wko_anime-face-similarity/metrics.py

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