.gitignore

@@ -1,6 +1,4 @@
 data
-.idea
-.yoloface
 
 # Byte-compiled / optimized / DLL files
 __pycache__/

README.md

@@ -1,40 +0,0 @@
-# wko_anime-face-similarity
-Projekt przygotowany na zajęcia z widzenia komputerowego.
-
-Rozpoznaje twarz na zdjęciu wejściowym i dokonując transferu stylu do anime, porównuje zdjęcie ze zbiorem postaci
-z anime i wskazuje podobieństwa według wybranych metryk.
-
-## Instalacja
-1. Pobranie submodułów:
-    ```shell
-    $ git submodule update --init
-    ```
-2. Instalacja zależności:
-   * Windows/Linux
-     ```shell
-     $ pip install -r requirements.txt     
-     ```
-   * MacOS
-     ```shell
-     $ pip install -r requirements-osx.txt
-     ```
-3. Konfiguracja DCT-Netu (anime style transfer)
-    ```shell
-    $ cd DCT-Net && python download.py
-    ```
-4. Pobranie datasetu twarzy postaci z anime (MyAnimeList)
-    ```shell
-    $ python scrape_data.py
-    ```
-
-## Uruchomienie
-Na tę chwilę zdjęcie poddawane porównaniu to `UAM-Andre.jpg`
-```shell
-$ python main.py
-```
-
-### Walidacja
-Do walidacji metryk na postawie testowego datasetu z cosplayerami (`test_set`) uruchamiamy
-```shell
-$ python --validate_only 1
-```

face_detect.py

@@ -1,54 +0,0 @@
-import cv2
-import numpy as np
-from yoloface import face_analysis
-
-face_detector = face_analysis()
-
-
-def equalize_image(data: np.ndarray):
-  data_hsv = cv2.cvtColor(data, cv2.COLOR_RGB2HSV)
-  data_hsv[:, :, 2] = cv2.equalizeHist(data_hsv[:, :, 2])
-  return cv2.cvtColor(data_hsv, cv2.COLOR_HSV2RGB)
-
-
-def find_face_bbox_yolo(data: np.ndarray):
-  _, box, conf = face_detector.face_detection(frame_arr=data, frame_status=True, model='full')
-  if len(box) < 1:
-    return None, None
-  return box, conf
-
-
-def find_face_bbox(data: np.ndarray):
-  classifier_files = [
-    'haarcascades/haarcascade_frontalface_default.xml',
-    'haarcascades/haarcascade_frontalface_alt.xml',
-    'haarcascades/haarcascade_frontalface_alt2.xml',
-    'haarcascades/haarcascade_profileface.xml',
-    'haarcascades/haarcascade_glasses.xml',
-    'lbpcascade_animeface.xml',
-  ]
-  data_equalized = equalize_image(data)
-  data_gray = cv2.cvtColor(data_equalized, cv2.COLOR_RGB2GRAY)
-  face_coords, conf = find_face_bbox_yolo(cv2.cvtColor(data_equalized, cv2.COLOR_RGB2BGR))
-  if face_coords is not None:
-    return face_coords[0]
-
-  for classifier in classifier_files:
-    face_cascade = cv2.CascadeClassifier(classifier)
-    face_coords = face_cascade.detectMultiScale(data_gray, 1.1, 3)
-    if face_coords is not None:
-      break
-  return max(face_coords, key=lambda v: v[2]*v[3])
-
-
-def crop_face(data: np.ndarray, bounding_box) -> np.ndarray:
-  x, y, w, h = bounding_box
-  # Extending the boxes
-  factor = 0.4
-  x, y = round(x - factor * w), round(y - factor * h)
-  w, h = round(w + factor * w * 2), round(h + factor * h * 2)
-  y = max(y, 0)
-  x = max(x, 0)
-
-  face = data[y:y + h, x:x + w]
-  return face

helpers.py

@@ -1,12 +0,0 @@
-import os
-import sys
-
-
-def no_stdout(func):
-  def wrapper(*args, **kwargs):
-    old_stdout = sys.stdout
-    sys.stdout = open(os.devnull, "w")
-    ret = func(*args, **kwargs)
-    sys.stdout = old_stdout
-    return ret
-  return wrapper

