changes mentioned in revew

ocrd_anybaseocr/cli/ocrd_anybaseocr_binarize.py

@@ -122,7 +122,7 @@ def process(self):
                                                                for name in self.parameter.keys()])]))
 
             page = pcgts.get_Page()
-            page_image, page_xywh, page_image_info = self.workspace.image_from_page(page, page_id, feature_filter="binarized")
+            page_image, page_xywh, page_image_info = self.workspace.image_from_page(page, page_id, feature_filter="binarized,deskewed,cropped")
             LOG.info("Binarizing on '%s' level in page '%s'", oplevel, page_id)                    
 
             if oplevel=="page":

ocrd_anybaseocr/cli/ocrd_anybaseocr_block_segmentation.py

@@ -28,7 +28,6 @@
 from shapely.geometry import Polygon
 
 from ocrd_anybaseocr.mrcnn import model
-#from ocrd_anybaseocr.mrcnn import visualize
 from ocrd_anybaseocr.mrcnn.config import Config
 from ocrd_models.constants import NAMESPACES as NS
 
@@ -69,7 +68,6 @@ def process(self):
         if not tf.test.is_gpu_available():
             LOG.error("Your system has no CUDA installed. No GPU detected.")
             sys.exit(1)
-
         try:
             page_grp, self.image_grp = self.output_file_grp.split(',')
         except ValueError:
@@ -94,7 +92,7 @@ def process(self):
             sys.exit(1)
         '''    
         config = InferenceConfig()
-        mrcnn_model = model.MaskRCNN(mode="inference", model_dir="./", config=config)
+        mrcnn_model = model.MaskRCNN(mode="inference", model_dir=str(model_path), config=config)
         mrcnn_model.load_weights(str(model_weights), by_name=True)
 
         oplevel = self.parameter['operation_level']
@@ -104,7 +102,7 @@ def process(self):
             page = pcgts.get_Page()
             page_id = input_file.pageId or input_file.ID 
 
-            page_image, page_xywh, page_image_info = self.workspace.image_from_page(page, page_id, feature_filter='binarized,deskewed,cropped') 
+            page_image, page_xywh, page_image_info = self.workspace.image_from_page(page, page_id, feature_filter ='binarized,deskewed,cropped') 
 
             #Display Warning If image segment results already exist or not in StructMap?
             regions = page.get_TextRegion() + page.get_TableRegion()
@@ -141,11 +139,13 @@ def _process_segment(self,page_image, page, page_xywh, page_id, input_file, n, m
             else:
                 LOG.warning('keeping existing TextRegions in page "%s"', page_id)
                 return
-
-        border_coords = page.get_Border().get_Coords()
-        border_points = polygon_from_points(border_coords.get_points())
-
-        border = Polygon(border_points)
+        #check if border exists
+        if page.get_Border():
+            border_coords = page.get_Border().get_Coords()
+            border_points = polygon_from_points(border_coords.get_points())
+
+            border = Polygon(border_points)
+
         img_array = ocrolib.pil2array(page_image)
         if len(img_array.shape) <= 2:
             img_array = np.stack((img_array,)*3, axis=-1)
@@ -160,6 +160,12 @@ def _process_segment(self,page_image, page, page_xywh, page_id, input_file, n, m
             width,height,_ = img_array.shape
             min_x = r['rois'][i][0]
             min_y = r['rois'][i][1]
+            max_x = r['rois'][i][2]
+            max_y = r['rois'][i][3]
+            if (min_x - 5) > width and r['class_ids'][i] == 2:
+                min_x-=5
+            if (max_x + 10) < width and r['class_ids'][i] == 2:
+                min_x+=10
             reading_order.append((min_y, min_x))
 
         reading_order = sorted(reading_order, key=lambda reading_order:(reading_order[0], reading_order[1]))
@@ -173,11 +179,18 @@ def _process_segment(self,page_image, page, page_xywh, page_id, input_file, n, m
             min_y = r['rois'][i][1]
             max_x = r['rois'][i][2]
             max_y = r['rois'][i][3]
+            if (min_x - 5) > width and r['class_ids'][i] == 2:
+                min_x-=5
+            if (max_x + 10) < width and r['class_ids'][i] == 2:
+                min_x+=10
             region_polygon = [[min_x, min_y], [max_x, min_y], [max_x, max_y], [min_x, max_y]]
 
