Preprocessing steps for Blood Cells Detection Dataset

create_dataframe.py

import os, sys, random
import xml.etree.ElementTree as ET
from glob import glob
import pandas as pd
from shutil import copyfile

annotations = glob('BCCD_Dataset/BCCD/Annotations/*.xml')
df = []
for file in annotations:
    #filename = file.split('/')[-1].split('.')[0] + '.jpg'
    #filename = str(cnt) + '.jpg'
    filename = file.split('\\')[-1]
    filename =filename.split('.')[0] + '.jpg'
    row = []
    parsedXML = ET.parse(file)
    cell_id = 0
    for node in parsedXML.getroot().iter('object'):
        blood_cells = node.find('name').text
        xmin = int(node.find('bndbox/xmin').text)
        xmax = int(node.find('bndbox/xmax').text)
        ymin = int(node.find('bndbox/ymin').text)
        ymax = int(node.find('bndbox/ymax').text)

        row = [filename, cell_id, blood_cells, xmin, xmax, ymin, ymax]
        df.append(row)
        cell_id += 1

data = pd.DataFrame(df, columns=['filename', 'cell_id', 'cell_type', 'xmin', 'xmax', 'ymin', 'ymax'])
data['image_id'] = data['filename'].apply(lambda x: int(x[-7:-4]))
data[['filename', 'image_id', 'cell_id', 'cell_type', 'xmin', 'xmax', 'ymin', 'ymax']].to_csv('bccd.csv', index=False)