diff --git a/assignment2/.png b/assignment2/.png
index 799e680..485ee88 100644
Binary files a/assignment2/.png and b/assignment2/.png differ
diff --git a/assignment2/solution.py b/assignment2/solution.py
index af72814..c57dcb3 100644
--- a/assignment2/solution.py
+++ b/assignment2/solution.py
@@ -186,11 +186,10 @@ def one_e(distances: list, selected_dists: list):
 ############################
 
 def ex2():
-    #two_b()
-    #two_c()
+    two_b()
+    two_d()
     two_e()
     
-
 def two_b():
     """
     Implement the function simple_convolution that uses a 1-D signal I and a kernel
@@ -289,7 +288,7 @@ def two_e():
 # EXCERCISE 3: Image Filtering #
 ################################
 def ex3():
-    #three_a()
+    three_a()
     three_b()
 
 def three_a():
@@ -341,18 +340,17 @@ def three_b():
     Convolution can also be used for image sharpening. Look at its definition in the
     lecture slides and implement it. Test it on the image from file museum.jpg.
     """
-    museum_grayscale = cv2.imread('./data/images/museum.jpg', 0)
+    museum_grayscale = uz_image.imread_gray('./data/images/museum.jpg', uz_image.ImageType.uint8)
 
-    #https://blog.demofox.org/2022/02/26/image-sharpening-convolution-kernels/
-    # Pa tui na slajdih lepo pise
+    #https://blog.demofox.org/2022/02/26/image-sharpening-convolution-kernels/  # Pa tui na slajdih lepo pise
 
     kernel = np.array([[-1, -1, -1], 
                        [-1, 17, -1],
                        [-1, -1,-1]])
+
     kernel = kernel * 1./9.
 
-    museo = cv2.filter2D(museum_grayscale, cv2.CV_64F, kernel)
-    museo = cv2.filter2D(museo, cv2.CV_64F, kernel.T)
+    museo = cv2.filter2D(museum_grayscale, -1, kernel)
 
     fig, axs = plt.subplots(1, 2)
     axs[0].imshow(museum_grayscale, cmap='gray')
@@ -369,8 +367,8 @@ def three_b():
 
 def main():
     #ex1()
-    ex2()
-    # ex3()
+    #ex2()
+    ex3()
 
 if __name__ == '__main__':
     main()