mirror of
https://github.com/qurator-spk/eynollah.git
synced 2025-12-01 08:44:13 +01:00
reorganize cli
This commit is contained in:
kba
parent
5a1900e664
commit
82266f8234
10 changed files with 621 additions and 602 deletions
|
|
@ -1,602 +0,0 @@
|
||||||
from dataclasses import dataclass
|
|
||||||
import logging
|
|
||||||
import sys
|
|
||||||
import os
|
|
||||||
from typing import Union
|
|
||||||
|
|
||||||
import click
|
|
||||||
|
|
||||||
# NOTE: For debugging/predictable order of imports
|
|
||||||
from .eynollah_imports import imported_libs
|
|
||||||
from .model_zoo import EynollahModelZoo
|
|
||||||
from .cli_models import models_cli
|
|
||||||
|
|
||||||
@dataclass()
|
|
||||||
class EynollahCliCtx:
|
|
||||||
"""
|
|
||||||
Holds options relevant for all eynollah subcommands
|
|
||||||
"""
|
|
||||||
model_zoo: EynollahModelZoo
|
|
||||||
log_level : Union[str, None] = 'INFO'
|
|
||||||
|
|
||||||
|
|
||||||
@click.group()
|
|
||||||
@click.option(
|
|
||||||
"--model-basedir",
|
|
||||||
"-m",
|
|
||||||
help="directory of models",
|
|
||||||
# NOTE: not mandatory to exist so --help for subcommands works but will log a warning
|
|
||||||
# and raise exception when trying to load models in the CLI
|
|
||||||
# type=click.Path(exists=True),
|
|
||||||
default=f'{os.getcwd()}/models_eynollah',
|
|
||||||
)
|
|
||||||
@click.option(
|
|
||||||
"--model-overrides",
|
|
||||||
"-mv",
|
|
||||||
help="override default versions of model categories, syntax is 'CATEGORY VARIANT PATH', e.g 'region light /path/to/model'. See eynollah list-models for the full list",
|
|
||||||
type=(str, str, str),
|
|
||||||
multiple=True,
|
|
||||||
)
|
|
||||||
@click.option(
|
|
||||||
"--log_level",
|
|
||||||
"-l",
|
|
||||||
type=click.Choice(['OFF', 'DEBUG', 'INFO', 'WARN', 'ERROR']),
|
|
||||||
help="Override log level globally to this",
|
|
||||||
)
|
|
||||||
@click.pass_context
|
|
||||||
def main(ctx, model_basedir, model_overrides, log_level):
|
|
||||||
"""
|
|
||||||
eynollah - Document Layout Analysis, Image Enhancement, OCR
|
|
||||||
"""
|
|
||||||
# Initialize logging
|
|
||||||
console_handler = logging.StreamHandler(sys.stdout)
|
|
||||||
console_handler.setLevel(logging.NOTSET)
|
|
||||||
formatter = logging.Formatter('%(asctime)s.%(msecs)03d %(levelname)s %(name)s - %(message)s', datefmt='%H:%M:%S')
|
|
||||||
console_handler.setFormatter(formatter)
|
|
||||||
logging.getLogger('eynollah').addHandler(console_handler)
|
|
||||||
logging.getLogger('eynollah').setLevel(log_level or logging.INFO)
|
|
||||||
# Initialize model zoo
|
|
||||||
model_zoo = EynollahModelZoo(basedir=model_basedir, model_overrides=model_overrides)
|
|
||||||
# Initialize CLI context
|
|
||||||
ctx.obj = EynollahCliCtx(
|
|
||||||
model_zoo=model_zoo,
|
|
||||||
log_level=log_level,
|
|
||||||
)
|
|
||||||
|
|
||||||
main.add_command(models_cli, 'models')
|
|
||||||
|
|
||||||
@main.command()
|
|
||||||
@click.option(
|
|
||||||
"--input",
|
|
||||||
"-i",
|
|
||||||
help="PAGE-XML input filename",
|
|
||||||
type=click.Path(exists=True, dir_okay=False),
|
|
||||||
)
|
|
||||||
@click.option(
|
|
||||||
"--dir_in",
|
|
||||||
"-di",
|
|
||||||
help="directory of PAGE-XML input files (instead of --input)",
|
|
||||||
type=click.Path(exists=True, file_okay=False),
|
|
||||||
)
|
|
||||||
@click.option(
|
|
||||||
"--out",
|
|
||||||
"-o",
|
|
||||||
help="directory for output images",
|
|
||||||
type=click.Path(exists=True, file_okay=False),
|
|
||||||
required=True,
|
|
||||||
)
|
|
||||||
@click.pass_context
|
|
||||||
def machine_based_reading_order(ctx, input, dir_in, out):
|
|
||||||
"""
|
|
||||||
Generate ReadingOrder with a ML model
|
|
||||||
"""
|
|
||||||
from eynollah.mb_ro_on_layout import machine_based_reading_order_on_layout
|
|
||||||
assert bool(input) != bool(dir_in), "Either -i (single input) or -di (directory) must be provided, but not both."
|
|
||||||
orderer = machine_based_reading_order_on_layout(model_zoo=ctx.obj.model_zoo)
|
|
||||||
orderer.run(xml_filename=input,
|
|
||||||
dir_in=dir_in,
|
|
||||||
dir_out=out,
|
|
||||||
)
|
|
||||||
|
|
||||||
|
|
||||||
@main.command()
|
|
||||||
@click.option('--patches/--no-patches', default=True, help='by enabling this parameter you let the model to see the image in patches.')
|
|
||||||
@click.option(
|
|
||||||
"--input-image", "--image",
|
|
||||||
"-i",
|
|
||||||
help="input image filename",
|
|
||||||
type=click.Path(exists=True, dir_okay=False)
|
|
||||||
)
|
|
||||||
@click.option(
|
|
||||||
"--dir_in",
|
|
||||||
"-di",
|
|
||||||
help="directory of input images (instead of --image)",
|
|
||||||
type=click.Path(exists=True, file_okay=False),
|
|
||||||
)
|
|
||||||
@click.option(
|
|
||||||
"--output",
|
|
||||||
"-o",
|
|
||||||
help="output image (if using -i) or output image directory (if using -di)",
|
|
||||||
type=click.Path(file_okay=True, dir_okay=True),
|
|
||||||
required=True,
|
|
||||||
)
|
|
||||||
@click.option(
|
|
||||||
'-M',
|
|
||||||
'--mode',
|
|
||||||
type=click.Choice(['single', 'multi']),
|
|
||||||
default='single',
|
|
||||||
help="Whether to use the (newer and faster) single-model binarization or the (slightly better) multi-model binarization"
|
|
||||||
)
|
|
||||||
@click.pass_context
|
|
||||||
def binarization(
|
|
||||||
ctx,
|
|
||||||
patches,
|
|
||||||
input_image,
|
|
||||||
mode,
|
|
||||||
dir_in,
|
|
||||||
output,
|
|
||||||
):
|
|
||||||
"""
|
|
||||||
Binarize images with a ML model
|
|
||||||
"""
|
|
||||||
from eynollah.sbb_binarize import SbbBinarizer
|
|
||||||
assert bool(input_image) != bool(dir_in), "Either -i (single input) or -di (directory) must be provided, but not both."