load_test_data.py

@@ -5,11 +5,7 @@ import cv2 as cv
 from pathlib import Path
 
 
-def load_source(filename: str) -> np.ndarray:
-  return cv.imread(filename)[..., ::-1]
-
-
-def load_data(input_dir):
+def load_data(input_dir, newSize=(64,64)):
     image_path = Path(input_dir)
     file_names = os.listdir(image_path)
     categories_name = []
@@ -31,7 +27,9 @@ def load_data(input_dir):
 
     for n in file_names:
         p = image_path / n
-        img = load_source(str(p)) # zwraca ndarry postaci xSize x ySize x colorDepth
+        img = imread(p) # zwraca ndarry postaci xSize x ySize x colorDepth
+        img = cv.resize(img, newSize, interpolation=cv.INTER_AREA) # zwraca ndarray
+        img = img / 255 # type: ignore #normalizacja
         test_img.append(img)
         labels.append(n)
 

main.py

@@ -1,114 +1,35 @@
-import argparse
-import sys
-import cv2
-import matplotlib.pyplot as plt
-import numpy as np
-
-from metrics import histogram_comparison, structural_similarity_index, euclidean_distance, AccuracyGatherer
-
-from face_detect import find_face_bbox, crop_face
-from helpers import no_stdout
-from load_test_data import load_data, load_source
-from metrics import get_top_results
-from plots import plot_two_images, plot_results
-
 # Allows imports from the style transfer submodule
+import sys
 sys.path.append('DCT-Net')
 
+import cv2
+import os
+import numpy as np
+
 from source.cartoonize import Cartoonizer
 
 
-anime_transfer = Cartoonizer(dataroot='DCT-Net/damo/cv_unet_person-image-cartoon_compound-models')
+def load_source(filename: str) -> np.ndarray:
+  return cv2.imread(filename)[...,::-1]
 
 
-def compare_with_anime_characters(source_image: np.ndarray, anime_faces_dataset: dict, verbose=False) -> list[dict]:
-  all_metrics = []
-  for anime_image, label in zip(anime_faces_dataset['values'], anime_faces_dataset['labels']):
-    current_result = {
-      'name': label,
-      'metrics': {}
-    }
-    # TODO: Use a different face detection method for anime images
-    # anime_face = find_and_crop_face(anime_image, 'haarcascades/lbpcascade_animeface.xml')
-    anime_face = anime_image
-    source_rescaled = cv2.resize(source_image, anime_face.shape[:2])
-    if verbose:
-      plot_two_images(anime_face, source_rescaled)
-    current_result['metrics'] = histogram_comparison(source_rescaled, anime_face)
-    current_result['metrics']['structural-similarity'] = structural_similarity_index(source_rescaled, anime_face)
-    current_result['metrics']['euclidean-distance'] = euclidean_distance(source_rescaled, anime_face)
-    all_metrics.append(current_result)
-
-  return all_metrics
+def find_and_crop_face(data: np.ndarray) -> np.ndarray:
+  # TODO
+  return data
 
 
-@no_stdout
-def transfer_to_anime(img: np.ndarray):
-  model_out = anime_transfer.cartoonize(img).astype(np.uint8)
-  return cv2.cvtColor(model_out, cv2.COLOR_BGR2RGB)
+def compare_with_anime_characters(data: np.ndarray) -> int:
+  # TODO
+  return 1
 