-            cut_region_polygon = border.intersection(Polygon(region_polygon))
-            if cut_region_polygon.is_empty:
-                continue
+            if border:
+                cut_region_polygon = border.intersection(Polygon(region_polygon))
+                if cut_region_polygon.is_empty:
+                    continue
+            else:
+                cut_region_polygon = Polygon(region_polygon)
 
             order_index = reading_order.index((min_y, min_x))
             region_id = '%s_region%04d' % (page_id, order_index)
@@ -195,6 +208,11 @@ def _process_segment(self,page_image, page, page_xywh, page_id, input_file, n, m
             min_y = r['rois'][i][1]
             max_x = r['rois'][i][2]
             max_y = r['rois'][i][3]
+
+            if (min_x - 5) > width and r['class_ids'][i] == 2:
+                min_x-=5
+            if (max_x + 10) < width and r['class_ids'][i] == 2:
+                min_x+=10
             region_polygon = [[min_x, min_y], [max_x, min_y], [max_x, max_y], [min_x, max_y]]
 
             cut_region_polygon = border.intersection(Polygon(region_polygon))
@@ -207,11 +225,7 @@ def _process_segment(self,page_image, page, page_xywh, page_id, input_file, n, m
 
             read_order = reading_order.index((min_y, min_x))
 
-            #small post-processing incase of paragrapgh to not cut last alphabets
-            if (min_x - 5) > width and r['class_ids'][i] == 2:
-                min_x-=5
-            if (max_x + 10) < width and r['class_ids'][i] == 2:
-                min_x+=10
+
 
 
 

ocrd_anybaseocr/cli/ocrd_anybaseocr_cropping.py

@@ -452,7 +452,7 @@ def process(self):
             page = pcgts.get_Page()
 
 
-            page_image, page_xywh, page_image_info = self.workspace.image_from_page(page, page_id, feature_filter='cropped') 
+            page_image, page_xywh, page_image_info = self.workspace.image_from_page(page, page_id, feature_filter='cropped',feature_selector='binarized,deskewed') 
 
 
             if oplevel=="page":

ocrd_anybaseocr/cli/ocrd_anybaseocr_deskew.py

@@ -112,7 +112,7 @@ def process(self):
             angle = page.get_orientation()
             if angle:
                 LOG.warning('Overwriting existing deskewing angle: %i', angle)
-            page_image, page_xywh, page_image_info = self.workspace.image_from_page(page, page_id, feature_filter='deskewed')
+            page_image, page_xywh, page_image_info = self.workspace.image_from_page(page, page_id, feature_filter='deskewed,cropped',feature_selector='binarized')
 
 
             if oplevel=="page":

ocrd_anybaseocr/cli/ocrd_anybaseocr_layout_analysis.py

@@ -204,7 +204,6 @@ def process(self):
         if not tf.test.is_gpu_available():
             LOG.error("Your system has no CUDA installed. No GPU detected.")
             sys.exit(1)
-
         model_path = Path(self.parameter['model_path'])
         class_mapper_path = Path(self.parameter['class_mapping_path'])
         if not Path(model_path).is_file():
@@ -229,8 +228,24 @@ def process(self):
             fname = pcgts.get_Page().imageFilename            
             LOG.info("CURRENT INPUT FILE %s", fname)
             size = 600, 500
-            img = Image.open(fname)
-            img_array = ocrolib.pil2array(img.resize((500, 600), Image.ANTIALIAS))
+
+            metadata = pcgts.get_Metadata()
+            metadata.add_MetadataItem(
+                    MetadataItemType(type_="processingStep",
+                                     name=self.ocrd_tool['steps'][0],
+                                     value=TOOL,                                     
+                                     Labels=[LabelsType(#externalRef="parameter",
+                                                        Label=[LabelType(type_=name,
+                                                                         value=self.parameter[name])
+                                                               for name in self.parameter.keys()])]))
+
+            page = pcgts.get_Page()
+            LOG.info("INPUT FILE %s", input_file.pageId or input_file.ID)
+
+            page_image, page_xywh, page_image_info = self.workspace.image_from_page(page, page_id, feature_selector='binarized,deskewed')
+
+
+            img_array = ocrolib.pil2array(page_image.resize((500, 600), Image.ANTIALIAS))
             img_array = img_array * 1./255.
             img_array = img_array[np.newaxis, :, :, np.newaxis]            
             results = self.start_test(model, img_array, fname, label_mapping)

