Cosine similarity added

color_transfer.py

@@ -3,7 +3,7 @@ from sklearn.cluster import KMeans, MiniBatchKMeans
 import torch
 import ast
 import cv2
-from .utils import EuclideanDistance, ManhattanDistance
+from .utils import EuclideanDistance, ManhattanDistance, CosineSimilarity
 
 
 
@@ -28,7 +28,8 @@ def SwitchColors(image, detected_colors, target_colors, clustering_model, distan
 
     distance_methods = {
     "Euclidean": EuclideanDistance,
-    "Manhattan": ManhattanDistance
+    "Manhattan": ManhattanDistance,
+    "HSV_Similarity": CosineSimilarity
     }
 
     distance_method = distance_methods.get(distance_method)
@@ -54,7 +55,7 @@ class PaletteTransferNode:
                 "target_colors": ("COLOR_LIST",),
                 "color_space": (["RGB", "HSV", "LAB"], {'default': 'RGB'}),
                 "cluster_method": (["Kmeans","Mini batch Kmeans"], {'default': 'Kmeans'}, ),
-                "distance_method": (["Euclidean", "Manhattan"], {'default': 'Euclidean'}, )
+                "distance_method": (["Euclidean", "Manhattan", "CosineSimilarity"], {'default': 'Euclidean'}, )
                 }
             }
         return data_in

utils.py

@@ -7,3 +7,19 @@ def EuclideanDistance(detected_colors, target_colors):
 
 def ManhattanDistance(detected_colors, target_colors):
     return np.sum(np.abs(detected_colors - target_colors), axis=1)
+
+
+def CosineSimilarity(detected_colors, target_colors):
+    return np.dot(detected_colors, target_colors) / (np.linalg.norm(detected_colors) * np.linalg.norm(target_colors))
+
+
+'''def HSV_Color_Similarity(detected_colors, target_colors):
+    h1, s1, _ = detected_colors
+    h2, s2, _ = target_colors
+    
+    h1_rad, h2_rad = np.radians(h1), np.radians(h2)
+    
+    v1 = np.array([s1 * np.cos(h1_rad), s1 * np.sin(h1_rad)])
+    v2 = np.array([s2 * np.cos(h2_rad), s2 * np.sin(h2_rad)])
+    
+    return np.dot(v1, v2) / (np.linalg.norm(v1) * np.linalg.norm(v2))'''