def OnChangeFeatures(self, event):
#---------------------------------------------------------------------------
from gamera import plugin
from gamera.core import ONEBIT
from gamera.core import ImageBase
from gamera.args import Args, Check
if self.classifier is None:
gui.message("No classifier loaded")
return
allFeatures = [x[0] for x in plugin.methods_flat_category("Features", ONEBIT)]
allFeatures.sort()
existingFeatures = [x[0] for x in ImageBase.get_feature_functions(self.classifier.features)[0]]
featureControls = []
for f in allFeatures:
featureControls.append(Check('', f, default=(f in existingFeatures)))
dialog = Args(featureControls, name = "Feature selection",
title="Select the features you want to use for optimization")
result = dialog.show(self)
if result is None:
gui_util.message("No change applied")
return
selectedFeatures = [name for check, name in zip(result, allFeatures) if check]
self.classifier.change_feature_set(selectedFeatures)
self.UpdatePanels()
def save_image(image, filename):
"""**save_image** (Image(ALL) *image*, String *filename*)
Saves an image to a file. The file type is automatically
determined from the extension.
"""
from gamera import plugin
methods = plugin.methods_flat_category("File")
methods = [y for x, y in methods if x.startswith("save") and x != "save_image"]
if len(methods) == 0:
raise RuntimeError(
"There don't seem to be any imported plugins that can save files. Try running init_gamera(), or explicitly loading the plugins that support file saving, such as tiff_support and png_support."
)
for method in methods:
for ext in method.exts:
if os.path.splitext(filename)[1][1:].lower() == ext.lower():
method.__call__(image, filename)
return
# For backward compatibility, fall back to tiff if
# we can't automatically determine the filetype by
# the extension
from gamera.plugins import _tiff_support
_tiff_support.save_tiff(image, filename)
def OnChangeFeatures(self, event):
# ---------------------------------------------------------------------------
from gamera import plugin
from gamera.core import ONEBIT
from gamera.core import ImageBase
from gamera.args import Args, Check
if self.classifier == None:
gui.message("No classifier loaded")
return
allFeatures = [x[0] for x in plugin.methods_flat_category("Features", ONEBIT)]
allFeatures.sort()
existingFeatures = [x[0] for x in ImageBase.get_feature_functions(self.classifier.features)[0]]
featureControls = []
for f in allFeatures:
featureControls.append(Check("", f, default=(f in existingFeatures)))
dialog = Args(
featureControls, name="Feature selection", title="Select the features you want to use for optimization"
)
result = dialog.show(self)
if result == None:
gui_util.message("No change applied")
return
selectedFeatures = [name for check, name in zip(result, allFeatures) if check]
self.classifier.change_feature_set(selectedFeatures)
self.UpdatePanels()
def get_file_extensions(mode):
from gamera import plugin
import os.path
from gamera.backport import sets
methods = plugin.methods_flat_category("File")
methods = [
y for x, y in methods if x.startswith(mode) and not x.endswith("image")
]
if len(methods) == 0:
raise RuntimeError(
"There don't seem to be any imported plugins that can %s files. Try running init_gamera() or explictly loading file i/o plugins such as tiff_support and png_support."
% mode)
extensions = sets.Set()
types = []
for method in methods:
wildcards = ";".join(
["*.%s;*.%s" % (ext.lower(), ext.upper()) for ext in method.exts])
type = "%s Files (%s)|%s" % (method.exts[0].upper(), wildcards,
wildcards)
types.append(type)
# We have to cast the lists to sets here to make Python 2.3.0 happy.
extensions.update(sets.Set(method.exts))
extensions.update(sets.Set([x.upper() for x in method.exts]))
all_extensions = ";".join(["*.%s" % x for x in extensions])
types.insert(0, "All images (%s)|%s" % (all_extensions, all_extensions))
types.append("All files (*.*)|*.*")
return "|".join(types)
def save_image(image, filename):
"""**save_image** (Image(ALL) *image*, String *filename*)
Saves an image to a file. The file type is automatically
determined from the extension.