|
|
||||||
binarizer = SbbBinarizer(model_zoo=ctx.obj.model_zoo, mode=mode)
|
|
||||||
binarizer.run(
|
|
||||||
image_path=input_image,
|
|
||||||
use_patches=patches,
|
|
||||||
output=output,
|
|
||||||
dir_in=dir_in
|
|
||||||
)
|
|
||||||
|
|
||||||
|
|
||||||
@main.command()
|
|
||||||
@click.option(
|
|
||||||
"--image",
|
|
||||||
"-i",
|
|
||||||
help="input image filename",
|
|
||||||
type=click.Path(exists=True, dir_okay=False),
|
|
||||||
)
|
|
||||||
|
|
||||||
@click.option(
|
|
||||||
"--out",
|
|
||||||
"-o",
|
|
||||||
help="directory for output PAGE-XML files",
|
|
||||||
type=click.Path(exists=True, file_okay=False),
|
|
||||||
required=True,
|
|
||||||
)
|
|
||||||
@click.option(
|
|
||||||
"--overwrite",
|
|
||||||
"-O",
|
|
||||||
help="overwrite (instead of skipping) if output xml exists",
|
|
||||||
is_flag=True,
|
|
||||||
)
|
|
||||||
@click.option(
|
|
||||||
"--dir_in",
|
|
||||||
"-di",
|
|
||||||
help="directory of input images (instead of --image)",
|
|
||||||
type=click.Path(exists=True, file_okay=False),
|
|
||||||
)
|
|
||||||
@click.option(
|
|
||||||
"--num_col_upper",
|
|
||||||
"-ncu",
|
|
||||||
help="lower limit of columns in document image",
|
|
||||||
)
|
|
||||||
@click.option(
|
|
||||||
"--num_col_lower",
|
|
||||||
"-ncl",
|
|
||||||
help="upper limit of columns in document image",
|
|
||||||
)
|
|
||||||
@click.option(
|
|
||||||
"--save_org_scale/--no_save_org_scale",
|
|
||||||
"-sos/-nosos",
|
|
||||||
is_flag=True,
|
|
||||||
help="if this parameter set to true, this tool will save the enhanced image in org scale.",
|
|
||||||
)
|
|
||||||
@click.pass_context
|
|
||||||
def enhancement(ctx, image, out, overwrite, dir_in, num_col_upper, num_col_lower, save_org_scale):
|
|
||||||
"""
|
|
||||||
Enhance image
|
|
||||||
"""
|
|
||||||
assert bool(image) != bool(dir_in), "Either -i (single input) or -di (directory) must be provided, but not both."
|
|
||||||
from .image_enhancer import Enhancer
|
|
||||||
enhancer = Enhancer(
|
|
||||||
model_zoo=ctx.obj.model_zoo,
|
|
||||||
num_col_upper=num_col_upper,
|
|
||||||
num_col_lower=num_col_lower,
|
|
||||||
save_org_scale=save_org_scale,
|
|
||||||
)
|
|
||||||
enhancer.run(overwrite=overwrite,
|
|
||||||
dir_in=dir_in,
|
|
||||||
image_filename=image,
|
|
||||||
dir_out=out,
|
|
||||||
)
|
|
||||||
|
|
||||||
@main.command()
|
|
||||||
@click.option(
|
|
||||||
"--image",
|
|
||||||
"-i",
|
|
||||||
help="input image filename",
|
|
||||||
type=click.Path(exists=True, dir_okay=False),
|
|
||||||
)
|
|
||||||
|
|
||||||
@click.option(
|
|
||||||
"--out",
|
|
||||||
"-o",
|
|
||||||
help="directory for output PAGE-XML files",
|
|
||||||
type=click.Path(exists=True, file_okay=False),
|
|
||||||
required=True,
|
|
||||||
)
|
|
||||||
@click.option(
|
|
||||||
"--overwrite",
|
|
||||||
"-O",
|
|
||||||
help="overwrite (instead of skipping) if output xml exists",
|
|
||||||
is_flag=True,
|
|
||||||
)
|
|
||||||
@click.option(
|
|
||||||
"--dir_in",
|
|
||||||
"-di",
|
|
||||||
help="directory of input images (instead of --image)",
|
|
||||||
type=click.Path(exists=True, file_okay=False),
|
|
||||||
)
|
|
||||||
@click.option(
|
|
||||||
"--save_images",
|
|
||||||
"-si",
|
|
||||||
help="if a directory is given, images in documents will be cropped and saved there",
|
|
||||||
type=click.Path(exists=True, file_okay=False),
|
|
||||||
)
|
|
||||||
@click.option(
|
|
||||||
"--save_layout",
|
|
||||||
"-sl",
|
|
||||||
help="if a directory is given, plot of layout will be saved there",
|
|
||||||
type=click.Path(exists=True, file_okay=False),
|
|
||||||
)
|
|
||||||
@click.option(
|
|
||||||
"--save_deskewed",
|
|
||||||
"-sd",
|
|
||||||
help="if a directory is given, deskewed image will be saved there",
|
|
||||||
type=click.Path(exists=True, file_okay=False),
|
|
||||||
)
|
|
||||||
@click.option(
|
|
||||||
"--save_all",
|
|
||||||
"-sa",
|
|
||||||
help="if a directory is given, all plots needed for documentation will be saved there",
|
|
||||||
type=click.Path(exists=True, file_okay=False),
|
|
||||||
)
|
|
||||||
@click.option(
|
|
||||||
"--save_page",
|
|
||||||
"-sp",
|
|
||||||
help="if a directory is given, page crop of image will be saved there",
|
|
||||||
type=click.Path(exists=True, file_okay=False),
|
|
||||||
)
|
|
||||||
@click.option(
|
|
||||||
"--enable-plotting/--disable-plotting",
|
|
||||||
"-ep/-noep",
|
|
||||||
is_flag=True,
|
|
||||||
help="If set, will plot intermediary files and images",
|
|
||||||
)
|
|
||||||
@click.option(
|
|
||||||
"--extract_only_images/--disable-extracting_only_images",
|
|
||||||
"-eoi/-noeoi",
|
|
||||||
is_flag=True,
|
|
||||||
help="If a directory is given, only images in documents will be cropped and saved there and the other processing will not be done",
|
|
||||||
)
|
|
||||||
@click.option(
|
|
||||||
"--allow-enhancement/--no-allow-enhancement",
|
|
||||||
"-ae/-noae",
|
|
||||||
is_flag=True,
|
|
||||||
help="if this parameter set to true, this tool would check that input image need resizing and enhancement or not. If so output of resized and enhanced image and corresponding layout data will be written in out directory",
|
|
||||||
)
|
|
||||||
@click.option(
|
|
||||||
"--curved-line/--no-curvedline",
|
|
||||||
"-cl/-nocl",
|
|
||||||
is_flag=True,
|
|
||||||
help="if this parameter set to true, this tool will try to return contoure of textlines instead of rectangle bounding box of textline. This should be taken into account that with this option the tool need more time to do process.",
|
|
||||||
)
|
|
||||||
@click.option(
|
|
||||||
"--textline_light/--no-textline_light",
|
|
||||||
"-tll/-notll",
|
|
||||||
is_flag=True,
|
|
||||||
help="if this parameter set to true, this tool will try to return contoure of textlines instead of rectangle bounding box of textline with a faster method.",
|
|
||||||
)
|
|
||||||
@click.option(
|
|
||||||
"--full-layout/--no-full-layout",
|
|
||||||
"-fl/-nofl",
|
|
||||||
is_flag=True,
|
|
||||||
help="if this parameter set to true, this tool will try to return all elements of layout.",
|
|
||||||
)
|
|
||||||
@click.option(
|
|
||||||
"--tables/--no-tables",
|
|
||||||
"-tab/-notab",
|
|
||||||
is_flag=True,
|
|
||||||
help="if this parameter set to true, this tool will try to detect tables.",
|
|
||||||
)
|
|
||||||
@click.option(
|
|
||||||
"--right2left/--left2right",
|
|
||||||
"-r2l/-l2r",
|
|
||||||
is_flag=True,
|
|
||||||
help="if this parameter set to true, this tool will extract right-to-left reading order.",
|
|
||||||
)
|
|
||||||
@click.option(
|
|
||||||
"--input_binary/--input-RGB",
|
|
||||||
"-ib/-irgb",
|
|
||||||
is_flag=True,
|
|
||||||
help="In general, eynollah uses RGB as input but if the input document is very dark, very bright or for any other reason you can turn on input binarization. When this flag is set, eynollah will binarize the RGB input document, you should always provide RGB images to eynollah.",
|
|
||||||
)
|
|
||||||
@click.option(
|
|
||||||
"--allow_scaling/--no-allow-scaling",
|
|
||||||
"-as/-noas",
|
|
||||||
is_flag=True,
|
|
||||||
help="if this parameter set to true, this tool would check the scale and if needed it will scale it to perform better layout detection",
|
|
||||||
)
|
|
||||||
