier.is_interactive()
assert len(classifier.get_glyphs()) == 0
classifier.from_xml_filename("data/testline.xml")
assert len(classifier.get_glyphs()) == 66
_test_classification(classifier, ccs)
_test_training(classifier, ccs)
length = len(classifier.get_glyphs())
# subtract len(group_parts) because to_xml_filename() does
# not save "_group._part"
group_parts = [x for x in classifier.get_glyphs()
if x.get_main_id().startswith("_group._part")]
length = length - len(group_parts)
classifier.to_xml_filename("tmp/testline_classifier.xml")
classifier.from_xml_filename("tmp/testline_classifier.xml")
assert len(classifier.get_glyphs()) == length
classifier.merge_from_xml_filename("data/testline.xml")
assert len(classifier.get_glyphs()) == length + 66
classifier.clear_glyphs()
assert len(classifier.get_glyphs()) == 0
classifier.from_xml_filename("data/testline.xml")
assert len(classifier.get_glyphs()) == 66
def glyph_classification(self):
""" Glyph classification.
Returns a list of the classified glyphs with its position and size.
"""
cknn = knn.kNNInteractive([],
["area",
"aspect_ratio",
"black_area",
"compactness",
"moments",
"ncols_feature",
"nholes",
"nholes_extended",
"nrows_feature",
"skeleton_features",
"top_bottom",
"volume",
"volume16regions",
"volume64regions",
"zernike_moments"],
True,
8)
cknn.from_xml_filename(self.classifier_glyphs)
cknn.load_settings(self.classifier_weights) # Option for loading the features and weights of the training stage.
ccs = self.img_no_st.cc_analysis()
grouping_function = classify.ShapedGroupingFunction(16) # variable ?
self.classified_image = cknn.group_and_update_list_automatic(ccs, grouping_function, max_parts_per_group = 4) # variable ?
def make_spanning_tree(glyphs, k=None):
if k is None:
k = knn.kNNInteractive()
uniq_dists = k.distance_matrix(glyphs, 0)
g = graph.Undirected()
g.create_minimum_spanning_tree(glyphs, uniq_dists)
return g
def test_interactive_classifier():
# We assume the XML reading/writing itself is fine (given
# test_xml), but we should test the wrappers in classify anyway
image = load_image("data/testline.png")
ccs = image.cc_analysis()
classifier = knn.kNNInteractive([], features=featureset)
assert classifier.is_interactive()
assert len(classifier.get_glyphs()) == 0
classifier.from_xml_filename("data/testline.xml")
assert len(classifier.get_glyphs()) == 66
_test_classification(classifier, ccs)
_test_training(classifier, ccs)
length = len(classifier.get_glyphs())
# subtract len(group_parts) because to_xml_filename() does
# not save "_group._part"
group_parts = [
x for x in classifier.get_glyphs()
if x.get_main_id().startswith("_group._part")
]
length = length - len(group_parts)
classifier.to_xml_filename("tmp/testline_classifier.xml")
classifier.from_xml_filename("tmp/testline_classifier.xml")
assert len(classifier.get_glyphs()) == length
classifier.merge_from_xml_filename("data/testline.xml")
assert len(classifier.get_glyphs()) == length + 66
classifier.clear_glyphs()
assert len(classifier.get_glyphs()) == 0
classifier.from_xml_filename("data/testline.xml")
assert len(classifier.get_glyphs()) == 66
def init_classifier(self,filename=None,features=["volume64regions"]):
self.l.debug("features=%s, filename=%s",features,filename)
self.classifier=knn.kNNInteractive([],features, 0)
self.classifier.num_k = self.k
if not filename is None:
self.load_new_training_data(filename)
else:
self.invalidate_images()
def init_classifier(self, filename=None, features=["volume64regions"]):
self.l.debug("features=%s, filename=%s", features, filename)
self.classifier = knn.kNNInteractive([], features, 0)
self.classifier.num_k = self.k
if not filename is None:
self.load_new_training_data(filename)
else:
self.invalidate_images()
def gui_show_remove_lyrics(self):