"""
methods = plugin.methods_flat_category("File")
methods = [
y for x, y in methods if x.startswith("save") and x != "save_image"
]
if len(methods) == 0:
raise RuntimeError(
"There don't seem to be any imported plugins that can save files. Try running init_gamera(), or explicitly loading the plugins that support file saving, such as tiff_support and png_support."
)
for method in methods:
for ext in method.exts:
if os.path.splitext(filename)[1][1:].lower() == ext.lower():
method.__call__(image, filename)
return None
# For backward compatibility, fall back to tiff if
# we can't automatically determine the filetype by
# the extension
_tiff_support.save_tiff(image, filename)
def get_feature_functions(cls, features="all"):
from gamera import plugin
global all_features
if all_features is None:
all_features = plugin.methods_flat_category("Features", ONEBIT)
all_features.sort()
if features == "all" or features is None:
functions = all_features
return functions, cls._get_feature_vector_size(functions)
features = util.make_sequence(features)
all_strings = True
for feature in features:
if not util.is_string_or_unicode(feature):
all_strings = False
break
if not all_strings:
import plugin
all_functions = False
if (
type(features) == tuple
and len(features) == 2
and type(features[0]) == list
and type(features[1]) == int
):
all_functions = True
for feature in features[0]:
if not (
type(feature) == tuple
and util.is_string_or_unicode(feature[0])
and issubclass(feature[1], plugin.PluginFunction)
):
all_functions = False
break
if not all_functions:
raise ValueError("'%s' is not a valid way to specify a list of features." % str(features))
else:
return features
else:
features.sort()
functions = []
for feature in features:
found = 0
for i in all_features:
if feature == i[0]:
functions.append(i)
found = 1
break
if not found:
raise ValueError("'%s' is not a known feature function." % feature)
functions.sort()
return functions, cls._get_feature_vector_size(functions)
def get_feature_functions(cls, features='all'):
from gamera import plugin
global all_features
if all_features is None:
all_features = plugin.methods_flat_category('Features', ONEBIT)
all_features.sort()
if features == 'all' or features is None:
functions = all_features
return functions, cls._get_feature_vector_size(functions)
features = util.make_sequence(features)
all_strings = True
for feature in features:
if not util.is_string_or_unicode(feature):
all_strings = False
break
if not all_strings:
import plugin
all_functions = False
if (type(features) == tuple and len(features) == 2
and type(features[0]) == list
and type(features[1]) == int):
all_functions = True
for feature in features[0]:
if not (type(feature) == tuple
and util.is_string_or_unicode(feature[0])
and issubclass(feature[1], plugin.PluginFunction)):
all_functions = False
break
if not all_functions:
raise ValueError(
"'%s' is not a valid way to specify a list of features." %
str(features))
else:
return features
else:
features.sort()
functions = []
for feature in features:
found = 0
for i in all_features:
if feature == i[0]:
functions.append(i)
found = 1
break
if not found:
raise ValueError("'%s' is not a known feature function." %
feature)
functions.sort()
return functions, cls._get_feature_vector_size(functions)
def load_image(filename, compression=DENSE):
"""**load_image** (FileOpen *filename*, Choice *storage_format* = ``DENSE``)
Load an image from the given filename. At present, TIFF and PNG files are
supported.
*storage_format*
The type of `storage format`__ to use for the resulting image.
.. __: image_types.html#storage-formats"""
from gamera import plugin
import os.path
methods = plugin.methods_flat_category("File")
methods = [
y for x, y in methods if x.startswith("load") and x != "load_image"
]
if len(methods) == 0:
raise RuntimeError(
"There don't seem to be any imported plugins that can load files. Try running init_gamera(), or explicitly loading the plugins that support file loading, such as tiff_support and png_support."
)
try:
filename = filename.encode('utf8')
except:
pass
# First, try being smart by loading by extension
for method in methods:
for ext in method.exts:
if os.path.splitext(filename)[1].lower() == ext.lower():
try:
image = method.__call__(filename, compression)
except:
pass
else:
return image
# Then just try all options
for method in methods:
try:
image = method.__call__(filename, compression)
except:
pass
else:
return image
raise IOError("'%s' could not be loaded." % filename)
def load_image(filename, compression=DENSE):
"""**load_image** (FileOpen *filename*, Choice *storage_format* = ``DENSE``)
Load an image from the given filename. At present, TIFF and PNG files are
supported.
