check_dpi: use OcrdExif instead identify callout

sbb_newspapers_org_image/eynollah.py

@@ -12,8 +12,9 @@ import time
 import warnings
 from pathlib import Path
 from multiprocessing import Process, Queue, cpu_count
-from ocrd_utils import getLogger
 
+from lxml import etree as ET
+from ocrd_utils import getLogger
 import cv2
 import numpy as np
 
@@ -27,14 +28,6 @@ import tensorflow as tf
 tf.get_logger().setLevel("ERROR")
 warnings.filterwarnings("ignore")
 
-from scipy.signal import find_peaks
-from scipy.ndimage import gaussian_filter1d
-from shapely import geometry
-from lxml import etree as ET
-from matplotlib import pyplot, transforms
-import matplotlib.patches as mpatches
-import imutils
-
 from .utils.contour import (
     contours_in_same_horizon,
     filter_contours_area_of_image_interiors,
@@ -115,7 +108,7 @@ from .utils import (
 )
 
 from .utils.xml import create_page_xml
-
+from .utils.pil_cv2 import check_dpi
 from .plot import EynollahPlotter
 
 SLOPE_THRESHOLD = 0.13
@@ -275,11 +268,6 @@ class eynollah:
 
             return prediction_true
 
-    def check_dpi(self):
-        self.logger.debug("enter check_dpi")
-        dpi = os.popen('identify -format "%x " ' + self.image_filename).read()
-        return int(float(dpi))
-
     def calculate_width_height_by_columns(self, img, num_col, width_early, label_p_pred):
         self.logger.debug("enter calculate_width_height_by_columns")
         if num_col == 1 and width_early < 1100:
@@ -389,7 +377,7 @@ class eynollah:
 
     def resize_and_enhance_image_with_column_classifier(self):
         self.logger.debug("enter resize_and_enhance_image_with_column_classifier")
-        dpi = self.check_dpi()
+        dpi = check_dpi(self.image_filename)
         self.logger.info("Detected %s DPI" % dpi)
         img = cv2.imread(self.image_filename)
 

sbb_newspapers_org_image/utils/pil_cv2.py

@@ -0,0 +1,24 @@
+from PIL import Image
+import numpy as np
+from ocrd_models import OcrdExif
+from cv2 import COLOR_GRAY2BGR, COLOR_RGB2BGR, cvtColor, imread
+
+# from sbb_binarization
+
+def cv2pil(img):
+    return Image.fromarray(img.astype('uint8'))
+
+def pil2cv(img):
+    # from ocrd/workspace.py
+    color_conversion = COLOR_GRAY2BGR if img.mode in ('1', 'L') else  COLOR_RGB2BGR
+    pil_as_np_array = np.array(img).astype('uint8') if img.mode == '1' else np.array(img)
+    return cvtColor(pil_as_np_array, color_conversion)
+
+def check_dpi(image_filename):
+    exif = OcrdExif(Image.open(image_filename))
+    print(exif.to_xml())
+    resolution = exif.resolution
+    if exif.resolutionUnit == 'cm':
+        resolution /= 2.54
+    return int(resolution)
+

tests/test_dpi.py

@@ -0,0 +1,10 @@
+from pathlib import Path
+from sbb_newspapers_org_image.utils.pil_cv2 import check_dpi
+from tests.base import main
+
+def test_dpi():
+    fpath = Path(__file__).parent.joinpath('resources', 'kant_aufklaerung_1784_0020.tif')
+    assert 300 == check_dpi(str(fpath))
+
+if __name__ == '__main__':
+    main(__file__)