1 files changed, 105 insertions, 0 deletions
diff --git a/megapixels/commands/cv/csv_to_faces.py b/megapixels/commands/cv/csv_to_faces.py
new file mode 100644
index 00000000..64c8b965
--- /dev/null
+++ b/megapixels/commands/cv/csv_to_faces.py
@@ -0,0 +1,105 @@
+"""
+Reads in CSV of ROIs and extracts facial regions with padding
+"""
+
+import click
+
+from app.settings import types
+from app.utils import click_utils
+from app.settings import app_cfg as cfg
+
+@click.command()
+@click.option('-i', '--input', 'opt_fp_in', required=True,
+  help='Input CSV')
+@click.option('-m', '--media', 'opt_dir_media', required=True,
+  help='Input image/video directory')
+@click.option('-o', '--output', 'opt_dir_out', required=True,
+  help='Output directory for extracted ROI images')
+@click.option('--slice', 'opt_slice', type=(int, int), default=(None, None),
+  help='Slice list of files')
+@click.option('--padding', 'opt_padding', default=0.25,
+  help='Facial padding as percentage of face width')
+@click.option('--ext', 'opt_ext_out', default='png', type=click.Choice(['jpg', 'png']),
+  help='Output image type')
+@click.option('--min', 'opt_min', default=(60, 60),
+  help='Minimum original face size')
+@click.pass_context
+def cli(ctx, opt_fp_in, opt_dir_media, opt_dir_out, opt_slice, 
+  opt_padding, opt_ext_out, opt_min):
+  """Converts ROIs to images"""
+  
+  import os
+  from os.path import join
+  from pathlib import Path
+  from glob import glob
+  
+  from tqdm import tqdm
+  import numpy as np
+  from PIL import Image, ImageOps, ImageFilter, ImageDraw
+  import cv2 as cv
+  import pandas as pd
+
+  from app.utils import logger_utils, file_utils, im_utils
+  from app.models.bbox import BBox
+
+  # -------------------------------------------------
+  # process here
+  log = logger_utils.Logger.getLogger()
+  
+  df_rois = pd.read_csv(opt_fp_in, dtype={'subdir': str, 'fn': str})
+  if opt_slice:
+    df_rois = df_rois[opt_slice[0]:opt_slice[1]]
+  
+  log.info('Processing {:,} rows'.format(len(df_rois)))
+
+  file_utils.mkdirs(opt_dir_out)
+
+  df_rois_grouped = df_rois.groupby(['fn'])  # group by fn/filename
+  groups = df_rois_grouped.groups
+  skipped = []
+
+  for group in tqdm(groups):
+    # get image
+    group_rows = df_rois_grouped.get_group(group)
+
+    row = group_rows.iloc[0]
+    fp_im = join(opt_dir_media, str(row['subdir']), '{fn}.{ext}'.format(**row))  # TODO change to ext
+    try:
+      im = Image.open(fp_im).convert('RGB')
+      im.verify()
+    except Exception as e:
+      log.warn('Could not open: {}'.format(fp_im))
+      log.error(e)
+      continue
+
+    for idx, roi in group_rows.iterrows():
+      # get bbox to im dimensions
+      xywh = [roi['x'], roi['y'], roi['w'] , roi['h']]
+      bbox = BBox.from_xywh(*xywh)
+      dim = im.size
+      bbox_dim = bbox.to_dim(dim)
+      # expand
+      opt_padding_px = int(opt_padding * bbox_dim.width)
+      bbox_dim_exp = bbox_dim.expand_dim(opt_padding_px, dim)
+      # crop
+      x1y2 = bbox_dim_exp.pt_tl + bbox_dim_exp.pt_br
+      im_crop = im.crop(box=x1y2)
+
+      # strip exif, create new image and paste data
+      im_crop_data = list(im_crop.getdata())
+      im_crop_no_exif = Image.new(im_crop.mode, im_crop.size)
+      im_crop_no_exif.putdata(im_crop_data)
+
+      # save
+      idx_zpad = file_utils.zpad(idx, zeros=3)
+      subdir = '' if roi['subdir'] == '.' else '{}_'.format(roi['subdir'])
+      subdir = subdir.replace('/', '_')
+      fp_im_out = join(opt_dir_out, '{}{}{}.{}'.format(subdir, roi['fn'], idx_zpad, opt_ext_out))
+      # threshold size and save
+      if im_crop_no_exif.size[0] < opt_min[0] or im_crop_no_exif.size[1] < opt_min[1]:
+        skipped.append(fp_im_out)
+        log.info('Face too small: {}, idx: {}'.format(fp_im, idx))
+      else:
+        im_crop_no_exif.save(fp_im_out)
+
+  log.info('Skipped {:,} images'.format(len(skipped)))