*storage_format*
The type of `storage format`__ to use for the resulting image.
.. __: image_types.html#storage-formats"""
from gamera import plugin
methods = plugin.methods_flat_category("File")
methods = [y for x, y in methods if x.startswith("load") and x != "load_image"]
if len(methods) == 0:
raise RuntimeError(
"There don't seem to be any imported plugins that can load files. Try running init_gamera(), or explicitly loading the plugins that support file loading, such as tiff_support and png_support."
)
# First, try being smart by loading by extension
for method in methods:
for ext in method.exts:
if os.path.splitext(filename)[1].lower() == ext.lower():
try:
image = method.__call__(filename, compression)
except:
pass
else:
return image
# Then just try all options
for method in methods:
try:
image = method.__call__(filename, compression)
except:
pass
else:
return image
raise IOError("'%s' could not be loaded." % filename)
def get_file_extensions(mode):
from gamera import plugin
from gamera.backport import sets
methods = plugin.methods_flat_category("File")
methods = [y for x, y in methods if x.startswith(mode) and not x.endswith("image")]
if len(methods) == 0:
raise RuntimeError("There don't seem to be any imported plugins that can %s files. Try running init_gamera() or explictly loading file i/o plugins such as tiff_support and png_support." % mode)
extensions = sets.Set()
types = []
for method in methods:
wildcards = ";".join(["*.%s;*.%s" %
(ext.lower(), ext.upper()) for ext in method.exts])
type = "%s Files (%s)|%s" % (method.exts[0].upper(), wildcards, wildcards)
types.append(type)
# We have to cast the lists to sets here to make Python 2.3.0 happy.
extensions.update(sets.Set(method.exts))
extensions.update(sets.Set([x.upper() for x in method.exts]))
all_extensions = ";".join(["*.%s" % x for x in extensions])
types.insert(0, "All images (%s)|%s" % (all_extensions, all_extensions))
types.append("All files (*.*)|*.*")
return "|".join(types)
def aomr_remaining_pages(outdir, classifier):
aomr_opts = {
'staff_finder': 0,
'lines_per_staff': 4,
'staff_removal': 0,
'binarization': 0,
'discard_size': 14
}
for dirpath, dirnames, filenames in os.walk(outdir):
if dirpath == outdir:
continue
if ".git" in dirpath.split("/"):
continue
folder_no = os.path.basename(dirpath)
pnum = int(folder_no)
lg.debug("Processing page {0}".format(pnum))
# these files give us problems.
if pnum in [41, 87, 100]:
lg.debug("Skipping page {0}".format(pnum))
continue
corrpg = "{0}_corr_page_glyphs.xml".format(folder_no.zfill(4))
# badpg = "bad_{0}_corr_page_glyphs.xml".format(folder_no.zfill(4))
if not corrpg in filenames:
# we need to perform aomr.
original_image = os.path.join(dirpath, "{0}_staves_only.tiff".format(folder_no.zfill(4)))
aomr_obj = AomrObject(original_image, **aomr_opts)
try:
lg.debug("Finding Staves")
s = aomr_obj.find_staves()
except Exception, e:
lg.debug("Cannot find staves: {0} because {1}".format(pnum, e))
continue
if not s:
lg.debug("No staves were found on page {0}".format(pnum))
continue
try:
aomr_obj.remove_stafflines()
except Exception, e:
lg.debug("Cannot remove stafflines: {0} because {1}".format(pnum, e))
continue
cknn = knn.kNNNonInteractive(classifier, 'all', True, 1)
ccs = aomr_obj.img_no_st.cc_analysis()
func = classify.BoundingBoxGroupingFunction(4)
classified_image = cknn.group_and_update_list_automatic(
ccs,
grouping_function=func,
max_parts_per_group=4,
max_graph_size=16
)
lg.debug("save all the files from page {0}".format(pnum))
cknn.generate_features_on_glyphs(classified_image)
s = SymbolTable()
for split in plugin.methods_flat_category("Segmentation", ONEBIT):
s.add("_split." + split[0])
s.add("_group")
s.add("_group._part")
gamera_xml.WriteXMLFile(glyphs=classified_image, with_features=True).write_filename(os.path.join(dirpath, "{0}_uncorr_page_glyphs.xml".format(folder_no.zfill(4))))
del aomr_obj
del classified_image
del cknn
def process_axz_directory(directory, class_glyphs, class_weights, outputdir):
print "Processing AXZ Folder"
for dirpath, dirnames, filenames in os.walk(directory):
# if os.path.abspath(directory) == os.path.abspath(dirpath):
# continue
for f in filenames:
if f == ".DS_Store":
continue
pagenum = f.split("_")[-1].strip('.axz')
print "Loading page ", str(pagenum)
# create an output directory
outdir = os.path.join(outputdir, pagenum)
os.mkdir(outdir)
axzfile = os.path.join(dirpath, f)
ax = AxFile(axzfile, "")
axtmp = ax.tmpdir
staves = ax.get_img0().extract(0)
# shutil.move(tfile[1], os.path.join(outdir, "original_image.tiff"))
sfile = os.path.join(outdir, "original_image.tiff")
save_image(staves, sfile)
# lg.debug("Tempfile is: {0}".format(tfile[1]))
# grab and remove the staves
aomr_opts = {
'lines_per_staff': 4,
'staff_finder': 0,
'staff_removal': 0,
'binarization': 0,
'discard_size': 12 # GVM, was 6
}
aomr_obj = AomrObject(sfile, **aomr_opts)
try:
lg.debug("Finding Staves")
s = aomr_obj.find_staves()
except Exception, e:
lg.debug("Cannot find staves: {0} because {1}".format(pagenum, e))
continue
lg.debug("S is: {0}".format(s))
if not s:
lg.debug("no staves were found")
os.remove(sfile)
os.rmdir(outdir)
try:
aomr_obj.remove_stafflines()
except Exception, e:
lg.debug("Cannot remove stafflines: {0} because {1}".format(pagenum, e))
continue
cknn = knn.kNNNonInteractive(class_glyphs, 'all', True, 1)
# cknn.load_settings(class_weights)
ccs = aomr_obj.img_no_st.cc_analysis()
func = classify.BoundingBoxGroupingFunction(4)
# classified_image = cknn.group_and_update_list_automatic(ccs, grouping_function, max_parts_per_group=4, max_graph_size=16)
classified_image = cknn.group_and_update_list_automatic(
ccs,
grouping_function=func,
max_parts_per_group=4,
max_graph_size=16
)
lg.debug("save all the files into this directory")
cknn.save_settings(os.path.join(outdir, "classifier_settings.xml"))
cknn.generate_features_on_glyphs(classified_image)
s = SymbolTable()
for split in plugin.methods_flat_category("Segmentation", ONEBIT):
s.add("_split." + split[0])
s.add("_group")
s.add("_group._part")
avg_punctum_col = aomr_obj.average_punctum(cknn.get_glyphs())
print 'average punctum column size = ', avg_punctum_col
glyphs_center_of_mass = aomr_obj.x_projection_vector(cknn.get_glyphs(), avg_punctum_col, aomr_opts.get('discard_size'))
print 'center of mass for each glyph = ', glyphs_center_of_mass
gamera_xml.WriteXMLFile(glyphs=classified_image, with_features=True).write_filename(os.path.join(outdir, "page_glyphs.xml"))
# gamera_xml.WriteXMLFile(symbol_table=s).write_filename(os.path.join(outdir, "symbol_table.xml"))
# cknn.to_xml_filename(os.path.join(outdir, "classifier_glyphs.xml"), with_features=True)
save_image(aomr_obj.img_no_st, os.path.join(outdir, "source_image.tiff"))
# clean up
del aomr_obj.img_no_st
del aomr_obj
del classified_image
del ax
del cknn