ocrd_anybaseocr/cli/ocrd_anybaseocr_textline.py

@@ -84,11 +84,12 @@ def process(self):
             page = pcgts.get_Page()
             LOG.info("INPUT FILE %s", input_file.pageId or input_file.ID)
 
-            page_image, page_xywh, page_image_info = self.workspace.image_from_page(page, page_id, feature_filter='tiseged')
+            page_image, page_xywh, page_image_info = self.workspace.image_from_page(page, page_id, feature_selector='binarized,deskewed,cropped')
 
             if oplevel == 'page':
                 LOG.warning("Operation level should be region.")
-                break
+                self._process_segment(page_image, page,None, page_xywh, page_id, input_file, n)
+
             else:
                 regions = page.get_TextRegion()
                 if not regions:
@@ -110,8 +111,11 @@ def process(self):
                         y_max = page_image.size[1]-1
 
                     img__ = page_image.crop((x_min,y_min,x_max,y_max))
+                    # page_image = page_image.crop((x_min,y_min,x_max,y_max))
 
+
                     region_image, region_xywh = self.workspace.image_from_segment(region, page_image, page_xywh)
+                    # region_image = region_image.crop((x_min,y_min,x_max,y_max))
                     #region_image, region_xywh = self.workspace.image_from_segment(region, page_image, page_xywh)            
                     # TODO: not tested on regions
                     #self._process_segment(region_image, page, region, region_xywh, region.id, input_file, k)
@@ -183,9 +187,9 @@ def _process_segment(self, page_image, page, textregion, region_xywh, page_id, i
             line_polygon = coordinates_for_segment(line_polygon, page_image, region_xywh)
             line_points = points_from_polygon(line_polygon)
 
-            img = binary[l.bounds[0],l.bounds[1]]
-            img = (1-img) * (-1)
+            img = cleaned[l.bounds[0],l.bounds[1]]
             img = np.array(255*(img>ocrolib.midrange(img)),'B')
+            img = 255-img
             img = ocrolib.array2pil(img)
 
             file_id = input_file.ID.replace(self.input_file_grp, self.image_grp)

ocrd_anybaseocr/cli/ocrd_anybaseocr_tiseg.py

@@ -80,7 +80,7 @@ def process(self):
             page = pcgts.get_Page()
             LOG.info("INPUT FILE %s", input_file.pageId or input_file.ID)
 
-            page_image, page_xywh, page_image_info = self.workspace.image_from_page(page, page_id, feature_filter='tiseged')            
+            page_image, page_xywh, page_image_info = self.workspace.image_from_page(page, page_id, feature_selector='binarized,deskewed,cropped')            
             if oplevel == 'page':
                 self._process_segment(page_image, page, page_xywh, page_id, input_file, n)
             else:
@@ -129,7 +129,7 @@ def _process_segment(self,page_image, page, page_xywh, page_id, input_file, n):
         text_part = array((1-I*(1-Iseedfill)), dtype=int)
         text_part[0, 0] = 0  # only for visualisation purpose
 
-        page_xywh['features'] += ',tiseged'
+        # page_xywh['features'] += ',tiseged'
 
         bin_array = array(255*(text_part>ocrolib.midrange(text_part)),'B')
         bin_image = ocrolib.array2pil(bin_array)