Generating Images similar to Oxford Synthetic Word Dataset about textrecognitiondatagenerator HOT 12 CLOSED

def parse_arguments():
#Parse the command line arguments of the program.

parser = argparse.ArgumentParser(description='Generate synthetic text data for text recognition.')
parser.add_argument(
    "--output_dir",
    type=str,
    nargs="?",
    help="The output directory",
    default="out/",
)
parser.add_argument(
    "-i",
    "--input_file",
    type=str,
    nargs="?",
    help="When set, this argument uses a specified text file as source for the text",
    default=""
)
parser.add_argument(
    "-l",
    "--language",
    type=str,
    nargs="?",
    help="The language to use, should be fr (French), en (English), es (Spanish), de (German), or cn (Chinese).",
    default="en"
)
parser.add_argument(
    "-c",
    "--count",
    type=int,
    nargs="?",
    help="The number of images to be created.",
    default=1000
)
parser.add_argument(
    "-rs",
    "--random_sequences",
    action="store_true",
    help="Use random sequences as the source text for the generation. Set '-let','-num','-sym' to use letters/numbers/symbols. If none specified, using all three.",
    default=True
)
parser.add_argument(
    "-let",
    "--include_letters",
    action="store_true",
    help="Define if random sequences should contain letters. Only works with -rs",
    default=True
)
parser.add_argument(
    "-num",
    "--include_numbers",
    action="store_true",
    help="Define if random sequences should contain numbers. Only works with -rs",
    default=True
)
parser.add_argument(
    "-sym",
    "--include_symbols",
    action="store_true",
    help="Define if random sequences should contain symbols. Only works with -rs",
    default=True
)
parser.add_argument(
    "-w",
    "--length",
    type=int,
    nargs="?",
    help="Define how many words should be included in each generated sample. If the text source is Wikipedia, this is the MINIMUM length",
    default=1
)
parser.add_argument(
    "-r",
    "--random",
    action="store_true",
    help="Define if the produced string will have variable word count (with --length being the maximum)",
    default=False
)
parser.add_argument(
    "-f",
    "--format",
    type=int,
    nargs="?",
    help="Define the height of the produced images",
    default=32,
)
parser.add_argument(
    "-t",
    "--thread_count",
    type=int,
    nargs="?",
    help="Define the number of thread to use for image generation",
    default=3,
)
parser.add_argument(
    "-e",
    "--extension",
    type=str,
    nargs="?",
    help="Define the extension to save the image with",
    default="jpg",
)
parser.add_argument(
    "-k",
    "--skew_angle",
    type=int,
    nargs="?",
    help="Define skewing angle of the generated text. In positive degrees",
    default=10,
)
parser.add_argument(
    "-rk",
    "--random_skew",
    action="store_true",
    help="When set, the skew angle will be randomized between the value set with -k and it's opposite",
    default=True,
)
parser.add_argument(
    "-wk",
    "--use_wikipedia",
    action="store_true",
    help="Use Wikipedia as the source text for the generation, using this paremeter ignores -r, -n, -s",
    default=False,
)
parser.add_argument(
    "-bl",
    "--blur",
    type=int,
    nargs="?",
    help="Apply gaussian blur to the resulting sample. Should be an integer defining the blur radius",
    #default = 0.7,
    default=0,
)
parser.add_argument(
    "-rbl",
    "--random_blur",
    action="store_true",
    help="When set, the blur radius will be randomized between 0 and -bl.",
    default = 0.5,
    #default=False,
)
parser.add_argument(
    "-b",
    "--background",
    type=int,
    nargs="?",
    help="Define what kind of background to use. 0: Gaussian Noise, 1: Plain white, 2: Quasicrystal, 3: Pictures",
    default=0,
)
parser.add_argument(
    "-hw",
    "--handwritten",
    action="store_true",
    help="Define if the data will be \"handwritten\" by an RNN",
)
parser.add_argument(
    "-na",
    "--name_format",
    type=int,
    help="Define how the produced files will be named. 0: [TEXT]_[ID].[EXT], 1: [ID]_[TEXT].[EXT] 2: [ID].[EXT] + one file labels.txt containing id-to-label mappings",
    default=0,
)
parser.add_argument(
    "-d",
    "--distorsion",
    type=int,
    nargs="?",
    help="Define a distorsion applied to the resulting image. 0: None (Default), 1: Sine wave, 2: Cosine wave, 3: Random",
    default=0
)
parser.add_argument(
    "-do",
    "--distorsion_orientation",
    type=int,
    nargs="?",
    help="Define the distorsion's orientation. Only used if -d is specified. 0: Vertical (Up and down), 1: Horizontal (Left and Right), 2: Both",
    default=0
)
parser.add_argument(
    "-wd",
    "--width",
    type=int,
    nargs="?",
    help="Define the width of the resulting image. If not set it will be the width of the text + 10. If the width of the generated text is bigger that number will be used",
    default=-1
)
parser.add_argument(
    "-al",
    "--alignment",
    type=int,
    nargs="?",
    help="Define the alignment of the text in the image. Only used if the width parameter is set. 0: left, 1: center, 2: right",
    default=1
)
parser.add_argument(
    "-tc",
    "--text_color",
    type=str,
    nargs="?",
    help="Define the text's color, should be either a single hex color or a range in the ?,? format.",
    default = "#282828,#444444"
    #default='#282828'
)
return parser.parse_args()