 
-def similarity_to_anime(source_image, anime_faces_set, debug=False):
-  try:
-    source_face_bbox = find_face_bbox(source_image)
-  except ValueError:
-    return None
-  source_anime = transfer_to_anime(source_image)
-  source_face_anime = crop_face(source_anime, source_face_bbox)
-
-  if debug:
-    source_image_with_box = source_image.copy()
-    x, y, w, h = source_face_bbox
-    cv2.rectangle(source_image_with_box, (x, y), (x + w, y + h), (255, 0, 0), 2)
-    plt.figure(figsize=[12, 4])
-    plt.subplot(131)
-    plt.imshow(source_image_with_box)
-    plt.subplot(132)
-    plt.imshow(source_anime)
-    plt.subplot(133)
-    plt.imshow(source_face_anime)
-    plt.show()
-
-  return compare_with_anime_characters(source_face_anime, anime_faces_set, verbose=debug)
-
-
-def validate(test_set, anime_faces_set):
-  all_entries = len(test_set['values'])
-  accuracy = AccuracyGatherer(all_entries)
-  for test_image, test_label in zip(test_set['values'], test_set['labels']):
-    test_results = similarity_to_anime(test_image, anime_faces_set)
-
-    if test_results is None:
-      print(f"cannot find face for {test_label}")
-      all_entries -= 1
-      continue
-
-    accuracy.for_results(test_results, test_label)
-
-  accuracy.count = all_entries
-  accuracy.print()
-
-
-
-def main():
-  parser = argparse.ArgumentParser()
-  parser.add_argument('-v', '--validate_only')
-  args = parser.parse_args()
-  anime_faces_set = load_data('data/croped_anime_faces')
-
-  if args.validate_only:
-    print('Validating')
-    test_set = load_data('test_set')
-    validate(test_set, anime_faces_set)
-    exit(0)
-
-  source = load_source('test_set/Ayanokouji, Kiyotaka.jpg')
-  results = similarity_to_anime(source, anime_faces_set)
-  method = 'correlation'
-  top_results = get_top_results(results, count=4, metric=method)
-  print(top_results)
-  plot_results(source, transfer_to_anime(source), top_results, anime_faces_set, method)
+def transfer_to_anime(ima: np.ndarray):
+  algo = Cartoonizer(dataroot='damo/cv_unet_person-image-cartoon_compound-models')
+  return algo.cartoonize(img)
 
 
 if __name__ == '__main__':
-  main()
+  source = load_source('input.png')
+  source_face = find_and_crop_face(source)
+  source_face_anime = transfer_to_anime(source)
+  print(compare_with_anime_characters(source_face_anime))

metrics.py

@@ -1,81 +0,0 @@
-import cv2
-import numpy as np
-from skimage.metrics import structural_similarity
-
-def histogram_comparison(data_a: np.ndarray, data_b: np.ndarray) -> dict:
-  hsv_a = cv2.cvtColor(data_a, cv2.COLOR_BGR2HSV)
-  hsv_b = cv2.cvtColor(data_b, cv2.COLOR_BGR2HSV)
-
-  histSize = [50, 60]
-  hue_ranges = [0, 180]
-  sat_ranges = [0, 256]
-  channels = [0, 1]
-  ranges = hue_ranges + sat_ranges
-
-  hist_a = cv2.calcHist([hsv_a], channels, None, histSize, ranges, accumulate=False)
-  cv2.normalize(hist_a, hist_a, alpha=0, beta=1, norm_type=cv2.NORM_MINMAX)
-  hist_b = cv2.calcHist([hsv_b], channels, None, histSize, ranges, accumulate=False)
-  cv2.normalize(hist_b, hist_b, alpha=0, beta=1, norm_type=cv2.NORM_MINMAX)
-
-  return {
-    'correlation': cv2.compareHist(hist_a, hist_b, 0),
-    'chi-square': cv2.compareHist(hist_a, hist_b, 1),
-    'intersection': cv2.compareHist(hist_a, hist_b, 2),
-    'bhattacharyya-distance': cv2.compareHist(hist_a, hist_b, 3),
-  }
-
-
-def structural_similarity_index(data_a: np.ndarray, data_b: np.ndarray) -> float:
-  return structural_similarity(cv2.cvtColor(data_a, cv2.COLOR_BGR2GRAY), cv2.cvtColor(data_b, cv2.COLOR_BGR2GRAY))
-
-
-def euclidean_distance(data_a: np.ndarray, data_b: np.ndarray) -> float:
-  gray_a = cv2.cvtColor(data_a, cv2.COLOR_BGR2GRAY)
-  histogram_a = cv2.calcHist([gray_a], [0], None, [256], [0, 256])
-
-  gray_b = cv2.cvtColor(data_b, cv2.COLOR_BGR2GRAY)
-  histogram_b = cv2.calcHist([gray_b], [0],  None, [256], [0, 256])
-  result, i = [0.], 0
-  while i < len(histogram_a) and i < len(histogram_b):
-    result += (histogram_a[i] - histogram_b[i]) ** 2
-    i += 1
-  return result[0] ** (1 / 2)
-
-
-def get_top_results(all_metrics: list[dict], metric='correlation', count=1):
-  all_metrics.sort(reverse=True, key=lambda item: item['metrics'][metric])
-  return list(map(lambda item: {'name': item['name'], 'score': item['metrics'][metric]}, all_metrics[:count]))
-
-
-class AccuracyGatherer:
-  all_metric_names = [
-    'structural-similarity',
-    'euclidean-distance',
-    'chi-square',
-    'correlation',
-    'intersection',
-    'bhattacharyya-distance'
-  ]
-
-  def __init__(self, count, top_ks=(1, 3, 5)):
-    self.top_ks = top_ks
-    self.hits = {k: {metric: 0 for metric in AccuracyGatherer.all_metric_names} for k in top_ks}
-    self.count = count
-
-  def print(self):
-    for k in self.top_ks:
-      all_metrics = {metric: self.hits[k][metric] / self.count for metric in AccuracyGatherer.all_metric_names}
-      print(f'Top {k} matches results:')
-      [print(f'\t{key}: {value * 100}%') for key, value in all_metrics.items()]
-
-  def for_results(self, results, test_label):
-    top_results_all_metrics = {
-      k: {m: get_top_results(results, m, k) for m in AccuracyGatherer.all_metric_names} for k in self.top_ks
-    }
-    for metric_name in AccuracyGatherer.all_metric_names:
-      self.add_if_hit(top_results_all_metrics, test_label, metric_name)
-
-  def add_if_hit(self, results, test_label, metric_name):
-    for k in self.top_ks:
-      if any(map(lambda single_result: single_result['name'] == test_label, results[k][metric_name])):
-        self.hits[k][metric_name] += 1

