Merge e428e7ad78 into 38c028c6b5

src/eynollah/cli.py

@@ -79,18 +79,28 @@ def machine_based_reading_order(input, dir_in, out, model, log_level):
     type=click.Path(file_okay=True, dir_okay=True),
     required=True,
 )
+@click.option(
+    "--overwrite",
+    "-O",
+    help="overwrite (instead of skipping) if output xml exists",
+    is_flag=True,
+)
 @click.option(
     "--log_level",
     "-l",
     type=click.Choice(['OFF', 'DEBUG', 'INFO', 'WARN', 'ERROR']),
     help="Override log level globally to this",
 )
-def binarization(patches, model_dir, input_image, dir_in, output, log_level):
+def binarization(patches, model_dir, input_image, dir_in, output, overwrite, log_level):
     assert bool(input_image) != bool(dir_in), "Either -i (single input) or -di (directory) must be provided, but not both."
     binarizer = SbbBinarizer(model_dir)
     if log_level:
-        binarizer.log.setLevel(getLevelName(log_level))
-    binarizer.run(image_path=input_image, use_patches=patches, output=output, dir_in=dir_in)
+        binarizer.logger.setLevel(getLevelName(log_level))
+    binarizer.run(overwrite=overwrite,
+                  use_patches=patches,
+                  image_path=input_image,
+                  output=output,
+                  dir_in=dir_in)
 
 
 @main.command()

src/eynollah/ocrd_cli_binarization.py

@@ -70,7 +70,7 @@ class SbbBinarizeProcessor(Processor):
 
         if oplevel == 'page':
             self.logger.info("Binarizing on 'page' level in page '%s'", page_id)
-            page_image_bin = cv2pil(self.binarizer.run(image=pil2cv(page_image), use_patches=True))
+            page_image_bin = cv2pil(self.binarizer.run_single(image=pil2cv(page_image), use_patches=True))
             # update PAGE (reference the image file):
             page_image_ref = AlternativeImageType(comments=page_xywh['features'] + ',binarized,clipped')
             page.add_AlternativeImage(page_image_ref)
@@ -83,7 +83,7 @@ class SbbBinarizeProcessor(Processor):
             for region in regions:
                 region_image, region_xywh = self.workspace.image_from_segment(
                     region, page_image, page_xywh, feature_filter='binarized')
-                region_image_bin = cv2pil(self.binarizer.run(image=pil2cv(region_image), use_patches=True))
+                region_image_bin = cv2pil(self.binarizer.run_single(image=pil2cv(region_image), use_patches=True))
                 # update PAGE (reference the image file):
                 region_image_ref = AlternativeImageType(comments=region_xywh['features'] + ',binarized')
                 region.add_AlternativeImage(region_image_ref)
@@ -95,7 +95,7 @@ class SbbBinarizeProcessor(Processor):
                 self.logger.warning("Page '%s' contains no text lines", page_id)
             for line in lines:
                 line_image, line_xywh = self.workspace.image_from_segment(line, page_image, page_xywh, feature_filter='binarized')
-                line_image_bin = cv2pil(self.binarizer.run(image=pil2cv(line_image), use_patches=True))
+                line_image_bin = cv2pil(self.binarizer.run_single(image=pil2cv(line_image), use_patches=True))
                 # update PAGE (reference the image file):
                 line_image_ref = AlternativeImageType(comments=line_xywh['features'] + ',binarized')
                 line.add_AlternativeImage(region_image_ref)

src/eynollah/sbb_binarize.py

@@ -25,7 +25,7 @@ class SbbBinarizer:
 
     def __init__(self, model_dir, logger=None):
         self.model_dir = model_dir
-        self.log = logger if logger else logging.getLogger('SbbBinarizer')
+        self.logger = logger if logger else logging.getLogger('SbbBinarizer')
 
         self.start_new_session()
 
@@ -315,47 +315,30 @@ class SbbBinarizer:
             prediction_true = prediction_true.astype(np.uint8)
         return prediction_true[:,:,0]
 