@click.option(
|
|
||||||
"--headers_off/--headers-on",
|
|
||||||
"-ho/-noho",
|
|
||||||
is_flag=True,
|
|
||||||
help="if this parameter set to true, this tool would ignore headers role in reading order",
|
|
||||||
)
|
|
||||||
@click.option(
|
|
||||||
"--light_version/--original",
|
|
||||||
"-light/-org",
|
|
||||||
is_flag=True,
|
|
||||||
help="if this parameter set to true, this tool would use lighter version",
|
|
||||||
)
|
|
||||||
@click.option(
|
|
||||||
"--ignore_page_extraction/--extract_page_included",
|
|
||||||
"-ipe/-epi",
|
|
||||||
is_flag=True,
|
|
||||||
help="if this parameter set to true, this tool would ignore page extraction",
|
|
||||||
)
|
|
||||||
@click.option(
|
|
||||||
"--reading_order_machine_based/--heuristic_reading_order",
|
|
||||||
"-romb/-hro",
|
|
||||||
is_flag=True,
|
|
||||||
help="if this parameter set to true, this tool would apply machine based reading order detection",
|
|
||||||
)
|
|
||||||
@click.option(
|
|
||||||
"--num_col_upper",
|
|
||||||
"-ncu",
|
|
||||||
help="lower limit of columns in document image",
|
|
||||||
)
|
|
||||||
@click.option(
|
|
||||||
"--num_col_lower",
|
|
||||||
"-ncl",
|
|
||||||
help="upper limit of columns in document image",
|
|
||||||
)
|
|
||||||
@click.option(
|
|
||||||
"--threshold_art_class_layout",
|
|
||||||
"-tharl",
|
|
||||||
help="threshold of artifical class in the case of layout detection. The default value is 0.1",
|
|
||||||
)
|
|
||||||
@click.option(
|
|
||||||
"--threshold_art_class_textline",
|
|
||||||
"-thart",
|
|
||||||
help="threshold of artifical class in the case of textline detection. The default value is 0.1",
|
|
||||||
)
|
|
||||||
@click.option(
|
|
||||||
"--skip_layout_and_reading_order",
|
|
||||||
"-slro/-noslro",
|
|
||||||
is_flag=True,
|
|
||||||
help="if this parameter set to true, this tool will ignore layout detection and reading order. It means that textline detection will be done within printspace and contours of textline will be written in xml output file.",
|
|
||||||
)
|
|
||||||
@click.pass_context
|
|
||||||
def layout(
|
|
||||||
ctx,
|
|
||||||
image,
|
|
||||||
out,
|
|
||||||
overwrite,
|
|
||||||
dir_in,
|
|
||||||
save_images,
|
|
||||||
save_layout,
|
|
||||||
save_deskewed,
|
|
||||||
save_all,
|
|
||||||
extract_only_images,
|
|
||||||
save_page,
|
|
||||||
enable_plotting,
|
|
||||||
allow_enhancement,
|
|
||||||
curved_line,
|
|
||||||
textline_light,
|
|
||||||
full_layout,
|
|
||||||
tables,
|
|
||||||
right2left,
|
|
||||||
input_binary,
|
|
||||||
allow_scaling,
|
|
||||||
headers_off,
|
|
||||||
light_version,
|
|
||||||
reading_order_machine_based,
|
|
||||||
num_col_upper,
|
|
||||||
num_col_lower,
|
|
||||||
threshold_art_class_textline,
|
|
||||||
threshold_art_class_layout,
|
|
||||||
skip_layout_and_reading_order,
|
|
||||||
ignore_page_extraction,
|
|
||||||
):
|
|
||||||
"""
|
|
||||||
Detect Layout (with optional image enhancement and reading order detection)
|
|
||||||
"""
|
|
||||||
from .eynollah import Eynollah
|
|
||||||
assert enable_plotting or not save_layout, "Plotting with -sl also requires -ep"
|
|
||||||
assert enable_plotting or not save_deskewed, "Plotting with -sd also requires -ep"
|
|
||||||
assert enable_plotting or not save_all, "Plotting with -sa also requires -ep"
|
|
||||||
assert enable_plotting or not save_page, "Plotting with -sp also requires -ep"
|
|
||||||
assert enable_plotting or not save_images, "Plotting with -si also requires -ep"
|
|
||||||
assert enable_plotting or not allow_enhancement, "Plotting with -ae also requires -ep"
|
|
||||||
assert not enable_plotting or save_layout or save_deskewed or save_all or save_page or save_images or allow_enhancement, \
|
|
||||||
"Plotting with -ep also requires -sl, -sd, -sa, -sp, -si or -ae"
|
|
||||||
assert textline_light == light_version, "Both light textline detection -tll and light version -light must be set or unset equally"
|
|
||||||
assert not extract_only_images or not allow_enhancement, "Image extraction -eoi can not be set alongside allow_enhancement -ae"
|
|
||||||
assert not extract_only_images or not allow_scaling, "Image extraction -eoi can not be set alongside allow_scaling -as"
|
|
||||||
assert not extract_only_images or not light_version, "Image extraction -eoi can not be set alongside light_version -light"
|
|
||||||
assert not extract_only_images or not curved_line, "Image extraction -eoi can not be set alongside curved_line -cl"
|
|
||||||
assert not extract_only_images or not textline_light, "Image extraction -eoi can not be set alongside textline_light -tll"
|
|
||||||
assert not extract_only_images or not full_layout, "Image extraction -eoi can not be set alongside full_layout -fl"
|
|
||||||
assert not extract_only_images or not tables, "Image extraction -eoi can not be set alongside tables -tab"
|
|
||||||
assert not extract_only_images or not right2left, "Image extraction -eoi can not be set alongside right2left -r2l"
|
|
||||||
assert not extract_only_images or not headers_off, "Image extraction -eoi can not be set alongside headers_off -ho"
|
|
||||||
assert bool(image) != bool(dir_in), "Either -i (single input) or -di (directory) must be provided, but not both."
|
|
||||||
eynollah = Eynollah(
|
|
||||||
model_zoo=ctx.obj.model_zoo,
|
|
||||||
extract_only_images=extract_only_images,
|
|
||||||
enable_plotting=enable_plotting,
|
|
||||||
allow_enhancement=allow_enhancement,
|
|
||||||
curved_line=curved_line,
|
|
||||||
textline_light=textline_light,
|
|
||||||
full_layout=full_layout,
|
|
||||||
tables=tables,
|
|
||||||
right2left=right2left,
|
|
||||||
input_binary=input_binary,
|
|
||||||
allow_scaling=allow_scaling,
|
|
||||||
headers_off=headers_off,
|
|
||||||
light_version=light_version,
|
|
||||||
ignore_page_extraction=ignore_page_extraction,
|
|
||||||
reading_order_machine_based=reading_order_machine_based,
|
|
||||||
num_col_upper=num_col_upper,
|
|
||||||
num_col_lower=num_col_lower,
|
|
||||||
skip_layout_and_reading_order=skip_layout_and_reading_order,
|
|
||||||
threshold_art_class_textline=threshold_art_class_textline,
|
|
||||||
threshold_art_class_layout=threshold_art_class_layout,
|
|
||||||
)
|
|
||||||
eynollah.run(overwrite=overwrite,
|
|
||||||
image_filename=image,
|
|
||||||
dir_in=dir_in,
|
|
||||||
dir_out=out,
|
|
||||||
dir_of_cropped_images=save_images,
|
|
||||||
dir_of_layout=save_layout,
|
|
||||||
dir_of_deskewed=save_deskewed,
|
|
||||||
dir_of_all=save_all,
|
|
||||||
dir_save_page=save_page,
|
|
||||||
)
|
|
||||||
|
|
||||||
@main.command()
|
|
||||||
@click.option(
|
|
||||||
"--image",
|
|
||||||
"-i",
|
|
||||||
help="input image filename",
|
|
||||||
type=click.Path(exists=True, dir_okay=False),
|
|
||||||
)
|
|
||||||
@click.option(
|
|
||||||
"--dir_in",
|
|
||||||
"-di",
|
|
||||||
help="directory of input images (instead of --image)",
|
|
||||||
type=click.Path(exists=True, file_okay=False),
|
|
||||||
)
|
|
||||||
@click.option(
|
|
||||||
"--dir_in_bin",
|
|
||||||
"-dib",
|
|
||||||
help=("""
|
|
||||||
directory of binarized images (in addition to --dir_in for RGB
|
|
||||||
images; filename stems must match the RGB image files, with '.png'
|
|
||||||
\n
|
|
||||||
Perform prediction using both RGB and binary images.