""" GUI function: Deletes the lyrics out of an image. When a trainfile is given, the lyrics are removed by the trained based method. Otherwise the rule based method is used. """
if has_gui.has_gui:
dialog=Args([FileOpen("Trainfile (optional)", "", "*.*")],\
"Lyrics removal")
params=dialog.show()
if params[0] != None:
filename=params[0]
#
# create a classifier and load the database
#
#print "Classify"
ccs=self.fullimage.cc_analysis()
classifier=knn.kNNInteractive([], [\
'aspect_ratio',\
'moments',\
'nrows_feature',\
'volume64regions',\
], 0)
classifier.num_k = 1
classifier.from_xml_filename(filename)
#
# classify the connected components of the image, use half of oligon_height
# height to decide about grouped glyphs
#
grp_distance = max([self.oligon_height/2,4])
#grp_distance=4
added, removed=classifier.group_list_automatic(ccs,\
BoundingBoxGroupingFunction(grp_distance),max_parts_per_group=2)
#
# process groups detected by gamera's grouping algorithm
# and remove group.parts and trash
#
ccs=[x for x in ccs if \
(not x.match_id_name("_group._part.*")) and \
(not x.match_id_name("*trash*"))]
if len(added)>0:
ccs.extend(added)
self.remove_lyrics(ccs,debug=0)
else:
self.remove_lyrics()
def __bar_candidate_grouping(ungrouped_bars):
"""
Groups bar candidates
"""
for bar in ungrouped_bars:
bar.classify_heuristic('_group._part.bc')
cknn = knn.kNNInteractive()
cknn.set_glyphs(ungrouped_bars)
grouped_bars = cknn.group_and_update_list_automatic(ungrouped_bars,
max_parts_per_group=10,
grouping_function=BoundingBoxGroupingFunction(5000)) # Threshold distance in pixels between bounding boxes
return grouped_bars
def ShowClassifier(classifier=None, current_database=[],
image=None, symbol_table=[]):
if classifier is None:
from gamera import knn
classifier = knn.kNNInteractive()
wx.BeginBusyCursor()
try:
class_disp = classifier_display.ClassifierFrame(classifier, symbol_table)
class_disp.set_image(current_database, image)
class_disp.Show(1)
finally:
wx.EndBusyCursor()
return class_disp
def ShowClassifier(classifier=None, current_database=[],
image=None, symbol_table=[]):
if classifier is None:
from gamera import knn
classifier = knn.kNNInteractive()
wx.BeginBusyCursor()
try:
class_disp = classifier_display.ClassifierFrame(classifier, symbol_table)
class_disp.set_image(current_database, image)
class_disp.Show(1)
finally:
wx.EndBusyCursor()
return class_disp
def __init__(self, mode="wholistic", splits=0, feats=["aspect_ratio", "volume64regions", "moments", "nholes_extended"], hocr=None):
"""Signature:
``init (mode="wholistic")``
where *mode* can be "wholistic" or "separatistic".
"""
self.optimizeknn = False
self.debug = False
self.cknn = knn.kNNInteractive([], feats, splits)
self.autogroup = False
self.output = ""
self.mode = mode
self.hocr = hocr
def __bar_candidate_grouping(ungrouped_bars):
"""
Groups bar candidates
"""
for bar in ungrouped_bars:
bar.classify_heuristic('_group._part.bc')
cknn = knn.kNNInteractive()
cknn.set_glyphs(ungrouped_bars)
grouped_bars = cknn.group_and_update_list_automatic(
ungrouped_bars,
max_parts_per_group=10,
grouping_function=BoundingBoxGroupingFunction(5000)
) # Threshold distance in pixels between bounding boxes
return grouped_bars
def _copyClassifier(original, k=0):
"""Copy a given kNNClassifer by constructing a new one with identical
parameters.
*original*
The classifier to be copied
*k*
If the copy shall have another k-value as the original, set k accordingly.
k = 0 means, that the original's k-value will be used"""
if k == 0:
k = original.num_k
return kNNInteractive(list(original.get_glyphs()), original.features,
original._perform_splits, k)
def _copyClassifier(original, k = 0):
"""Copy a given kNNClassifer by constructing a new one with identical
parameters.
*original*
The classifier to be copied
*k*
If the copy shall have another k-value as the original, set k accordingly.
