Marmelator/cv-analysis-service
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 37 Wiki Activity

keyword 'show' to fix annotation script without causing problems for non-script usage

Browse Source
This commit is contained in:
Isaac Riley 2022-04-11 09:44:47 +02:00
parent 64258ed6e1
commit 0b96980cc5
6 changed files with 8 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
.gitignore vendored
View File

@ -21,3 +21,4 @@ build_venv/
/cv_analysis.egg-info/PKG-INFO
/cv_analysis.egg-info/SOURCES.txt
/cv_analysis.egg-info/top_level.txt
/.vscode/

2
cv_analysis/figure_detection.py
View File

@ -28,7 +28,7 @@ def detect_figures(image: np.array):
return list(rects)
def detect_figures_in_pdf(pdf_path, page_index=1, show=True):
def detect_figures_in_pdf(pdf_path, page_index=1, show=False):
page = pdf2image.convert_from_path(pdf_path, first_page=page_index + 1, last_page=page_index + 1)[0]
page = np.array(page)

2
cv_analysis/redaction_detection.py
View File

@ -36,7 +36,7 @@ def find_redactions(image: np.array, min_normalized_area=200000):
return []
def annotate_redactions_in_pdf(pdf_path, page_index=1, show=True):
def annotate_redactions_in_pdf(pdf_path, page_index=1, show=False):
page = pdf2image.convert_from_path(pdf_path, first_page=page_index + 1, last_page=page_index + 1)[0]
page = np.array(page)

2
cv_analysis/table_parsing.py
View File

@ -141,7 +141,7 @@ def parse_table(image: np.array, show=False):
return list(rects)
def annotate_tables_in_pdf(pdf_path, page_index=0, deskew=False, show=True):
def annotate_tables_in_pdf(pdf_path, page_index=0, deskew=False, show=False):
page = pdf2image.convert_from_path(pdf_path, first_page=page_index + 1, last_page=page_index + 1)[0]
page = np.array(page)
if deskew:

8
scripts/annotate.py
View File

@ -20,10 +20,10 @@ def parse_args():
if __name__ == "__main__":
args = parse_args()
if args.type == "table":
annotate_tables_in_pdf(args.pdf_path, page_index=args.page_index)
annotate_tables_in_pdf(args.pdf_path, page_index=args.page_index, show=True)
elif args.type == "redaction":
annotate_redactions_in_pdf(args.pdf_path, page_index=args.page_index)
annotate_redactions_in_pdf(args.pdf_path, page_index=args.page_index, show=True)
elif args.type == "layout":
annotate_layout_in_pdf(args.pdf_path, page_index=args.page_index)
annotate_layout_in_pdf(args.pdf_path, page_index=args.page_index, show=True)
elif args.type == "figure":
detect_figures_in_pdf(args.pdf_path, page_index=args.page_index)
detect_figures_in_pdf(args.pdf_path, page_index=args.page_index, show=True)

6
src/run_service.py
View File

@ -2,7 +2,6 @@ import json
import tracemalloc
from sys import getsizeof
import logging
from typing import List
from flask import Flask, request, jsonify
from prometheus_client import Counter, Gauge
from prometheus_flask_exporter import PrometheusMetrics
@ -21,15 +20,10 @@ from cv_analysis.config import CONFIG
def suppress_user_warnings():
import warnings
warnings.filterwarnings("ignore")
def main():
run_server()
def run_server():
file_counter = Counter("cv_analysis_file_counter", "count processed files")
# page_counter = Counter("cv_analysis_page_counter", "count pages from processed files")
ram_metric = Gauge("cv_analysis_memory_usage", "Memory usage in Mb")