|
|
||||||
(This does not necessarily improve results, however it may be beneficial
|
|
||||||
for certain document images.
|
|
||||||
"""),
|
|
||||||
|
|
||||||
type=click.Path(exists=True, file_okay=False),
|
|
||||||
)
|
|
||||||
@click.option(
|
|
||||||
"--dir_xmls",
|
|
||||||
"-dx",
|
|
||||||
help="directory of input PAGE-XML files (in addition to --dir_in; filename stems must match the image files, with '.xml' suffix).",
|
|
||||||
type=click.Path(exists=True, file_okay=False),
|
|
||||||
required=True,
|
|
||||||
)
|
|
||||||
@click.option(
|
|
||||||
"--out",
|
|
||||||
"-o",
|
|
||||||
help="directory for output PAGE-XML files",
|
|
||||||
type=click.Path(exists=True, file_okay=False),
|
|
||||||
required=True,
|
|
||||||
)
|
|
||||||
@click.option(
|
|
||||||
"--dir_out_image_text",
|
|
||||||
"-doit",
|
|
||||||
help="directory for output images, newly rendered with predicted text",
|
|
||||||
type=click.Path(exists=True, file_okay=False),
|
|
||||||
)
|
|
||||||
@click.option(
|
|
||||||
"--overwrite",
|
|
||||||
"-O",
|
|
||||||
help="overwrite (instead of skipping) if output xml exists",
|
|
||||||
is_flag=True,
|
|
||||||
)
|
|
||||||
@click.option(
|
|
||||||
"--tr_ocr",
|
|
||||||
"-trocr/-notrocr",
|
|
||||||
is_flag=True,
|
|
||||||
help="if this parameter set to true, transformer ocr will be applied, otherwise cnn_rnn model.",
|
|
||||||
)
|
|
||||||
@click.option(
|
|
||||||
"--export_textline_images_and_text",
|
|
||||||
"-etit/-noetit",
|
|
||||||
is_flag=True,
|
|
||||||
help="if this parameter set to true, images and text in xml will be exported into output dir. This files can be used for training a OCR engine.",
|
|
||||||
)
|
|
||||||
@click.option(
|
|
||||||
"--do_not_mask_with_textline_contour",
|
|
||||||
"-nmtc/-mtc",
|
|
||||||
is_flag=True,
|
|
||||||
help="if this parameter set to true, cropped textline images will not be masked with textline contour.",
|
|
||||||
)
|
|
||||||
@click.option(
|
|
||||||
"--batch_size",
|
|
||||||
"-bs",
|
|
||||||
help="number of inference batch size. Default b_s for trocr and cnn_rnn models are 2 and 8 respectively",
|
|
||||||
)
|
|
||||||
@click.option(
|
|
||||||
"--dataset_abbrevation",
|
|
||||||
"-ds_pref",
|
|
||||||
help="in the case of extracting textline and text from a xml GT file user can add an abbrevation of dataset name to generated dataset",
|
|
||||||
)
|
|
||||||
@click.option(
|
|
||||||
"--min_conf_value_of_textline_text",
|
|
||||||
"-min_conf",
|
|
||||||
help="minimum OCR confidence value. Text lines with a confidence value lower than this threshold will not be included in the output XML file.",
|
|
||||||
)
|
|
||||||
@click.pass_context
|
|
||||||
def ocr(
|
|
||||||
ctx,
|
|
||||||
image,
|
|
||||||
dir_in,
|
|
||||||
dir_in_bin,
|
|
||||||
dir_xmls,
|
|
||||||
out,
|
|
||||||
dir_out_image_text,
|
|
||||||
overwrite,
|
|
||||||
tr_ocr,
|
|
||||||
export_textline_images_and_text,
|
|
||||||
do_not_mask_with_textline_contour,
|
|
||||||
batch_size,
|
|
||||||
dataset_abbrevation,
|
|
||||||
min_conf_value_of_textline_text,
|
|
||||||
):
|
|
||||||
"""
|
|
||||||
Recognize text with a CNN/RNN or transformer ML model.
|
|
||||||
"""
|
|
||||||
assert not export_textline_images_and_text or not tr_ocr, "Exporting textline and text -etit can not be set alongside transformer ocr -tr_ocr"
|
|
||||||
# FIXME: refactor: move export_textline_images_and_text out of eynollah.py
|
|
||||||
# assert not export_textline_images_and_text or not model, "Exporting textline and text -etit can not be set alongside model -m"
|
|
||||||
assert not export_textline_images_and_text or not batch_size, "Exporting textline and text -etit can not be set alongside batch size -bs"
|
|
||||||
assert not export_textline_images_and_text or not dir_in_bin, "Exporting textline and text -etit can not be set alongside directory of bin images -dib"
|
|
||||||
assert not export_textline_images_and_text or not dir_out_image_text, "Exporting textline and text -etit can not be set alongside directory of images with predicted text -doit"
|
|
||||||
assert bool(image) != bool(dir_in), "Either -i (single image) or -di (directory) must be provided, but not both."
|
|
||||||
from .eynollah_ocr import Eynollah_ocr
|
|
||||||
eynollah_ocr = Eynollah_ocr(
|
|
||||||
model_zoo=ctx.obj.model_zoo,
|
|
||||||
tr_ocr=tr_ocr,
|
|
||||||
export_textline_images_and_text=export_textline_images_and_text,
|
|
||||||
do_not_mask_with_textline_contour=do_not_mask_with_textline_contour,
|
|
||||||
batch_size=batch_size,
|
|
||||||
pref_of_dataset=dataset_abbrevation,
|
|
||||||
min_conf_value_of_textline_text=min_conf_value_of_textline_text)
|
|
||||||
eynollah_ocr.run(overwrite=overwrite,
|
|
||||||
dir_in=dir_in,
|
|
||||||
dir_in_bin=dir_in_bin,
|
|
||||||
image_filename=image,
|
|
||||||
dir_xmls=dir_xmls,
|
|
||||||
dir_out_image_text=dir_out_image_text,
|
|
||||||
dir_out=out,
|
|
||||||
)
|
|
||||||
|
|
||||||
if __name__ == "__main__":
|
|
||||||
main()
