qurator-spk/eynollah
1
0
Fork 0
mirror of https://github.com/qurator-spk/eynollah.git synced 2025-06-10 04:39:54 +02:00
Code Issues Projects Releases Wiki Activity

rename: image_{dir,filename}, {f_name,image_filename_stem}

Browse source
This commit is contained in:
Konstantin Baierer 2021-01-27 12:52:51 +01:00
parent f5e11a1056
commit 52df6972ad
2 changed files with 10 additions and 123 deletions
Download patch file Download diff file Expand all files Collapse all files

34
sbb_newspapers_org_image/eynollah.py
View file

@ -1,3 +1,4 @@
# pylint: disable=no-member
""" """
tool to extract table form data from alto xml data tool to extract table form data from alto xml data
""" """
@ -200,15 +201,8 @@ class eynollah:
nxf = img_w / float(width_mid) nxf = img_w / float(width_mid)
nyf = img_h / float(height_mid) nyf = img_h / float(height_mid)
if nxf > int(nxf): nxf = int(nxf) + 1 if nxf > int(nxf) else int(nxf)
nxf = int(nxf) + 1 nyf = int(nyf) + 1 if nyf > int(nyf) else int(nyf)
else:
nxf = int(nxf)
if nyf > int(nyf):
nyf = int(nyf) + 1
else:
nyf = int(nyf)
for i in range(nxf): for i in range(nxf):
for j in range(nyf): for j in range(nyf):
@ -295,7 +289,6 @@ class eynollah:
return int(float(dpi)) return int(float(dpi))
def resize_image_with_column_classifier(self, is_image_enhanced): def resize_image_with_column_classifier(self, is_image_enhanced):
dpi = self.check_dpi()
img = cv2.imread(self.image_filename) img = cv2.imread(self.image_filename)
img = img.astype(np.uint8) img = img.astype(np.uint8)
@ -540,11 +533,6 @@ class eynollah:
image_res = self.predict_enhancement(img_new) image_res = self.predict_enhancement(img_new)
# cv2.imwrite(os.path.join(self.dir_out, self.image_filename_stem) + ".tif",self.image) # cv2.imwrite(os.path.join(self.dir_out, self.image_filename_stem) + ".tif",self.image)
# self.image=self.image.astype(np.uint16) # self.image=self.image.astype(np.uint16)
# self.scale_x=1
# self.scale_y=1
# self.height_org = self.image.shape[0]
# self.width_org = self.image.shape[1]
is_image_enhanced = True is_image_enhanced = True
else: else:
is_image_enhanced = False is_image_enhanced = False
@ -570,8 +558,6 @@ class eynollah:
def get_image_and_scales_after_enhancing(self, img_org, img_res): def get_image_and_scales_after_enhancing(self, img_org, img_res):
# self.image = cv2.imread(self.image_filename)
self.image = np.copy(img_res) self.image = np.copy(img_res)
self.image = self.image.astype(np.uint8) self.image = self.image.astype(np.uint8)
self.image_org = np.copy(img_org) self.image_org = np.copy(img_org)
@ -630,15 +616,8 @@ class eynollah:
nxf = img_w / float(width_mid) nxf = img_w / float(width_mid)
nyf = img_h / float(height_mid) nyf = img_h / float(height_mid)
if nxf > int(nxf): nxf = int(nxf) + 1 if nxf > int(nxf) else int(nxf)
nxf = int(nxf) + 1 nyf = int(nyf) + 1 if nyf > int(nyf) else int(nyf)
else:
nxf = int(nxf)
if nyf > int(nyf):
nyf = int(nyf) + 1
else:
nyf = int(nyf)
for i in range(nxf): for i in range(nxf):
for j in range(nyf): for j in range(nyf):
@ -665,11 +644,8 @@ class eynollah:
index_y_d = img_h - img_height_model index_y_d = img_h - img_height_model
img_patch = img[index_y_d:index_y_u, index_x_d:index_x_u, :] img_patch = img[index_y_d:index_y_u, index_x_d:index_x_u, :]
