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

simplify calculate_page_coords

Browse source
This commit is contained in:
Konstantin Baierer 2021-02-24 14:42:15 +01:00
parent ddeb6938e5
commit 6398579a72
1 changed files with 9 additions and 18 deletions
Download patch file Download diff file Expand all files Collapse all files

23
sbb_newspapers_org_image/eynollah.py
View file

@ -576,19 +576,14 @@ class eynollah:
self.logger.debug("enter extract_page") self.logger.debug("enter extract_page")
model_page, session_page = self.start_new_session_and_model(self.model_page_dir) model_page, session_page = self.start_new_session_and_model(self.model_page_dir)
img = cv2.GaussianBlur(self.image, (5, 5), 0) img = cv2.GaussianBlur(self.image, (5, 5), 0)
img_page_prediction = self.do_prediction(False, img, model_page) img_page_prediction = self.do_prediction(False, img, model_page)
imgray = cv2.cvtColor(img_page_prediction, cv2.COLOR_BGR2GRAY) imgray = cv2.cvtColor(img_page_prediction, cv2.COLOR_BGR2GRAY)
_, thresh = cv2.threshold(imgray, 0, 255, 0) _, thresh = cv2.threshold(imgray, 0, 255, 0)
thresh = cv2.dilate(thresh, KERNEL, iterations=3) thresh = cv2.dilate(thresh, KERNEL, iterations=3)
contours, _ = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE) contours, _ = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
cnt_size = np.array([cv2.contourArea(contours[j]) for j in range(len(contours))]) cnt_size = np.array([cv2.contourArea(contours[j]) for j in range(len(contours))])
cnt = contours[np.argmax(cnt_size)] cnt = contours[np.argmax(cnt_size)]
x, y, w, h = cv2.boundingRect(cnt) x, y, w, h = cv2.boundingRect(cnt)
if x <= 30: if x <= 30:
w += x w += x
x = 0 x = 0
@ -602,9 +597,7 @@ class eynollah:
box = [x, y, w, h] box = [x, y, w, h]
croped_page, page_coord = crop_image_inside_box(box, self.image) croped_page, page_coord = crop_image_inside_box(box, self.image)
self.cont_page.append(np.array([[page_coord[2], page_coord[0]], [page_coord[3], page_coord[0]], [page_coord[3], page_coord[1]], [page_coord[2], page_coord[1]]])) self.cont_page.append(np.array([[page_coord[2], page_coord[0]], [page_coord[3], page_coord[0]], [page_coord[3], page_coord[1]], [page_coord[2], page_coord[1]]]))
session_page.close() session_page.close()
K.clear_session() K.clear_session()
@ -1071,19 +1064,17 @@ class eynollah:
def calculate_page_coords(self): def calculate_page_coords(self):
self.logger.debug('enter calculate_page_coords') self.logger.debug('enter calculate_page_coords')
points_page_print = "" points_page_print = ""
for lmm in range(len(self.cont_page[0])): for lmm, contour in enumerate(self.cont_page[0]):
if len(self.cont_page[0][lmm]) == 2: if len(contour) == 2:
points_page_print += str(int((self.cont_page[0][lmm][0] ) / self.scale_x)) points_page_print += str(int((contour[0]) / self.scale_x))
points_page_print += ',' points_page_print += ','
points_page_print += str(int((self.cont_page[0][lmm][1] ) / self.scale_y)) points_page_print += str(int((contour[1]) / self.scale_y))
else: else:
points_page_print += str(int((self.cont_page[0][lmm][0][0]) / self.scale_x)) points_page_print += str(int((contour[0][0]) / self.scale_x))
points_page_print += ',' points_page_print += ','
points_page_print += str(int((self.cont_page[0][lmm][0][1] ) / self.scale_y)) points_page_print += str(int((contour[0][1] ) / self.scale_y))
if lmm < len( self.cont_page[0] ) - 1:
points_page_print = points_page_print + ' ' points_page_print = points_page_print + ' '
return points_page_print return points_page_print[:-1]
def xml_reading_order(self, page, order_of_texts, id_of_texts, id_of_marginalia, found_polygons_marginals): def xml_reading_order(self, page, order_of_texts, id_of_texts, id_of_marginalia, found_polygons_marginals):
""" """