|
|
||||||
21
src/eynollah/cli/__init__.py
Normal file
21
src/eynollah/cli/__init__.py
Normal file
|
|
@ -0,0 +1,21 @@
|
||||||
|
# NOTE: For predictable order of imports of torch/shapely/tensorflow
|
||||||
|
# this must be the first import of the CLI!
|
||||||
|
from ..eynollah_imports import imported_libs
|
||||||
|
from .cli_models import models_cli
|
||||||
|
from .cli_binarize import binarize_cli
|
||||||
|
|
||||||
|
from .cli import main
|
||||||
|
from .cli_binarize import binarize_cli
|
||||||
|
from .cli_enhance import enhance_cli
|
||||||
|
from .cli_layout import layout_cli
|
||||||
|
from .cli_ocr import ocr_cli
|
||||||
|
from .cli_readingorder import readingorder_cli
|
||||||
|
|
||||||
|
main.add_command(binarize_cli, 'binarization')
|
||||||
|
main.add_command(enhance_cli, 'enhancement')
|
||||||
|
main.add_command(layout_cli, 'layout')
|
||||||
|
main.add_command(readingorder_cli, 'machine-based-reading-order')
|
||||||
|
main.add_command(models_cli, 'models')
|
||||||
|
main.add_command(ocr_cli, 'ocr')
|
||||||
|
|
||||||
|
|
||||||
66
src/eynollah/cli/cli.py
Normal file
66
src/eynollah/cli/cli.py
Normal file
|
|
@ -0,0 +1,66 @@
|
||||||
|
from dataclasses import dataclass
|
||||||
|
import logging
|
||||||
|
import sys
|
||||||
|
import os
|
||||||
|
from typing import Union
|
||||||
|
|
||||||
|
import click
|
||||||
|
|
||||||
|
from ..model_zoo import EynollahModelZoo
|
||||||
|
from .cli_models import models_cli
|
||||||
|
|
||||||
|
@dataclass()
|
||||||
|
class EynollahCliCtx:
|
||||||
|
"""
|
||||||
|
Holds options relevant for all eynollah subcommands
|
||||||
|
"""
|
||||||
|
model_zoo: EynollahModelZoo
|
||||||
|
log_level : Union[str, None] = 'INFO'
|
||||||
|
|
||||||
|
|
||||||
|
@click.group()
|
||||||
|
@click.option(
|
||||||
|
"--model-basedir",
|
||||||
|
"-m",
|
||||||
|
help="directory of models",
|
||||||
|
# NOTE: not mandatory to exist so --help for subcommands works but will log a warning
|
||||||
|
# and raise exception when trying to load models in the CLI
|
||||||
|
# type=click.Path(exists=True),
|
||||||
|
default=f'{os.getcwd()}/models_eynollah',
|
||||||
|
)
|
||||||
|
@click.option(
|
||||||
|
"--model-overrides",
|
||||||
|
"-mv",
|
||||||
|
help="override default versions of model categories, syntax is 'CATEGORY VARIANT PATH', e.g 'region light /path/to/model'. See eynollah list-models for the full list",
|
||||||
|
type=(str, str, str),
|
||||||
|
multiple=True,
|
||||||
|
)
|
||||||
|
@click.option(
|
||||||
|
"--log_level",
|
||||||
|
"-l",
|
||||||
|
type=click.Choice(['OFF', 'DEBUG', 'INFO', 'WARN', 'ERROR']),
|
||||||
|
help="Override log level globally to this",
|
||||||
|
)
|
||||||
|
@click.pass_context
|
||||||
|
def main(ctx, model_basedir, model_overrides, log_level):
|
||||||
|
"""
|
||||||
|
eynollah - Document Layout Analysis, Image Enhancement, OCR
|
||||||
|
"""
|
||||||
|
# Initialize logging
|
||||||
|
console_handler = logging.StreamHandler(sys.stdout)
|
||||||
|
console_handler.setLevel(logging.NOTSET)
|
||||||
|
formatter = logging.Formatter('%(asctime)s.%(msecs)03d %(levelname)s %(name)s - %(message)s', datefmt='%H:%M:%S')
|
||||||
|
console_handler.setFormatter(formatter)
|
||||||
|
logging.getLogger('eynollah').addHandler(console_handler)
|
||||||
|
logging.getLogger('eynollah').setLevel(log_level or logging.INFO)
|
||||||
|
# Initialize model zoo
|
||||||
|
model_zoo = EynollahModelZoo(basedir=model_basedir, model_overrides=model_overrides)
|
||||||
|
# Initialize CLI context
|
||||||
|
ctx.obj = EynollahCliCtx(
|
||||||
|
model_zoo=model_zoo,
|
||||||
|
log_level=log_level,
|
||||||
|
)
|
||||||
|
|
||||||
|
|
||||||
|
if __name__ == "__main__":
|
||||||
|
main()
|
||||||
44
src/eynollah/cli/cli_binarize.py
Normal file
44
src/eynollah/cli/cli_binarize.py
Normal file
|
|
@ -0,0 +1,44 @@
|
||||||
|
import click
|
||||||
|
|
||||||
|
@click.command()
|
||||||
|
@click.option('--patches/--no-patches', default=True, help='by enabling this parameter you let the model to see the image in patches.')
|
||||||
|
@click.option(
|
||||||
|
"--input-image", "--image",
|
||||||
|
"-i",
|
||||||
|
help="input image filename",
|
||||||
|
type=click.Path(exists=True, dir_okay=False)
|
||||||
|
)
|
||||||
|
@click.option(
|
||||||
|
"--dir_in",
|
||||||
|
"-di",
|
||||||
|
help="directory of input images (instead of --image)",
|
||||||
|
type=click.Path(exists=True, file_okay=False),
|
||||||
|
)
|
||||||
|
@click.option(
|
||||||
|
"--output",
|
||||||
|
"-o",
|
||||||
|
help="output image (if using -i) or output image directory (if using -di)",
|
||||||
|
type=click.Path(file_okay=True, dir_okay=True),
|
||||||
|
required=True,
|
||||||
|
)
|
||||||
|
@click.pass_context
|
||||||
|
def binarize_cli(
|
||||||
|
ctx,
|
||||||
|
patches,
|
||||||
|
input_image,
|
||||||
|
dir_in,
|
||||||
|
output,
|
||||||
|
):
|
||||||
|
"""
|
||||||
|
Binarize images with a ML model
|
||||||
|
"""
|
||||||
|
from eynollah.sbb_binarize import SbbBinarizer
|
||||||
|
assert bool(input_image) != bool(dir_in), "Either -i (single input) or -di (directory) must be provided, but not both."
|
||||||
|
binarizer = SbbBinarizer(model_zoo=ctx.obj.model_zoo)
|
||||||
|
binarizer.run(
|
||||||
|
image_path=input_image,
|
||||||
|
use_patches=patches,
|
||||||
|
output=output,
|
||||||
|
dir_in=dir_in
|
||||||
|
)
|
||||||
|
|
||||||
63
src/eynollah/cli/cli_enhance.py
Normal file
63
src/eynollah/cli/cli_enhance.py
Normal file
|
|
@ -0,0 +1,63 @@
|
||||||
|
import click
|
||||||
|
|
||||||
|
@click.command()
|
||||||
|
@click.option(
|
||||||
|
"--image",
|
||||||
|
"-i",
|
||||||
|
help="input image filename",
|
||||||
|
type=click.Path(exists=True, dir_okay=False),
|
||||||
|
)
|
||||||
|
@click.option(
|
||||||
|
"--out",
|
||||||
|
"-o",
|
||||||
|
help="directory for output PAGE-XML files",
|
||||||
|
type=click.Path(exists=True, file_okay=False),
|
||||||
|
required=True,
|
||||||
|
)
|
||||||
|
@click.option(
|
||||||
|
"--overwrite",
|
||||||
|
"-O",
|
||||||
|
help="overwrite (instead of skipping) if output xml exists",
|
||||||
|
is_flag=True,
|
||||||
|
)
|
||||||
|
@click.option(
|
||||||
|
"--dir_in",
|
||||||
|
"-di",
|
||||||
|
help="directory of input images (instead of --image)",
|
||||||
|
type=click.Path(exists=True, file_okay=False),
|
||||||
|
)
|
||||||
|
@click.option(
|
||||||
|
"--num_col_upper",
|
||||||
|
"-ncu",
|
||||||
|
help="lower limit of columns in document image",
|
||||||
|
)
|
||||||
|
@click.option(
|
||||||
|
"--num_col_lower",
|
||||||
|
"-ncl",
|
||||||
|
help="upper limit of columns in document image",
|
||||||
|
)
|
||||||
|
@click.option(
|
||||||
|
"--save_org_scale/--no_save_org_scale",
|
||||||
|
"-sos/-nosos",
|
||||||
|
is_flag=True,
|
||||||
|
help="if this parameter set to true, this tool will save the enhanced image in org scale.",
|
||||||
|
)
|
||||||
|
@click.pass_context
|
||||||
|
def enhance_cli(ctx, image, out, overwrite, dir_in, num_col_upper, num_col_lower, save_org_scale):
|
||||||
|
"""
|
||||||
|
Enhance image
|
||||||
|
"""
|
||||||
|
assert bool(image) != bool(dir_in), "Either -i (single input) or -di (directory) must be provided, but not both."