label_p_pred = model.predict(img_patch.reshape(1, img_patch.shape[0], img_patch.shape[1], img_patch.shape[2])) label_p_pred = model.predict(img_patch.reshape(1, img_patch.shape[0], img_patch.shape[1], img_patch.shape[2]))
seg = np.argmax(label_p_pred, axis=3)[0] seg = np.argmax(label_p_pred, axis=3)[0]
seg_color = np.repeat(seg[:, :, np.newaxis], 3, axis=2) seg_color = np.repeat(seg[:, :, np.newaxis], 3, axis=2)
if i == 0 and j == 0: if i == 0 and j == 0:

99
sbb_newspapers_org_image/utils/separate_lines.py
View file

@ -1485,7 +1485,7 @@ def textline_contours_postprocessing(textline_mask, slope, contour_text_interest
return contours_rotated_clean return contours_rotated_clean
def seperate_lines_new2(img_path, thetha, num_col, slope_region, dir_of_all, f_name): def seperate_lines_new2(img_path, thetha, num_col, slope_region, dir_of_all, image_filename_stem):
if num_col == 1: if num_col == 1:
num_patches = int(img_path.shape[1] / 200.0) num_patches = int(img_path.shape[1] / 200.0)
@ -1536,7 +1536,7 @@ def seperate_lines_new2(img_path, thetha, num_col, slope_region, dir_of_all, f_n
sigma = 2 sigma = 2
try: try:
slope_xline = return_deskew_slop(img_xline, sigma, dir_of_all=dir_of_all, f_name=f_name) slope_xline = return_deskew_slop(img_xline, sigma, dir_of_all=dir_of_all, image_filename_stem=image_filename_stem)
except: except:
slope_xline = 0 slope_xline = 0
@ -1593,7 +1593,7 @@ def seperate_lines_new2(img_path, thetha, num_col, slope_region, dir_of_all, f_n
# plt.show() # plt.show()
return img_patch_ineterst_revised return img_patch_ineterst_revised
def return_deskew_slop(img_patch_org, sigma_des, main_page=False, dir_of_all=None, f_name=None): def return_deskew_slop(img_patch_org, sigma_des, main_page=False, dir_of_all=None, image_filename_stem=None):
if main_page and dir_of_all is not None: if main_page and dir_of_all is not None:
@ -1610,7 +1610,7 @@ def return_deskew_slop(img_patch_org, sigma_des, main_page=False, dir_of_all=Non
plt.yticks([0,len(gaussian_filter1d(img_patch_org.sum(axis=1), 3))]) plt.yticks([0,len(gaussian_filter1d(img_patch_org.sum(axis=1), 3))])
plt.gca().invert_yaxis() plt.gca().invert_yaxis()
plt.savefig(os.path.join(dir_of_all, f_name+'_density_of_textline.png')) plt.savefig(os.path.join(dir_of_all, image_filename_stem+'_density_of_textline.png'))
#print(np.max(img_patch_org.sum(axis=0)) ,np.max(img_patch_org.sum(axis=1)),'axislar') #print(np.max(img_patch_org.sum(axis=0)) ,np.max(img_patch_org.sum(axis=1)),'axislar')
#img_patch_org=resize_image(img_patch_org,int(img_patch_org.shape[0]*2.5),int(img_patch_org.shape[1]/2.5)) #img_patch_org=resize_image(img_patch_org,int(img_patch_org.shape[0]*2.5),int(img_patch_org.shape[1]/2.5))
@ -1647,53 +1647,23 @@ def return_deskew_slop(img_patch_org, sigma_des, main_page=False, dir_of_all=Non
#plt.show() #plt.show()
angels=np.array([-45, 0 , 45 , 90 , ])#np.linspace(-12,12,100)#np.array([0 , 45 , 90 , -45]) angels=np.array([-45, 0 , 45 , 90 , ])#np.linspace(-12,12,100)#np.array([0 , 45 , 90 , -45])
#res=[]
#num_of_peaks=[]
#index_cor=[]
var_res=[] var_res=[]
#indexer=0
for rot in angels: for rot in angels:
img_rot=rotate_image(img_resized,rot) img_rot=rotate_image(img_resized,rot)
#plt.imshow(img_rot) #plt.imshow(img_rot)
#plt.show() #plt.show()
img_rot[img_rot!=0]=1 img_rot[img_rot!=0]=1
#res_me=np.mean(self.find_num_col_deskew(img_rot,sigma_des,2.0 ))
#neg_peaks,var_spectrum=self.find_num_col_deskew(img_rot,sigma_des,20.3 ) #neg_peaks,var_spectrum=self.find_num_col_deskew(img_rot,sigma_des,20.3 )
#print(var_spectrum,'var_spectrum') #print(var_spectrum,'var_spectrum')
try: try:
var_spectrum=find_num_col_deskew(img_rot,sigma_des,20.3 ) var_spectrum=find_num_col_deskew(img_rot,sigma_des,20.3 )
##print(rot,var_spectrum,'var_spectrum') ##print(rot,var_spectrum,'var_spectrum')
#res_me=np.mean(neg_peaks)
#if res_me==0:
#res_me=1000000000000000000000
#else:
#pass
#res_num=len(neg_peaks)
except: except:
#res_me=1000000000000000000000
#res_num=0
var_spectrum=0 var_spectrum=0
#if self.isNaN(res_me):
#pass
#else:
#res.append( res_me )
#var_res.append(var_spectrum)
#num_of_peaks.append( res_num )
#index_cor.append(indexer)
#indexer=indexer+1
var_res.append(var_spectrum) var_res.append(var_spectrum)
#index_cor.append(indexer)
#indexer=indexer+1
try: try:
var_res=np.array(var_res) var_res=np.array(var_res)
ang_int=angels[np.argmax(var_res)]#angels_sorted[arg_final]#angels[arg_sort_early[arg_sort[arg_final]]]#angels[arg_fin] ang_int=angels[np.argmax(var_res)]#angels_sorted[arg_final]#angels[arg_sort_early[arg_sort[arg_final]]]#angels[arg_fin]
except: except:
ang_int=0 ang_int=0
@ -1701,32 +1671,19 @@ def return_deskew_slop(img_patch_org, sigma_des, main_page=False, dir_of_all=Non
angels=np.linspace(ang_int-22.5,ang_int+22.5,100) angels=np.linspace(ang_int-22.5,ang_int+22.5,100)
#res=[]
#num_of_peaks=[]
#index_cor=[]
var_res=[] var_res=[]
for rot in angels: for rot in angels:
img_rot=rotate_image(img_resized,rot) img_rot=rotate_image(img_resized,rot)
##plt.imshow(img_rot) ##plt.imshow(img_rot)
##plt.show() ##plt.show()
img_rot[img_rot!=0]=1 img_rot[img_rot!=0]=1
#res_me=np.mean(self.find_num_col_deskew(img_rot,sigma_des,2.0 ))
try: try:
var_spectrum=find_num_col_deskew(img_rot,sigma_des,20.3 ) var_spectrum=find_num_col_deskew(img_rot,sigma_des,20.3 )
except: except:
var_spectrum=0 var_spectrum=0
var_res.append(var_spectrum) var_res.append(var_spectrum)
try: try:
var_res=np.array(var_res) var_res=np.array(var_res)
ang_int=angels[np.argmax(var_res)]#angels_sorted[arg_final]#angels[arg_sort_early[arg_sort[arg_final]]]#angels[arg_fin] ang_int=angels[np.argmax(var_res)]#angels_sorted[arg_final]#angels[arg_sort_early[arg_sort[arg_final]]]#angels[arg_fin]
except: except:
ang_int=0 ang_int=0
@ -1745,9 +1702,6 @@ def return_deskew_slop(img_patch_org, sigma_des, main_page=False, dir_of_all=Non
#plt.imshow(img_rot) #plt.imshow(img_rot)
#plt.show() #plt.show()
img_rot[img_rot!=0]=1 img_rot[img_rot!=0]=1
#res_me=np.mean(self.find_num_col_deskew(img_rot,sigma_des,2.0 ))
#neg_peaks,var_spectrum=self.find_num_col_deskew(img_rot,sigma_des,20.3 ) #neg_peaks,var_spectrum=self.find_num_col_deskew(img_rot,sigma_des,20.3 )
#print(var_spectrum,'var_spectrum') #print(var_spectrum,'var_spectrum')
try: try:
@ -1769,41 +1723,29 @@ def return_deskew_slop(img_patch_org, sigma_des, main_page=False, dir_of_all=Non