plots.py

@@ -1,45 +0,0 @@
-import numpy as np
-from matplotlib import pyplot as plt, gridspec
-
-
-def plot_two_images(a: np.ndarray, b: np.ndarray):
-  plt.figure(figsize=[10, 10])
-  plt.subplot(121)
-  plt.imshow(a)
-  plt.title("A")
-  plt.subplot(122)
-  plt.imshow(b)
-  plt.title("B")
-  plt.show()
-
-
-def plot_results(source, source_anime, results, anime_faces_set, method):
-    cols = len(results)
-    plt.figure(figsize=[3*cols, 7])
-    gs = gridspec.GridSpec(2, cols)
-
-    plt.subplot(gs[0, cols // 2 - 1])
-    plt.imshow(source)
-    plt.title('Your image')
-    plt.axis('off')
-
-    plt.subplot(gs[0, cols // 2])
-    plt.imshow(source_anime)
-    plt.title('Your image in Anime style')
-    plt.axis('off')
-
-    plt.figtext(0.5, 0.525, "Predictions", ha="center", va="top", fontsize=16)
-
-    for idx, prediction in enumerate(results):
-        result_img = anime_faces_set['values'][anime_faces_set['labels'].index(prediction['name'])]
-        plt.subplot(gs[1, idx])
-        plt.imshow(result_img, interpolation='bicubic')
-        plt.title(f'{prediction["name"].partition(".")[0]}, score={str(round(prediction["score"], 4))}')
-        plt.axis('off')
-
-    plt.tight_layout()
-
-    plt.figtext(0.5, 0.01, f"Metric: {method}", ha="center", va="bottom", fontsize=12)
-    plt.subplots_adjust(wspace=0, hspace=0.1)
-
-    plt.show()

requirements-osx.txt

@@ -1,11 +0,0 @@
-tensorflow-macos==2.11.0
-easydict==1.10
-numpy==1.23.1
-modelscope==1.1.3
-requests==2.28.2
-beautifulsoup4==4.11.1
-lxml==4.9.2
-opencv-python==4.7.0.68
-torch==1.13.1
-matplotlib==3.6.3
-scikit-image==0.19.3

requirements.txt

@@ -5,9 +5,4 @@ modelscope==1.1.3
 requests==2.28.2
 beautifulsoup4==4.11.1
 lxml==4.9.2
-opencv-python==4.7.0.68
-torch==1.13.1
-matplotlib==3.6.3
-scikit-image==0.19.3
-yoloface==0.0.4
-ipython==8.9.0
+opencv-python==4.7.0.68