A script to crop and wrangle labels

crop_and_wrangle.py

import os
import pandas as pd
from PIL import Image


def crop_cell(row):
    """
    crop_cell(row)
    
    given a pd.Series row of the dataframe, load row['filename'] with PIL,
    crop it to the box row['xmin'], row['xmax'], row['ymin'], row['ymax']
    save the cropped image,
    return cropped filename
    """
    input_dir = 'BCCD\JPEGImages'
    output_dir = 'BCCD\cropped'
    # open image
    im = Image.open(f"{input_dir}\{row['filename']}")

    # size of the image in pixels
    width, height = im.size

    # setting the points for cropped image
    left = row['xmin']
    bottom = row['ymax']
    right = row['xmax']
    top = row['ymin']

    # cropped image
    im1 = im.crop((left, top, right, bottom))
    cropped_fname = f"BloodImage_{row['image_id']:03d}_{row['cell_id']:02d}.jpg"
    # shows the image in image viewer
    # im1.show()

    # save image
    try:
        im1.save(f"{output_dir}\{cropped_fname}")
    except:
        return 'error while saving image'

    return cropped_fname

if __name__ == "__main__":
    # load labels csv into Pandas DataFrame
    filepath = "BCCD\dataset2-master\labels.csv"
    df = pd.read_csv(filepath)
    
    # iterate through cells, crop each cell, and save cropped cell to file
    dataset_df['cell_filename'] = dataset_df.apply(crop_cell, axis=1)