Update

app.py

@@ -7,16 +7,12 @@ from collections import defaultdict
 from skimage.color import deltaE_ciede2000, rgb2lab
 import zipfile
 
-def DoG_filter(image, kernel_size, sigma, k_sigma, gamma):
-    if kernel_size == 0:
-        kernel_size = None  # OpenCVにカーネルサイズを自動で決定させる
-    else:
-        kernel_size = (kernel_size, kernel_size)
-    g1 = cv2.GaussianBlur(image, kernel_size, sigma)
-    g2 = cv2.GaussianBlur(image, kernel_size, sigma * k_sigma)
+def DoG_filter(image, kernel_size=0, sigma=1.0, k_sigma=2.0, gamma=1.5):
+    g1 = cv2.GaussianBlur(image, (kernel_size, kernel_size), sigma)
+    g2 = cv2.GaussianBlur(image, (kernel_size, kernel_size), sigma * k_sigma)
     return g1 - gamma * g2
 
-def XDoG_filter(image, kernel_size, sigma, k_sigma, epsilon, phi, gamma):
+def XDoG_filter(image, kernel_size=0, sigma=1.4, k_sigma=1.6, epsilon=0, phi=10, gamma=0.98):
     epsilon /= 255
     dog = DoG_filter(image, kernel_size, sigma, k_sigma, gamma)
     dog /= dog.max()
@@ -24,10 +20,24 @@ def XDoG_filter(image, kernel_size, sigma, k_sigma, epsilon, phi, gamma):
     e[e >= 1] = 1
     return (e * 255).astype('uint8')
 
-def process_XDoG(image, kernel_size, sigma, k_sigma, epsilon, phi, gamma):
-    image = cv2.cvtColor(np.array(image), cv2.COLOR_RGB2GRAY)
+def binarize_image(image):
+    _, binarized = cv2.threshold(image, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)
+    return binarized
+
+
+def process_XDoG(image_path):
+    kernel_size=0
+    sigma=1.4
+    k_sigma=1.6
+    epsilon=0
+    phi=10
+    gamma=0.98
+
+    image = cv2.imread(image_path, cv2.IMREAD_GRAYSCALE)
     xdog_image = XDoG_filter(image, kernel_size, sigma, k_sigma, epsilon, phi, gamma)
-    return Image.fromarray(xdog_image).convert('L')
+    binarized_image = binarize_image(xdog_image)
+    final_image = Image.fromarray(binarized_image)
+    return final_image
 
 
 
@@ -151,14 +161,7 @@ class webui:
     def __init__(self):
         self.demo = gr.Blocks()
 
-    def main(self, image_path, kernel_size, sigma, k_sigma, epsilon, phi, gamma):
-        kernel_size = int(kernel_size)
-        sigma = float(sigma)
-        k_sigma = float(k_sigma)
-        epsilon = int(epsilon)
-        phi = int(phi)
-        gamma = float(gamma)
-        
+    def main(self, image_path):
         image = Image.open(image_path).convert('RGBA')
         #拡張子を取り除いたファイル名を取得
         image_name = os.path.splitext(image_path)[0]
@@ -166,7 +169,7 @@ class webui:
         image.save(image_path)
         image = Image.open(image_path).convert('RGBA')
         rgb_image = image.convert('RGB')
-        lineart = process_XDoG(image, kernel_size, sigma, k_sigma, epsilon, phi, gamma).convert('L')
+        lineart = process_XDoG(image_path).convert('L')
         replace_color_image = process_image(rgb_image, lineart).convert('RGBA')
         
         if alpha:
@@ -194,45 +197,15 @@ class webui:
             with gr.Row():
                 with gr.Column():
                     input_image = gr.Image(type='filepath', image_mode="RGBA", label="Original Image")
-                    kernel_size = gr.Dropdown(choices=[0, 1, 3, 5, 7, 9], value=0, label="カーネルサイズ (kernel_size)")
-                    kernel_size_description = gr.Label("ガウシアンフィルタのカーネルサイズです。線の鋭さを設定します。0を選択するとOpenCVが自動でカーネルサイズを決定します。")
-                    sigma = gr.Slider(0.1, 10.0, step=0.1, value=1.4, label="シグマ (sigma)")
-                    sigma_description = gr.Label("ガウシアンフィルタの標準偏差。ぼかしの程度を制御します。")
-                    k_sigma = gr.Slider(1.0, 3.0, step=0.1, value=1.6, label="k_シグマ (k_sigma)")
-                    k_sigma_description = gr.Label("二つ目のガウシアンフィルタのシグマの倍率。線の太さが影響を受けます。")
-                    epsilon = gr.Slider(-10, 10, value=0, label="イプシロン (epsilon)")
-                    epsilon_description = gr.Label("XDoGフィルターの閾値パラメータ。線画の明瞭度やコントラストを調整します。")
-                    phi = gr.Slider(1, 100, value=10, label="ファイ (phi)")
-                    phi_description = gr.Label("タンジェントハイパーボリック関数の係数。閾値を超えた部分の鮮明さを高めます。")
-                    gamma = gr.Slider(0.5, 1.5, step=0.1, value=0.98, label="ガンマ (gamma)")
-                    gamma_description = gr.Label("DoGフィルタの強度調整パラメータ。主に線の明るさや暗さを調節します。")
                     submit = gr.Button(value="Start")
-
-                    # コンポーネントと説明を順番に追加
-                    self.demo.add(input_image)
-                    self.demo.add(kernel_size)
-                    self.demo.add(kernel_size_description)
-                    self.demo.add(sigma)
-                    self.demo.add(sigma_description)
-                    self.demo.add(k_sigma)
-                    self.demo.add(k_sigma_description)
-                    self.demo.add(epsilon)
-                    self.demo.add(epsilon_description)
-                    self.demo.add(phi)
-                    self.demo.add(phi_description)
-                    self.demo.add(gamma)
-                    self.demo.add(gamma_description)
-                    self.demo.add(submit)
-
-            with gr.Row():
-                with gr.Column():
-                    with gr.Tab("output"):
-                        output_0 = gr.Gallery(format="png")
-                    output_file = gr.File()
-            
+                with gr.Row():
+                    with gr.Column():
+                        with gr.Tab("output"):
+                            output_0 = gr.Gallery(format="png")
+                        output_file = gr.File()
             submit.click(
                 self.main, 
-                inputs=[input_image, kernel_size, sigma, k_sigma, epsilon, phi, gamma], 
+                inputs=[input_image], 
                 outputs=[output_0, output_file]
             )