|
||||||
|
from .image_enhancer import Enhancer
|
||||||
|
enhancer = Enhancer(
|
||||||
|
model_zoo=ctx.obj.model_zoo,
|
||||||
|
num_col_upper=num_col_upper,
|
||||||
|
num_col_lower=num_col_lower,
|
||||||
|
save_org_scale=save_org_scale,
|
||||||
|
)
|
||||||
|
enhancer.run(overwrite=overwrite,
|
||||||
|
dir_in=dir_in,
|
||||||
|
image_filename=image,
|
||||||
|
dir_out=out,
|
||||||
|
)
|
||||||
|
|
||||||
257
src/eynollah/cli/cli_layout.py
Normal file
257
src/eynollah/cli/cli_layout.py
Normal file
|
|
@ -0,0 +1,257 @@
|
||||||
|
import click
|
||||||
|
|
||||||
|
@click.command()
|
||||||
|
@click.option(
|
||||||
|
"--image",
|
||||||
|
"-i",
|
||||||
|
help="input image filename",
|
||||||
|
type=click.Path(exists=True, dir_okay=False),
|
||||||
|
)
|
||||||
|
|
||||||
|
@click.option(
|
||||||
|
"--out",
|
||||||
|
"-o",
|
||||||
|
help="directory for output PAGE-XML files",
|
||||||
|
type=click.Path(exists=True, file_okay=False),
|
||||||
|
required=True,
|
||||||
|
)
|
||||||
|
@click.option(
|
||||||
|
"--overwrite",
|
||||||
|
"-O",
|
||||||
|
help="overwrite (instead of skipping) if output xml exists",
|
||||||
|
is_flag=True,
|
||||||
|
)
|
||||||
|
@click.option(
|
||||||
|
"--dir_in",
|
||||||
|
"-di",
|
||||||
|
help="directory of input images (instead of --image)",
|
||||||
|
type=click.Path(exists=True, file_okay=False),
|
||||||
|
)
|
||||||
|
@click.option(
|
||||||
|
"--save_images",
|
||||||
|
"-si",
|
||||||
|
help="if a directory is given, images in documents will be cropped and saved there",
|
||||||
|
type=click.Path(exists=True, file_okay=False),
|
||||||
|
)
|
||||||
|
@click.option(
|
||||||
|
"--save_layout",
|
||||||
|
"-sl",
|
||||||
|
help="if a directory is given, plot of layout will be saved there",
|
||||||
|
type=click.Path(exists=True, file_okay=False),
|
||||||
|
)
|
||||||
|
@click.option(
|
||||||
|
"--save_deskewed",
|
||||||
|
"-sd",
|
||||||
|
help="if a directory is given, deskewed image will be saved there",
|
||||||
|
type=click.Path(exists=True, file_okay=False),
|
||||||
|
)
|
||||||
|
@click.option(
|
||||||
|
"--save_all",
|
||||||
|
"-sa",
|
||||||
|
help="if a directory is given, all plots needed for documentation will be saved there",
|
||||||
|
type=click.Path(exists=True, file_okay=False),
|
||||||
|
)
|
||||||
|
@click.option(
|
||||||
|
"--save_page",
|
||||||
|
"-sp",
|
||||||
|
help="if a directory is given, page crop of image will be saved there",
|
||||||
|
type=click.Path(exists=True, file_okay=False),
|
||||||
|
)
|
||||||
|
@click.option(
|
||||||
|
"--enable-plotting/--disable-plotting",
|
||||||
|
"-ep/-noep",
|
||||||
|
is_flag=True,
|
||||||
|
help="If set, will plot intermediary files and images",
|
||||||
|
)
|
||||||
|
@click.option(
|
||||||
|
"--extract_only_images/--disable-extracting_only_images",
|
||||||
|
"-eoi/-noeoi",
|
||||||
|
is_flag=True,
|
||||||
|
help="If a directory is given, only images in documents will be cropped and saved there and the other processing will not be done",
|
||||||
|
)
|
||||||
|
@click.option(
|
||||||
|
"--allow-enhancement/--no-allow-enhancement",
|
||||||
|
"-ae/-noae",
|
||||||
|
is_flag=True,
|
||||||
|
help="if this parameter set to true, this tool would check that input image need resizing and enhancement or not. If so output of resized and enhanced image and corresponding layout data will be written in out directory",
|
||||||
|
)
|
||||||
|
@click.option(
|
||||||
|
"--curved-line/--no-curvedline",
|
||||||
|
"-cl/-nocl",
|
||||||
|
is_flag=True,
|
||||||
|
help="if this parameter set to true, this tool will try to return contoure of textlines instead of rectangle bounding box of textline. This should be taken into account that with this option the tool need more time to do process.",
|
||||||
|
)
|
||||||
|
@click.option(
|
||||||
|
"--textline_light/--no-textline_light",
|
||||||
|
"-tll/-notll",
|
||||||
|
is_flag=True,
|
||||||
|
help="if this parameter set to true, this tool will try to return contoure of textlines instead of rectangle bounding box of textline with a faster method.",
|
||||||
|
)
|
||||||
|
@click.option(
|
||||||
|
"--full-layout/--no-full-layout",
|
||||||
|
"-fl/-nofl",
|
||||||
|
is_flag=True,
|
||||||
|
help="if this parameter set to true, this tool will try to return all elements of layout.",
|
||||||
|
)
|
||||||
|
@click.option(
|
||||||
|
"--tables/--no-tables",
|
||||||
|
"-tab/-notab",
|
||||||
|
is_flag=True,
|
||||||
|
help="if this parameter set to true, this tool will try to detect tables.",
|
||||||
|
)
|
||||||
|
@click.option(
|
||||||
|
"--right2left/--left2right",
|
||||||
|
"-r2l/-l2r",
|
||||||
|
is_flag=True,
|
||||||
|
help="if this parameter set to true, this tool will extract right-to-left reading order.",
|
||||||
|
)
|
||||||
|
@click.option(
|
||||||
|
"--input_binary/--input-RGB",
|
||||||
|
"-ib/-irgb",
|
||||||
|
is_flag=True,
|
||||||
|
help="In general, eynollah uses RGB as input but if the input document is very dark, very bright or for any other reason you can turn on input binarization. When this flag is set, eynollah will binarize the RGB input document, you should always provide RGB images to eynollah.",
|
||||||
|
)
|
||||||
|
@click.option(
|
||||||
|
"--allow_scaling/--no-allow-scaling",
|
||||||
|
"-as/-noas",
|
||||||
|
is_flag=True,
|
||||||
|
help="if this parameter set to true, this tool would check the scale and if needed it will scale it to perform better layout detection",
|
||||||
|
)
|
||||||
|
@click.option(
|
||||||
|
"--headers_off/--headers-on",
|
||||||
|
"-ho/-noho",
|
||||||
|
is_flag=True,
|
||||||
|
help="if this parameter set to true, this tool would ignore headers role in reading order",
|
||||||
|
)
|
||||||
|
@click.option(
|
||||||
|
"--light_version/--original",
|
||||||
|
"-light/-org",
|
||||||
|
is_flag=True,
|
||||||
|
help="if this parameter set to true, this tool would use lighter version",
|
||||||
|
)
|
||||||
|
@click.option(
|
||||||
|
"--ignore_page_extraction/--extract_page_included",
|
||||||
|
"-ipe/-epi",
|
||||||
|
is_flag=True,
|
||||||
|
help="if this parameter set to true, this tool would ignore page extraction",
|
||||||
|
)
|
||||||
|
@click.option(
|
||||||
|
"--reading_order_machine_based/--heuristic_reading_order",
|
||||||
|
"-romb/-hro",
|
||||||
|
is_flag=True,
|
||||||
|
help="if this parameter set to true, this tool would apply machine based reading order detection",
|
||||||
|
)
|
||||||
|
@click.option(
|
||||||
|
"--num_col_upper",
|
||||||
|
"-ncu",
|
||||||