k = 0 means, that the original's k-value will be used"""
if k == 0:
k = original.num_k
return kNNInteractive(
list(original.get_glyphs()), original.features,
original._perform_splits,
k)
def __call__(self, classifier, k=0, randomize=True):
# special case of empty classifier
if (not classifier.get_glyphs()):
return _copyClassifier(classifier)
if k == 0:
k = classifier.num_k
progress = ProgressFactory("Generating edited CNN classifier...",
len(classifier.get_glyphs()))
# initialize Store (a) with a single element
if randomize:
elem = _randomSetElement(classifier.get_glyphs())
else:
elem = classifier.get_glyphs().__iter__().next()
aGlyphs = [elem]
a = kNNInteractive(aGlyphs, classifier.features,
classifier._perform_splits, k)
progress.step()
# initialize Grabbag (b) with all other
b = classifier.get_glyphs().copy()
b.remove(aGlyphs[0])
# Classify each glyph in b with a as the classifier
# If glyph is misclassified, add it to a, repeat until no elements are
# added to a
changed = True
while changed == True:
changed = False
# copy needed because iteration through dict is not possible while
# deleting items from it
copyOfB = b.copy()
for glyph in copyOfB:
if glyph.get_main_id() != _getMainId(
a.guess_glyph_automatic(glyph)):
b.remove(glyph)
a.get_glyphs().add(glyph)
progress.step()
changed = True
progress.kill()
a.num_k = 1
return a
def __call__(self, classifier, k = 0, randomize = True):
# special case of empty classifier
if (not classifier.get_glyphs()):
return _copyClassifier(classifier)
if k == 0:
k = classifier.num_k
progress = ProgressFactory("Generating edited CNN classifier...",
len(classifier.get_glyphs()))
# initialize Store (a) with a single element
if randomize:
elem = _randomSetElement(classifier.get_glyphs())
else:
elem = classifier.get_glyphs().__iter__().next()
aGlyphs = [elem]
a = kNNInteractive(aGlyphs, classifier.features,
classifier._perform_splits, k)
progress.step()
# initialize Grabbag (b) with all other
b = classifier.get_glyphs().copy()
b.remove(aGlyphs[0]);
# Classify each glyph in b with a as the classifier
# If glyph is misclassified, add it to a, repeat until no elements are
# added to a
changed = True
while changed == True:
changed = False
# copy needed because iteration through dict is not possible while
# deleting items from it
copyOfB = b.copy()
for glyph in copyOfB:
if glyph.get_main_id() != _getMainId(a.guess_glyph_automatic(glyph)):
b.remove(glyph)
a.get_glyphs().add(glyph)
progress.step()
changed = True
progress.kill()
a.num_k = 1
return a
def glyph_classification(self):
""" Glyph classification.
Returns a list of the classified glyphs with its position and size.
"""
cknn = knn.kNNInteractive([], [
"area", "aspect_ratio", "black_area", "compactness", "moments",
"ncols_feature", "nholes", "nholes_extended", "nrows_feature",
"skeleton_features", "top_bottom", "volume", "volume16regions",
"volume64regions", "zernike_moments"
], True, 8)
cknn.from_xml_filename(self.classifier_glyphs)
cknn.load_settings(
self.classifier_weights
) # Option for loading the features and weights of the training stage.
ccs = self.img_no_st.cc_analysis()
grouping_function = classify.ShapedGroupingFunction(16) # variable ?
self.classified_image = cknn.group_and_update_list_automatic(
ccs, grouping_function, max_parts_per_group=4) # variable ?
from gamera.config import config
from gamera import gamera_xml
from gamera import knn
init_gamera()
config.set("progress_bar",True)
infile=sys.argv[1]
outfile=sys.argv[2]
time_factor=sys.argv[3]
iknn=knn.kNNInteractive([],['aspect_ratio','moments', 'nrows_feature','ncols_feature', 'volume64regions'],0)
iknn.num_k = 3
iknn.from_xml_filename(infile)
nknn = iknn.noninteractive_copy()
def hello():
global nknn
global outfile
global infile
nknn.stop_optimizing()
print "OPT", infile, "GA initial", nknn.ga_initial,"GA best", nknn.ga_best, "GA generation", nknn.ga_generation
nknn.save_settings(outfile)
nknn.start_optimizing()
from gamera.toolkits.aruspix.ax_file import *
axfile = ""
group = 0
# start options dialog
dialog = Args(
[FileOpen("Aruspix file", axfile, "*.axz"), Choice("group", ["Group", "No group"])], name="Select the file"
)
params = dialog.show()
