Added opencv installation to dockerfile and reverted to slim-bookworm

Dockerfile

@@ -1,11 +1,12 @@
-#FROM public.ecr.aws/docker/library/python:3.11.9-slim-bookworm
-FROM public.ecr.aws/docker/library/python:3.11.9
+FROM public.ecr.aws/docker/library/python:3.11.9-slim-bookworm
 
 # Install system dependencies. Need to specify -y for poppler to get it to install
 RUN apt-get update \
     && apt-get install -y \
         tesseract-ocr -y \
         poppler-utils -y \
+		libgl1-mesa-glx -y \
+		libglib2.0-0 -y \
     && apt-get clean \
     && rm -rf /var/lib/apt/lists/*
 

README.md

@@ -16,3 +16,4 @@ Take an image-based or text-based PDF document and redact any personal informati
 
 WARNING: This is a beta product. It is not 100% accurate, and it will miss some personal information. It is essential that all outputs are checked **by a human** to ensure that all personal information has been removed.
 
+Other redaction entities are possible to include in this app easily, especially country-specific entities. If you want to use these, clone the repo locally and add entity names from [this link](https://microsoft.github.io/presidio/supported_entities/) to the 'full_entity_list' variable in app.py.

requirements.txt

@@ -1,6 +1,6 @@
 pdfminer.six==20231228
 pdf2image==1.17.0
-#img2pdf==0.5.1
+opencv-python
 presidio_analyzer==2.2.351
 presidio_anonymizer==2.2.351
 presidio-image-redactor==0.0.52