|
help="lower limit of columns in document image",
|
||||||
|
)
|
||||||
|
@click.option(
|
||||||
|
"--num_col_lower",
|
||||||
|
"-ncl",
|
||||||
|
help="upper limit of columns in document image",
|
||||||
|
)
|
||||||
|
@click.option(
|
||||||
|
"--threshold_art_class_layout",
|
||||||
|
"-tharl",
|
||||||
|
help="threshold of artifical class in the case of layout detection. The default value is 0.1",
|
||||||
|
)
|
||||||
|
@click.option(
|
||||||
|
"--threshold_art_class_textline",
|
||||||
|
"-thart",
|
||||||
|
help="threshold of artifical class in the case of textline detection. The default value is 0.1",
|
||||||
|
)
|
||||||
|
@click.option(
|
||||||
|
"--skip_layout_and_reading_order",
|
||||||
|
"-slro/-noslro",
|
||||||
|
is_flag=True,
|
||||||
|
help="if this parameter set to true, this tool will ignore layout detection and reading order. It means that textline detection will be done within printspace and contours of textline will be written in xml output file.",
|
||||||
|
)
|
||||||
|
@click.pass_context
|
||||||
|
def layout_cli(
|
||||||
|
ctx,
|
||||||
|
image,
|
||||||
|
out,
|
||||||
|
overwrite,
|
||||||
|
dir_in,
|
||||||
|
save_images,
|
||||||
|
save_layout,
|
||||||
|
save_deskewed,
|
||||||
|
save_all,
|
||||||
|
extract_only_images,
|
||||||
|
save_page,
|
||||||
|
enable_plotting,
|
||||||
|
allow_enhancement,
|
||||||
|
curved_line,
|
||||||
|
textline_light,
|
||||||
|
full_layout,
|
||||||
|
tables,
|
||||||
|
right2left,
|
||||||
|
input_binary,
|
||||||
|
allow_scaling,
|
||||||
|
headers_off,
|
||||||
|
light_version,
|
||||||
|
reading_order_machine_based,
|
||||||
|
num_col_upper,
|
||||||
|
num_col_lower,
|
||||||
|
threshold_art_class_textline,
|
||||||
|
threshold_art_class_layout,
|
||||||
|
skip_layout_and_reading_order,
|
||||||
|
ignore_page_extraction,
|
||||||
|
):
|
||||||
|
"""
|
||||||
|
Detect Layout (with optional image enhancement and reading order detection)
|
||||||
|
"""
|
||||||
|
from ..eynollah import Eynollah
|
||||||
|
assert enable_plotting or not save_layout, "Plotting with -sl also requires -ep"
|
||||||
|
assert enable_plotting or not save_deskewed, "Plotting with -sd also requires -ep"
|
||||||
|
assert enable_plotting or not save_all, "Plotting with -sa also requires -ep"
|
||||||
|
assert enable_plotting or not save_page, "Plotting with -sp also requires -ep"
|
||||||
|
assert enable_plotting or not save_images, "Plotting with -si also requires -ep"
|
||||||
|
assert enable_plotting or not allow_enhancement, "Plotting with -ae also requires -ep"
|
||||||
|
assert not enable_plotting or save_layout or save_deskewed or save_all or save_page or save_images or allow_enhancement, \
|
||||||
|
"Plotting with -ep also requires -sl, -sd, -sa, -sp, -si or -ae"
|
||||||
|
assert textline_light == light_version, "Both light textline detection -tll and light version -light must be set or unset equally"
|
||||||
|
assert not extract_only_images or not allow_enhancement, "Image extraction -eoi can not be set alongside allow_enhancement -ae"
|
||||||
|
assert not extract_only_images or not allow_scaling, "Image extraction -eoi can not be set alongside allow_scaling -as"
|
||||||
|
assert not extract_only_images or not light_version, "Image extraction -eoi can not be set alongside light_version -light"
|
||||||
|
assert not extract_only_images or not curved_line, "Image extraction -eoi can not be set alongside curved_line -cl"
|
||||||
|
assert not extract_only_images or not textline_light, "Image extraction -eoi can not be set alongside textline_light -tll"
|
||||||
|
assert not extract_only_images or not full_layout, "Image extraction -eoi can not be set alongside full_layout -fl"
|
||||||
|
assert not extract_only_images or not tables, "Image extraction -eoi can not be set alongside tables -tab"
|
||||||
|
assert not extract_only_images or not right2left, "Image extraction -eoi can not be set alongside right2left -r2l"
|
||||||
|
assert not extract_only_images or not headers_off, "Image extraction -eoi can not be set alongside headers_off -ho"
|
||||||
|
assert bool(image) != bool(dir_in), "Either -i (single input) or -di (directory) must be provided, but not both."
|
||||||
|
eynollah = Eynollah(
|
||||||
|
model_zoo=ctx.obj.model_zoo,
|
||||||
|
extract_only_images=extract_only_images,
|
||||||
|
enable_plotting=enable_plotting,
|
||||||
|
allow_enhancement=allow_enhancement,
|
||||||
|
curved_line=curved_line,
|
||||||
|
textline_light=textline_light,
|
||||||
|
full_layout=full_layout,
|
||||||
|
tables=tables,
|
||||||
|
right2left=right2left,
|
||||||
|
input_binary=input_binary,
|
||||||
|
allow_scaling=allow_scaling,
|
||||||
|
headers_off=headers_off,
|
||||||
|
light_version=light_version,
|
||||||
|
ignore_page_extraction=ignore_page_extraction,
|
||||||
|
reading_order_machine_based=reading_order_machine_based,
|
||||||
|
num_col_upper=num_col_upper,
|
||||||
|
num_col_lower=num_col_lower,
|
||||||
|
skip_layout_and_reading_order=skip_layout_and_reading_order,
|
||||||
|
threshold_art_class_textline=threshold_art_class_textline,
|
||||||
|
threshold_art_class_layout=threshold_art_class_layout,
|
||||||
|
)
|
||||||
|
eynollah.run(overwrite=overwrite,
|
||||||
|
image_filename=image,
|
||||||
|
dir_in=dir_in,
|
||||||
|
dir_out=out,
|
||||||
|
dir_of_cropped_images=save_images,
|
||||||
|
dir_of_layout=save_layout,
|
||||||
|
dir_of_deskewed=save_deskewed,
|
||||||
|
dir_of_all=save_all,
|
||||||
|
dir_save_page=save_page,
|
||||||
|
)
|
||||||
|
|
||||||
132
src/eynollah/cli/cli_ocr.py
Normal file
132
src/eynollah/cli/cli_ocr.py
Normal file
|
|
@ -0,0 +1,132 @@
|
||||||
|
import click
|
||||||
|
|
||||||
|
@click.command()
|
||||||
|
@click.option(
|
||||||
|
"--image",
|
||||||
|
"-i",
|
||||||
|
help="input image filename",
|
||||||
|
type=click.Path(exists=True, dir_okay=False),
|
||||||
|
)
|
||||||
|
@click.option(
|
||||||
|
"--dir_in",
|
||||||
|
"-di",
|
||||||
|
help="directory of input images (instead of --image)",
|
||||||
|
type=click.Path(exists=True, file_okay=False),
|
||||||
|
)
|
||||||
|
@click.option(
|
||||||
|
"--dir_in_bin",
|
||||||
|
"-dib",
|
||||||
|
help=("""
|
||||||
|
directory of binarized images (in addition to --dir_in for RGB
|
||||||
|
images; filename stems must match the RGB image files, with '.png'
|
||||||
|
\n
|
||||||
|
Perform prediction using both RGB and binary images.
|
||||||
|
(This does not necessarily improve results, however it may be beneficial
|
||||||
|
for certain document images.