if params is not None and params[0]:
# map parameters
i = 0
axfile = params[i]
i += 1
group = params[i]
i += 1
f = AxFile(axfile, "")
gl = []
if group == 1:
gl = gamera_xml.glyphs_from_xml(f.tmpdirname + "gamera_page_no_group.xml")
else:
gl = gamera_xml.glyphs_from_xml(f.tmpdirname + "gamera_page_group.xml")
image = load_image(f.tmpdirname + "img2.tif")
classifier = knn.kNNInteractive()
classifier.display(gl, image)
ccs=image.cc_analysis() pspage=PsaltikiPage(image) if opt.trainfile!="": # # create a classifier and load the database # #print "Classify" if opt.weightfile=="": classifier=knn.kNNInteractive([], [\ 'aspect_ratio',\ 'moments',\ 'nrows_feature',\ 'volume64regions',\ ], 0) classifier.num_k = opt.num_k classifier.from_xml_filename(opt.trainfile) else: classifier=knn.kNNInteractive([],"all") classifier.num_k=opt.num_k classifier.from_xml_filename(opt.trainfile) classifier.load_settings(opt.weightfile) # # classify the connected components of the image, use half of oligon_height # height to decide about grouped glyphs #
# return 'C'
elif glyph == 'punctum' and kind == 'dot':
return 'U'
for n in neume_down: ### Then, all the other neumes
if glyph == n:
return 'D'
for n in neume_up:
if glyph == n:
return 'U'
return
print 'CLASSIFYING'
cknn = knn.kNNInteractive([], ["area", "aspect_ratio", "black_area", "compactness", "moments", "ncols_feature", "nholes", "nholes_extended", "nrows_feature", "skeleton_features", "top_bottom", "volume", "volume16regions", "volume64regions", "zernike_moments"], 8) #int k 8
cknn.from_xml_filename('/Users/gabriel/Documents/imgs/pdf_to_tiff_conversion/IMG_test/Liber_Usualis/_classifier_training/154_corrected/classifier_glyphs.xml') #154
cknn.load_settings('/Users/gabriel/Documents/imgs/pdf_to_tiff_conversion/IMG_test/Liber_Usualis/_classifier_training/177_corr/GA_opt_1.xml')
print 'FEATURES'
ccs = image_no_st.cc_analysis()
grouping_function = classify.ShapedGroupingFunction(16) # maximum solveable subgraph size 16
class_im = cknn.group_and_update_list_automatic(ccs, grouping_function, max_parts_per_group = 4) # 8
for c in class_im:
#print c.get_main_id()
staff_number = ''
uod = ''
staff_number = '' # Comment for have the non-neumes in position
line_number = ''
del cc
count = count + 1
print "filter done.",len(ccs)-count,"elements left."
if(opt.deskew):
#from gamera.toolkits.otr.otr_staff import *
if opt.verbosity > 0:
print "\ntry to skew correct..."
rotation = img.rotation_angle_projections(-10,10)[0]
img = img.rotate(rotation,0)
if opt.verbosity > 0:
print "rotated with",rotation,"angle"
if(opt.auto_group):
cknn = knn.kNNInteractive([], ["aspect_ratio", "volume64regions", "moments", "nholes_extended"], 0)
cknn.from_xml_filename(opt.trainfile)
if(opt.ccsfilter):
the_ccs = ccs
else:
the_ccs = img.cc_analysis()
median_cc = int(median([cc.nrows for cc in the_ccs]))
autogroup = ClassifyCCs(cknn)
autogroup.parts_to_group = 3
autogroup.grouping_distance = max([2,median_cc / 8])
p = Page(img, classify_ccs=autogroup)
if opt.verbosity > 0:
print "autogrouping glyphs activated."
print "maximal autogroup distance:", autogroup.grouping_distance
else:
p = Page(img)
del cc
count = count + 1
print "filter done.", len(ccs) - count, "elements left."
if (opt.deskew):
#from gamera.toolkits.otr.otr_staff import *
if opt.verbosity > 0:
print "\ntry to skew correct..."
rotation = img.rotation_angle_projections(-10, 10)[0]
img = img.rotate(rotation, 0)
if opt.verbosity > 0:
print "rotated with", rotation, "angle"
if (opt.auto_group):
cknn = knn.kNNInteractive(
[], ["aspect_ratio", "volume64regions", "moments", "nholes_extended"],
0)
cknn.from_xml_filename(opt.trainfile)
if (opt.ccsfilter):
the_ccs = ccs
else:
the_ccs = img.cc_analysis()
median_cc = int(median([cc.nrows for cc in the_ccs]))
autogroup = ClassifyCCs(cknn)
autogroup.parts_to_group = 3
autogroup.grouping_distance = max([2, median_cc / 8])
p = Page(img, classify_ccs=autogroup)
if opt.verbosity > 0:
print "autogrouping glyphs activated."
print "maximal autogroup distance:", autogroup.grouping_distance
else:
from gamera.knn import kNNInteractive
classifier = kNNInteractive()
classifier.from_xml_filename("preomr.xml")