plt.plot(angels[np.argmax(var_res)],var_res[np.argmax(np.array(var_res))] ,'*',markersize=50,label='Angle of deskewing=' +str("{:.2f}".format(angels[np.argmax(var_res)]))+r'$\degree$') plt.plot(angels[np.argmax(var_res)],var_res[np.argmax(np.array(var_res))] ,'*',markersize=50,label='Angle of deskewing=' +str("{:.2f}".format(angels[np.argmax(var_res)]))+r'$\degree$')
plt.legend(loc='best') plt.legend(loc='best')
plt.savefig(os.path.join(dir_of_all,f_name+'_rotation_angle.png')) plt.savefig(os.path.join(dir_of_all,image_filename_stem+'_rotation_angle.png'))
try: try:
var_res=np.array(var_res) var_res=np.array(var_res)
ang_int=angels[np.argmax(var_res)]#angels_sorted[arg_final]#angels[arg_sort_early[arg_sort[arg_final]]]#angels[arg_fin] ang_int=angels[np.argmax(var_res)]#angels_sorted[arg_final]#angels[arg_sort_early[arg_sort[arg_final]]]#angels[arg_fin]
except: except:
ang_int=0 ang_int=0
early_slope_edge=11 early_slope_edge=11
if abs(ang_int)>early_slope_edge and ang_int<0: if abs(ang_int)>early_slope_edge and ang_int<0:
angels=np.linspace(-90,-12,100) angels=np.linspace(-90,-12,100)
var_res=[] var_res=[]
for rot in angels: for rot in angels:
img_rot=rotate_image(img_resized,rot) img_rot=rotate_image(img_resized,rot)
##plt.imshow(img_rot) ##plt.imshow(img_rot)
##plt.show() ##plt.show()
img_rot[img_rot!=0]=1 img_rot[img_rot!=0]=1
#res_me=np.mean(self.find_num_col_deskew(img_rot,sigma_des,2.0 ))
try: try:
var_spectrum=find_num_col_deskew(img_rot,sigma_des,20.3 ) var_spectrum=find_num_col_deskew(img_rot,sigma_des,20.3 )
except: except:
var_spectrum=0 var_spectrum=0
var_res.append(var_spectrum) var_res.append(var_spectrum)
try: try:
var_res=np.array(var_res) var_res=np.array(var_res)
ang_int=angels[np.argmax(var_res)]#angels_sorted[arg_final]#angels[arg_sort_early[arg_sort[arg_final]]]#angels[arg_fin] ang_int=angels[np.argmax(var_res)]#angels_sorted[arg_final]#angels[arg_sort_early[arg_sort[arg_final]]]#angels[arg_fin]
except: except:
ang_int=0 ang_int=0
@ -1811,67 +1753,47 @@ def return_deskew_slop(img_patch_org, sigma_des, main_page=False, dir_of_all=Non
elif abs(ang_int)>early_slope_edge and ang_int>0: elif abs(ang_int)>early_slope_edge and ang_int>0:
angels=np.linspace(90,12,100) angels=np.linspace(90,12,100)
var_res=[] var_res=[]
for rot in angels: for rot in angels:
img_rot=rotate_image(img_resized,rot) img_rot=rotate_image(img_resized,rot)
##plt.imshow(img_rot) ##plt.imshow(img_rot)
##plt.show() ##plt.show()
img_rot[img_rot!=0]=1 img_rot[img_rot!=0]=1
#res_me=np.mean(self.find_num_col_deskew(img_rot,sigma_des,2.0 ))
try: try:
var_spectrum=find_num_col_deskew(img_rot,sigma_des,20.3 ) var_spectrum=find_num_col_deskew(img_rot,sigma_des,20.3 )
#print(indexer,'indexer') #print(indexer,'indexer')
except: except:
var_spectrum=0 var_spectrum=0
var_res.append(var_spectrum) var_res.append(var_spectrum)
try: try:
var_res=np.array(var_res) var_res=np.array(var_res)
ang_int=angels[np.argmax(var_res)]#angels_sorted[arg_final]#angels[arg_sort_early[arg_sort[arg_final]]]#angels[arg_fin] ang_int=angels[np.argmax(var_res)]#angels_sorted[arg_final]#angels[arg_sort_early[arg_sort[arg_final]]]#angels[arg_fin]
except: except:
ang_int=0 ang_int=0
else: else:
angels=np.linspace(-25,25,60) angels=np.linspace(-25,25,60)
var_res=[] var_res=[]
indexer=0 indexer=0
for rot in angels: for rot in angels:
img_rot=rotate_image(img_resized,rot) img_rot=rotate_image(img_resized,rot)
#plt.imshow(img_rot) #plt.imshow(img_rot)
#plt.show() #plt.show()
img_rot[img_rot!=0]=1 img_rot[img_rot!=0]=1
#res_me=np.mean(self.find_num_col_deskew(img_rot,sigma_des,2.0 ))
#neg_peaks,var_spectrum=self.find_num_col_deskew(img_rot,sigma_des,20.3 ) #neg_peaks,var_spectrum=self.find_num_col_deskew(img_rot,sigma_des,20.3 )
#print(var_spectrum,'var_spectrum') #print(var_spectrum,'var_spectrum')
try: try:
var_spectrum=find_num_col_deskew(img_rot,sigma_des,20.3 ) var_spectrum=find_num_col_deskew(img_rot,sigma_des,20.3 )
except: except:
var_spectrum=0 var_spectrum=0
var_res.append(var_spectrum) var_res.append(var_spectrum)
try: try:
var_res=np.array(var_res) var_res=np.array(var_res)
ang_int=angels[np.argmax(var_res)]#angels_sorted[arg_final]#angels[arg_sort_early[arg_sort[arg_final]]]#angels[arg_fin] ang_int=angels[np.argmax(var_res)]#angels_sorted[arg_final]#angels[arg_sort_early[arg_sort[arg_final]]]#angels[arg_fin]
except: except:
ang_int=0 ang_int=0
#plt.plot(var_res) #plt.plot(var_res)
#plt.show() #plt.show()
##plt.plot(mom3_res) ##plt.plot(mom3_res)
##plt.show() ##plt.show()
#print(ang_int,'ang_int111') #print(ang_int,'ang_int111')
@ -1888,20 +1810,14 @@ def return_deskew_slop(img_patch_org, sigma_des, main_page=False, dir_of_all=Non
##plt.imshow(img_rot) ##plt.imshow(img_rot)
##plt.show() ##plt.show()
img_rot[img_rot!=0]=1 img_rot[img_rot!=0]=1
#res_me=np.mean(self.find_num_col_deskew(img_rot,sigma_des,2.0 ))
try: try:
var_spectrum=find_num_col_deskew(img_rot,sigma_des,20.3 ) var_spectrum=find_num_col_deskew(img_rot,sigma_des,20.3 )
except: except:
var_spectrum=0 var_spectrum=0
var_res.append(var_spectrum) var_res.append(var_spectrum)
try: try:
var_res=np.array(var_res) var_res=np.array(var_res)
ang_int=angels[np.argmax(var_res)]#angels_sorted[arg_final]#angels[arg_sort_early[arg_sort[arg_final]]]#angels[arg_fin] ang_int=angels[np.argmax(var_res)]#angels_sorted[arg_final]#angels[arg_sort_early[arg_sort[arg_final]]]#angels[arg_fin]
except: except:
ang_int=0 ang_int=0
@ -1918,7 +1834,6 @@ def return_deskew_slop(img_patch_org, sigma_des, main_page=False, dir_of_all=Non
##plt.imshow(img_rot) ##plt.imshow(img_rot)
##plt.show() ##plt.show()
img_rot[img_rot!=0]=1 img_rot[img_rot!=0]=1
#res_me=np.mean(self.find_num_col_deskew(img_rot,sigma_des,2.0 ))
try: try:
var_spectrum=find_num_col_deskew(img_rot,sigma_des,20.3 ) var_spectrum=find_num_col_deskew(img_rot,sigma_des,20.3 )
#print(indexer,'indexer') #print(indexer,'indexer')
@ -1926,12 +1841,8 @@ def return_deskew_slop(img_patch_org, sigma_des, main_page=False, dir_of_all=Non
var_spectrum=0 var_spectrum=0
var_res.append(var_spectrum) var_res.append(var_spectrum)
try: try:
var_res=np.array(var_res) var_res=np.array(var_res)
ang_int=angels[np.argmax(var_res)]#angels_sorted[arg_final]#angels[arg_sort_early[arg_sort[arg_final]]]#angels[arg_fin] ang_int=angels[np.argmax(var_res)]#angels_sorted[arg_final]#angels[arg_sort_early[arg_sort[arg_final]]]#angels[arg_fin]
except: except:
ang_int=0 ang_int=0