0.5

Signed-off-by: Jerome Flesch <[email protected]>

Author: jflesch

ChangeLog

@@ -1,3 +1,7 @@
+14/12/2017 - 0.5:
+- Tesseract/Libtesseract + LineBoxBuilder: Add confidence scores to
+  every word boxes and to hOCR files
+
 13/05/2017 - 0.4.7:
 - Tesseract 4.00.00alpha:
   - Version parsing: Ignore suffix (so '4.00.00alpha' == (4, 0, 0))

README.markdown

@@ -107,8 +107,13 @@ line_and_word_boxes = tool.image_to_string(
 #   line.content is the whole text of the line
 #   line.position is the position of the whole line on the page (in pixels)
 #
-# Beware that some OCR tools (Tesseract for instance)
-# may return empty boxes
+# Each word box object has an attribute 'confidence' giving the confidence
+# score provided by the OCR tool. Confidence score depends entirely on
+# the OCR tool. Only supported with Tesseract and Libtesseract (always 0
+# with Cuneiform).
+#
+# Beware that some OCR tools (Tesseract for instance) may return boxes
+# with an empty content.
 
 # Digits - Only Tesseract (not 'libtesseract' yet !)
 digits = tool.image_to_string(

setup.py

@@ -11,12 +11,13 @@
     # - ChangeLog
     # - push
     # - tag
-    version="0.4.7",
+    # - python3 ./setup.py sdist upload
+    version="0.5",
     description=("A Python wrapper for OCR engines (Tesseract, Cuneiform,"
                  " etc)"),
     keywords="tesseract cuneiform ocr",
     url="https://github.com/openpaperwork/pyocr",
-    download_url="https://github.com/openpaperwork/pyocr/archive/0.4.7.zip",
+    download_url="https://github.com/openpaperwork/pyocr/archive/0.5.zip",
     classifiers=[
         "Development Status :: 5 - Production/Stable",
         "Intended Audience :: Developers",

src/pyocr/pyocr.py

@@ -62,7 +62,7 @@
     cuneiform,
 ]
 
-VERSION = (0, 4, 7)
+VERSION = (0, 5, 0)
 
 
 def get_available_tools():