-    def run(self, image=None, image_path=None, output=None, use_patches=False, dir_in=None):
-        # print(dir_in,'dir_in')
-        if not dir_in:
-            if (image is not None and image_path is not None) or \
-                (image is None and image_path is None):
-                raise ValueError("Must pass either a opencv2 image or an image_path")
-            if image_path is not None:
-                image = cv2.imread(image_path)
-            img_last = 0
-            for n, (model, model_file) in enumerate(zip(self.models, self.model_files)):
-                self.log.info('Predicting with model %s [%s/%s]' % (model_file, n + 1, len(self.model_files)))
-
-                res = self.predict(model, image, use_patches)
-
-                img_fin = np.zeros((res.shape[0], res.shape[1], 3))
-                res[:, :][res[:, :] == 0] = 2
-                res = res - 1
-                res = res * 255
-                img_fin[:, :, 0] = res
-                img_fin[:, :, 1] = res
-                img_fin[:, :, 2] = res
-
-                img_fin = img_fin.astype(np.uint8)
-                img_fin = (res[:, :] == 0) * 255
-                img_last = img_last + img_fin
-
-            kernel = np.ones((5, 5), np.uint8)
-            img_last[:, :][img_last[:, :] > 0] = 255
-            img_last = (img_last[:, :] == 0) * 255
-            if output:
-                cv2.imwrite(output, img_last)
-            return img_last
+    def run(self, image_path=None, output=None, dir_in=None, use_patches=False, overwrite=False):
+        if dir_in:
+            ls_imgs = [(os.path.join(dir_in, image_filename),
+                        os.path.join(output, os.path.splitext(image_filename)[0] + '.png'))
+                       for image_filename in filter(is_image_filename,
+                                                    os.listdir(dir_in))]
         else:
-            ls_imgs = list(filter(is_image_filename, os.listdir(dir_in)))
-            for image_name in ls_imgs:
-                image_stem = image_name.split('.')[0]
-                print(image_name,'image_name')
-                image = cv2.imread(os.path.join(dir_in,image_name) )
+            ls_imgs = [(image_path, output)]
+
+        for input_path, output_path in ls_imgs:
+            print(input_path, 'image_name')
+            if os.path.exists(output_path):
+                if overwrite:
+                    self.logger.warning("will overwrite existing output file '%s'", output_path)
+                else:
+                    self.logger.warning("will skip input for existing output file '%s'", output_path)
+            image = cv2.imread(input_path)
+            result = self.run_single(image, use_patches)
+            cv2.imwrite(output_path, result)
+
+    def run_single(self, image: np.ndarray, use_patches=False):
         img_last = 0
         for n, (model, model_file) in enumerate(zip(self.models, self.model_files)):
-                    self.log.info('Predicting with model %s [%s/%s]' % (model_file, n + 1, len(self.model_files)))
+            self.logger.info('Predicting with model %s [%s/%s]' % (model_file, n + 1, len(self.model_files)))
 
             res = self.predict(model, image, use_patches)
 
@@ -374,5 +357,4 @@ class SbbBinarizer:
         kernel = np.ones((5, 5), np.uint8)
         img_last[:, :][img_last[:, :] > 0] = 255
         img_last = (img_last[:, :] == 0) * 255
-                
-                cv2.imwrite(os.path.join(output, image_stem + '.png'), img_last)
+        return img_last

src/eynollah/utils/contour.py

@@ -14,21 +14,16 @@ from shapely.ops import unary_union, nearest_points
 from .rotate import rotate_image, rotation_image_new
 
 def contours_in_same_horizon(cy_main_hor):
-    X1 = np.zeros((len(cy_main_hor), len(cy_main_hor)))
-    X2 = np.zeros((len(cy_main_hor), len(cy_main_hor)))
-
-    X1[0::1, :] = cy_main_hor[:]
-    X2 = X1.T
-
-    X_dif = np.abs(X2 - X1)
-    args_help = np.array(range(len(cy_main_hor)))
-    all_args = []
-    for i in range(len(cy_main_hor)):
-        list_h = list(args_help[X_dif[i, :] <= 20])
-        list_h.append(i)
-        if len(list_h) > 1:
-            all_args.append(list(set(list_h)))
-    return np.unique(np.array(all_args, dtype=object))
+    """
+    Takes an array of y coords, identifies all pairs among them
+    which are close to each other, and returns all such pairs
+    by index into the array.
+    """
+    sort = np.argsort(cy_main_hor)
+    same = np.diff(cy_main_hor[sort] <= 20)
+    # groups = np.split(sort, np.arange(len(cy_main_hor) - 1)[~same] + 1)
+    same = np.flatnonzero(same)
+    return np.stack((sort[:-1][same], sort[1:][same])).T
 
 def find_contours_mean_y_diff(contours_main):
     M_main = [cv2.moments(contours_main[j]) for j in range(len(contours_main))]

src/eynollah/writer.py

@@ -89,7 +89,7 @@ class EynollahXmlWriter:
 
     def build_pagexml_no_full_layout(
             self, found_polygons_text_region,
-            page_coord, order_of_texts, id_of_texts,
+            page_coord, order_of_texts,
             all_found_textline_polygons,
             all_box_coord,
             found_polygons_text_region_img,
@@ -102,7 +102,7 @@ class EynollahXmlWriter:
             **kwargs):
         return self.build_pagexml_full_layout(
             found_polygons_text_region, [],
-            page_coord, order_of_texts, id_of_texts,
+            page_coord, order_of_texts,
             all_found_textline_polygons, [],
             all_box_coord, [],
             found_polygons_text_region_img, found_polygons_tables, [],
@@ -116,7 +116,7 @@ class EynollahXmlWriter:
     def build_pagexml_full_layout(
             self,
             found_polygons_text_region, found_polygons_text_region_h,
-            page_coord, order_of_texts, id_of_texts,
+            page_coord, order_of_texts,
             all_found_textline_polygons, all_found_textline_polygons_h,
             all_box_coord, all_box_coord_h,
             found_polygons_text_region_img, found_polygons_tables, found_polygons_drop_capitals,