|
||||||
|
"""),
|
||||||
|
|
||||||
|
type=click.Path(exists=True, file_okay=False),
|
||||||
|
)
|
||||||
|
@click.option(
|
||||||
|
"--dir_xmls",
|
||||||
|
"-dx",
|
||||||
|
help="directory of input PAGE-XML files (in addition to --dir_in; filename stems must match the image files, with '.xml' suffix).",
|
||||||
|
type=click.Path(exists=True, file_okay=False),
|
||||||
|
required=True,
|
||||||
|
)
|
||||||
|
@click.option(
|
||||||
|
"--out",
|
||||||
|
"-o",
|
||||||
|
help="directory for output PAGE-XML files",
|
||||||
|
type=click.Path(exists=True, file_okay=False),
|
||||||
|
required=True,
|
||||||
|
)
|
||||||
|
@click.option(
|
||||||
|
"--dir_out_image_text",
|
||||||
|
"-doit",
|
||||||
|
help="directory for output images, newly rendered with predicted text",
|
||||||
|
type=click.Path(exists=True, file_okay=False),
|
||||||
|
)
|
||||||
|
@click.option(
|
||||||
|
"--overwrite",
|
||||||
|
"-O",
|
||||||
|
help="overwrite (instead of skipping) if output xml exists",
|
||||||
|
is_flag=True,
|
||||||
|
)
|
||||||
|
@click.option(
|
||||||
|
"--tr_ocr",
|
||||||
|
"-trocr/-notrocr",
|
||||||
|
is_flag=True,
|
||||||
|
help="if this parameter set to true, transformer ocr will be applied, otherwise cnn_rnn model.",
|
||||||
|
)
|
||||||
|
@click.option(
|
||||||
|
"--export_textline_images_and_text",
|
||||||
|
"-etit/-noetit",
|
||||||
|
is_flag=True,
|
||||||
|
help="if this parameter set to true, images and text in xml will be exported into output dir. This files can be used for training a OCR engine.",
|
||||||
|
)
|
||||||
|
@click.option(
|
||||||
|
"--do_not_mask_with_textline_contour",
|
||||||
|
"-nmtc/-mtc",
|
||||||
|
is_flag=True,
|
||||||
|
help="if this parameter set to true, cropped textline images will not be masked with textline contour.",
|
||||||
|
)
|
||||||
|
@click.option(
|
||||||
|
"--batch_size",
|
||||||
|
"-bs",
|
||||||
|
help="number of inference batch size. Default b_s for trocr and cnn_rnn models are 2 and 8 respectively",
|
||||||
|
)
|
||||||
|
@click.option(
|
||||||
|
"--dataset_abbrevation",
|
||||||
|
"-ds_pref",
|
||||||
|
help="in the case of extracting textline and text from a xml GT file user can add an abbrevation of dataset name to generated dataset",
|
||||||
|
)
|
||||||
|
@click.option(
|
||||||
|
"--min_conf_value_of_textline_text",
|
||||||
|
"-min_conf",
|
||||||
|
help="minimum OCR confidence value. Text lines with a confidence value lower than this threshold will not be included in the output XML file.",
|
||||||
|
)
|
||||||
|
@click.pass_context
|
||||||
|
def ocr_cli(
|
||||||
|
ctx,
|
||||||
|
image,
|
||||||
|
dir_in,
|
||||||
|
dir_in_bin,
|
||||||
|
dir_xmls,
|
||||||
|
out,
|
||||||
|
dir_out_image_text,
|
||||||
|
overwrite,
|
||||||
|
tr_ocr,
|
||||||
|
export_textline_images_and_text,
|
||||||
|
do_not_mask_with_textline_contour,
|
||||||
|
batch_size,
|
||||||
|
dataset_abbrevation,
|
||||||
|
min_conf_value_of_textline_text,
|
||||||
|
):
|
||||||
|
"""
|
||||||
|
Recognize text with a CNN/RNN or transformer ML model.
|
||||||
|
"""
|
||||||
|
assert not export_textline_images_and_text or not tr_ocr, "Exporting textline and text -etit can not be set alongside transformer ocr -tr_ocr"
|
||||||
|
# FIXME: refactor: move export_textline_images_and_text out of eynollah.py
|
||||||
|
# assert not export_textline_images_and_text or not model, "Exporting textline and text -etit can not be set alongside model -m"
|
||||||
|
assert not export_textline_images_and_text or not batch_size, "Exporting textline and text -etit can not be set alongside batch size -bs"
|
||||||
|
assert not export_textline_images_and_text or not dir_in_bin, "Exporting textline and text -etit can not be set alongside directory of bin images -dib"
|
||||||
|
assert not export_textline_images_and_text or not dir_out_image_text, "Exporting textline and text -etit can not be set alongside directory of images with predicted text -doit"
|
||||||
|
assert bool(image) != bool(dir_in), "Either -i (single image) or -di (directory) must be provided, but not both."
|
||||||
|
from .eynollah_ocr import Eynollah_ocr
|
||||||
|
eynollah_ocr = Eynollah_ocr(
|
||||||
|
model_zoo=ctx.obj.model_zoo,
|
||||||
|
tr_ocr=tr_ocr,
|
||||||
|
export_textline_images_and_text=export_textline_images_and_text,
|
||||||
|
do_not_mask_with_textline_contour=do_not_mask_with_textline_contour,
|
||||||
|
batch_size=batch_size,
|
||||||
|
pref_of_dataset=dataset_abbrevation,
|
||||||
|
min_conf_value_of_textline_text=min_conf_value_of_textline_text)
|
||||||
|
eynollah_ocr.run(overwrite=overwrite,
|
||||||
|
dir_in=dir_in,
|
||||||
|
dir_in_bin=dir_in_bin,
|
||||||
|
image_filename=image,
|
||||||
|
dir_xmls=dir_xmls,
|
||||||
|
dir_out_image_text=dir_out_image_text,
|
||||||
|
dir_out=out,
|
||||||
|
)
|
||||||
35
src/eynollah/cli/cli_readingorder.py
Normal file
35
src/eynollah/cli/cli_readingorder.py
Normal file
|
|
@ -0,0 +1,35 @@
|
||||||
|
import click
|
||||||
|
|
||||||
|
@click.command()
|
||||||
|
@click.option(
|
||||||
|
"--input",
|
||||||
|
"-i",
|
||||||
|
help="PAGE-XML input filename",
|
||||||
|
type=click.Path(exists=True, dir_okay=False),
|
||||||
|
)
|
||||||
|
@click.option(
|
||||||
|
"--dir_in",
|
||||||
|
"-di",
|
||||||
|
help="directory of PAGE-XML input files (instead of --input)",
|
||||||
|
type=click.Path(exists=True, file_okay=False),
|
||||||
|
)
|
||||||
|
@click.option(
|
||||||
|
"--out",
|
||||||
|
"-o",
|
||||||
|
help="directory for output images",
|
||||||
|
type=click.Path(exists=True, file_okay=False),
|
||||||
|
required=True,
|
||||||
|
)
|
||||||
|
@click.pass_context
|
||||||
|
def readingorder_cli(ctx, input, dir_in, out):
|
||||||
|
"""
|
||||||
|
Generate ReadingOrder with a ML model
|
||||||
|
"""
|
||||||
|
from eynollah.mb_ro_on_layout import machine_based_reading_order_on_layout
|
||||||
|
assert bool(input) != bool(dir_in), "Either -i (single input) or -di (directory) must be provided, but not both."
|
||||||
|
orderer = machine_based_reading_order_on_layout(model_zoo=ctx.obj.model_zoo)
|
||||||
|
orderer.run(xml_filename=input,
|
||||||
|
dir_in=dir_in,
|
||||||
|
dir_out=out,
|
||||||
|
)
|
||||||
|
|
||||||
|
|
@ -1,3 +1,6 @@
|
||||||
|
# NOTE: For predictable order of imports of torch/shapely/tensorflow
|
||||||
|
# this must be the first import of the CLI!
|
||||||
|
from .eynollah_imports import imported_libs
|
||||||
from .processor import EynollahProcessor
|
from .processor import EynollahProcessor
|
||||||
from click import command
|
from click import command
|
||||||
from ocrd.decorators import ocrd_cli_options, ocrd_cli_wrap_processor
|
from ocrd.decorators import ocrd_cli_options, ocrd_cli_wrap_processor
|
||||||
|
|
|
||||||
Loading…
Add table
Add a link
Reference in a new issue