Research Article
Noise Estimation and Type Identification in Natural Scene and Medical Images using Deep Learning Approaches
Algorithm 2
Proposed algorithm for noise type identification.
Input: Noised images | Output: Identified noise type | Method: | Step 1: Read images | For i = 1 to n do | Read image Ii | Repeat step 2–5 for each image | Step 2: Resize an image | Resize image Ii to 256 × 256 | Step 3: DWT transformation | [LL, LH,HL,HH] = DWT transformation. | Step 4: Edge Detection and reduce size to match with HH sub-band | Id = Detect edges of Ii using the Sobel operator. | Idd = Downsample the image by two rows and two columns. | Step 5: Remove edge component from HH sub-band | Iwe = HH ○ Idd Hadamard operation | Step 6: Train and test the CNN model using the images obtained in step 5 | Divide images in the ratio 60 : 20 : 20. | Step 7: Measure the performance. |
|