Update tempo.txt

tempo.txt

@@ -1,98 +1,29 @@
 import cv2
 import numpy as np
 
-# Read the image mask (assuming grayscale mask)
-mask_path = 'mask_image.png'
-mask = cv2.imread(mask_path, cv2.IMREAD_GRAYSCALE)
-
-# Convert the mask to binary (thresholding)
-_, binary_mask = cv2.threshold(mask, 127, 255, cv2.THRESH_BINARY)
-
-# Find the coordinates of the bottom-right corner
-y_max, x_max = binary_mask.shape
-y_max -= 1
-x_max -= 1
-
-# Calculate the length of the line
-line_length = int(np.sqrt(x_max ** 2 + y_max ** 2))
-
-# Define the angle of the line (45 degrees)
-angle_degrees = 45
-angle_radians = np.deg2rad(angle_degrees)
-
-# Calculate the slope of the line
-slope = np.tan(angle_radians)
-
-# Initialize the starting position of the line
-start_x = x_max
-start_y = y_max
-
-# Move the line towards the top-left corner
-while start_x >= 0 and start_y >= 0:
-    # Calculate the end point of the line
-    end_x = int(start_x - line_length * np.cos(angle_radians))
-    end_y = int(start_y - line_length * np.sin(angle_radians))
-
-    # Draw the line on the binary mask
-    cv2.line(binary_mask, (start_x, start_y), (end_x, end_y), 255, 2)
-
-    # Check if the line touches the mask
-    if binary_mask[end_y, end_x] == 255:
-        break
-
-    # Move the line towards the top-left corner
-    start_x -= 1
-    start_y -= 1
-
-# Display or save the image with the line
-cv2.imshow('Line Image', binary_mask)
-cv2.waitKey(0)
-cv2.destroyAllWindows()
-
-
-import cv2
-import numpy as np
-
-def is_pixel_on_line(image, start, end):
-    # Bresenham's line algorithm
-    x0, y0 = start
-    x1, y1 = end
-    dx = abs(x1 - x0)
-    dy = abs(y1 - y0)
-    sx = 1 if x0 < x1 else -1
-    sy = 1 if y0 < y1 else -1
-    err = dx - dy
-
-    while True:
-        # Check if the current pixel is white (255)
-        if image[y0, x0] == 255:
-            return True  # Pixel is present on the line
-
-        # Check if we have reached the end point
-        if (x0, y0) == (x1, y1):
-            break
-
-        e2 = 2 * err
-        if e2 > -dy:
-            err -= dy
-            x0 += sx
-        if e2 < dx:
-            err += dx
-            y0 += sy
-
-    return False  # No white pixel is present on the line
-
-# Read the binary mask image
-mask_path = 'mask_image.png'
-mask = cv2.imread(mask_path, cv2.IMREAD_GRAYSCALE)
-
-# Define the start and end coordinates of the line
-start_point = (10, 10)
-end_point = (100, 100)
-
-# Check if any white pixel is present on the line
-is_pixel_present = is_pixel_on_line(mask, start_point, end_point)
-if is_pixel_present:
-    print("At least one white pixel is present on the line.")
+# Load the mask image
+mask = cv2.imread('mask_image.png', cv2.IMREAD_GRAYSCALE)  # Replace 'mask_image.png' with the path to your mask image
+
+# Apply Gaussian blur to the image to reduce noise
+blurred = cv2.GaussianBlur(mask, (5, 5), 0)
+
+# Apply Hough Circle Transform to detect circles
+circles = cv2.HoughCircles(blurred, cv2.HOUGH_GRADIENT, dp=1, minDist=20, param1=50, param2=30, minRadius=0, maxRadius=0)
+
+if circles is not None:
+    circles = np.uint16(np.around(circles))
+    
+    # Filter out semicircles based on the position of the circle centers
+    semicircles = [circle[0] for circle in circles[0] if circle[1] < mask.shape[0] / 2]
+
+    # Draw the semicircles on a blank image
+    semicircle_image = np.zeros_like(mask)
+    for (x, y, r) in semicircles:
+        cv2.circle(semicircle_image, (x, y), r, (255, 255, 255), thickness=cv2.FILLED)
+
+    # Display the image with the semicircles
+    cv2.imshow('Semicircles in Mask', semicircle_image)
+    cv2.waitKey(0)
+    cv2.destroyAllWindows()
 else:
-    print("No white pixel is present on the line.")
+    print("No semicircles found in the image.")