tathagata

transforms.py

@@ -24,10 +24,8 @@ def sobel_edge_detection(image):
     sobel_x = cv2.Sobel(image, cv2.CV_64F, 1, 0, ksize=3)
     sobel_y = cv2.Sobel(image, cv2.CV_64F, 0, 1, ksize=3)
     sobel_combined = np.sqrt(sobel_x**2 + sobel_y**2)
-    sobel_combined = cv2.normalize(sobel_combined, None, 0, 255, cv2.NORM_MINMAX)  # Added normalization
     return sobel_combined
 
-
 # 3. Gaussian Blur
 def gaussian_blur(image, kernel_size=5):
     blurred_img = cv2.GaussianBlur(image, (kernel_size, kernel_size), 0)
@@ -39,10 +37,8 @@ def laplacian_of_gaussian(image):
         image = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
     blurred_img = cv2.GaussianBlur(image, (3, 3), 0)
     log_img = cv2.Laplacian(blurred_img, cv2.CV_64F)
-    log_img = cv2.normalize(log_img, None, 0, 255, cv2.NORM_MINMAX)  # Added normalization
     return log_img
 
-
 # 5. Median Filtering
 def median_filter(image, kernel_size=5):
     median_img = cv2.medianBlur(image, kernel_size)
@@ -70,7 +66,7 @@ def high_pass_filter(image):
     dft_shift = np.fft.fftshift(dft)
     rows, cols = image.shape
     crow, ccol = rows // 2, cols // 2
-    mask = np.ones((rows, cols), np.float64)  # Changed to float64
+    mask = np.ones((rows, cols), np.uint8)
     mask[crow-30:crow+30, ccol-30:ccol+30] = 0
     fshift = dft_shift * mask
     f_ishift = np.fft.ifftshift(fshift)
@@ -78,7 +74,6 @@ def high_pass_filter(image):
     img_back = np.abs(img_back)
     return img_back
 
-
 def low_pass_filter(image):
     if len(image.shape) == 3:  # Convert to grayscale if RGB
         image = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
@@ -86,7 +81,7 @@ def low_pass_filter(image):
     dft_shift = np.fft.fftshift(dft)
     rows, cols = image.shape
     crow, ccol = rows // 2, cols // 2
-    mask = np.zeros((rows, cols), np.float64)  # Changed to float64
+    mask = np.zeros((rows, cols), np.uint8)
     mask[crow-30:crow+30, ccol-30:ccol+30] = 1
     fshift = dft_shift * mask
     f_ishift = np.fft.ifftshift(fshift)
@@ -94,7 +89,6 @@ def low_pass_filter(image):
     img_back = np.abs(img_back)
     return img_back
 
-
 def wavelet_transform(image):
     import pywt
     if len(image.shape) == 3:  # Convert to grayscale if RGB