🚧 WIP: Migrate to using ocrd:all image - ocrd_anybaseocr

Dockerfile-ocrd_anybaseocr

@@ -1,19 +0,0 @@
-ARG GIT_COMMIT="latest"
-FROM quratorspk/ocrd-galley-core-cuda12.1:$GIT_COMMIT
-
-ARG PIP_INSTALL="pip install --no-cache-dir"
-ARG OCRD_ANYBASEOCR_VERSION="1.8.2"
-
-
-
-# Build pip installable stuff
-RUN ${PIP_INSTALL} \
-    "ocrd_anybaseocr == ${OCRD_ANYBASEOCR_VERSION}"
-
-
-# Check pip dependencies
-RUN pip check
-
-
-# Default command
-CMD ["ocrd-anybaseocr-crop"]

test-ocrd_anybaseocr.sh

@@ -0,0 +1,16 @@
+#!/bin/sh
+set -ex
+
+test_id=`basename $0`
+cd `mktemp -d /tmp/$test_id-XXXXX`
+
+# Prepare processors
+
+# Prepare test workspace
+wget https://qurator-data.de/examples/actevedef_718448162.first-page.zip
+unzip actevedef_718448162.first-page.zip
+cd actevedef_718448162.first-page
+
+# Run tests
+ocrd-anybaseocr-binarize -I OCR-D-IMG -O OCR-D-BIN -P operation_level page -P threshold 0.3
+ocrd-anybaseocr-deskew -I OCR-D-BIN -O OCR-D-DESKEW -P maxskew 5.0 -P skewsteps 20 -P operation_level page

wrapper/qurator/ocrd_galley/sub_images.py

@@ -32,6 +32,7 @@ sub_images = {
         "ocrd-skimage-binarize": "ocrd_wrap",
         "ocrd-skimage-denoise": "ocrd_wrap",
         "ocrd-eynollah-segment": "eynollah",
+        "ocrd-anybaseocr-binarize": "ocrd_anybaseocr",
         "ocrd-anybaseocr-crop": "ocrd_anybaseocr",
         "ocrd-anybaseocr-deskew": "ocrd_anybaseocr",
         "ocrd-trocr-recognize": "ocrd_trocr",