Figure 9.31: Results on synthetic image with noise variance, a2 = 500 using FCM method. Row 1, left: Synthetic generate image. Row 1, right: After Perona-Malik smoothing. Row 2, left: After FCM classification system. Row 2, right: Binarization with only CO class (K = 1). Row 3, left: Binarization with merging CO, C1, and C2 classes (K > 1). Row 3, right: Binarization after CCA (K = 1). Row 4, left: Binarization after CCA (K > 1). Row 4, right: After assign ID (K = 1). Row 5, left: After assign ID (K > 1). Row 5, right: After region to boundary (K = 1). Row 6, left: After region to boundary (K > 1). Row 6, right: Overlay generation with and without crescent moon.

Figure 9.32: Results on synthetic image with noise variance, a2 = 500 using MRF method. Row 1, left: Synthetic generate image. Row 1, right: After MRF classification system. Row 2, left: Binarization with only C0 class (K = 1). Row 2, right: Binarization with merging C0, C1, and C2 classes (K > 1). Row 3, left: Binarization after CCA (K = 1). Row 3, right: Binarization after CCA (K > 1). Row 4, left: After assign ID (K = 1). Row 4, right: After assign ID (K > 1). Row 5, left: After region to boundary (K = 1). Row 5, right: After region to boundary (K > 1). Row 6, left: Overlay generation with and without crescent moon. Row 6, right: Overlay generation with and without crescent moon.

Figure 9.32: Results on synthetic image with noise variance, a2 = 500 using MRF method. Row 1, left: Synthetic generate image. Row 1, right: After MRF classification system. Row 2, left: Binarization with only C0 class (K = 1). Row 2, right: Binarization with merging C0, C1, and C2 classes (K > 1). Row 3, left: Binarization after CCA (K = 1). Row 3, right: Binarization after CCA (K > 1). Row 4, left: After assign ID (K = 1). Row 4, right: After assign ID (K > 1). Row 5, left: After region to boundary (K = 1). Row 5, right: After region to boundary (K > 1). Row 6, left: Overlay generation with and without crescent moon. Row 6, right: Overlay generation with and without crescent moon.

noise level a2 = 500. In the first row the left image shows the synthetically generated image. In the first row the right image shows the classified image after the image has gone through the MRF classification system. In the second row the left image shows the binarization of the image after selecting only the core class for binarization (K = 1). In the second row the right image shows the bi-narization of the image after selecting the core class and the edge classes for binarization (K > 1). In the third row the left image shows the image (K = 1) after the labeling of CCA. In the third row the right image shows the image (K > 1) after the labeling of CCA. In the fourth row the left image shows the image (K = 1) after the labeling of assign ID. In the fourth row the right image shows the image (K > 1) after the labeling of assign ID. In the fifth row the left image shows the computer-estimated boundary of the image (K = 1), using the region-to-boundary algorithm. In the fifth row the right image shows the computer-estimated boundary of the image (K > 1), using the region-to-boundary algorithm. In the sixth row the left image shows the original image on which is overlayed the ideal ground truth boundary, the artifacted boundary (K = 1), and the corrected boundary (K > 1). In the sixth row the right image shows the original image on which is overlayed the ideal ground truth boundary, the artifacted boundary (K = 1), and the corrected boundary (K > 1).

Figures 9.33 and 9.34 show in the GSM classification system all the steps for the left and right lumen detection, identification, and boundary estimation process in the synthetic images. We look at large noise protocol as an example below with noise level a2 = 500. In Fig. 9.33, the first row the left image shows the synthetically generated image. In the first row the right image shows the image after it has been smoothed by the Perona-Malik smoothing function. In the second row the left image shows the image after its frequency peaks of pixel values have been merged. In the second row the right image shows the classified image after the image has gone through the GSM classification system. In the third row the left image shows the binarization of the image after selecting only the core class for binarization (K = 1). In the third row the right image shows the binarization of the image after selecting the core class and the edge classes for binarization (K > 1). In the fourth row the left image shows the image (K = 1) after the labeling of CCA. In the fourth row the right image shows the image (K > 1) after the labeling of CCA. In Fig. 9.34, the first row the left image shows the image (K = 1) after the labeling of assign ID. In the first row the right image shows the image (K > 1) after the labeling of assign

Figure 9.33: Results on synthetic image with noise variance, a2 = 500 using GSM method. Row 1, left: Synthetic generate image. Row 1, right: After peak merger. Row 2, left: After Perona-Malik Smoothing. Row 2, right: After GSM classification system. Row 3, left: Binarization with only CO class (K = 1). Row 3, right: Binarization with merging CO, C1, and C2 classes (K > 1). Row 4, left: Binarization after CCA (K = 1). Row 4, right: Binarization after CCA (K > 1).

Figure 9.33: Results on synthetic image with noise variance, a2 = 500 using GSM method. Row 1, left: Synthetic generate image. Row 1, right: After peak merger. Row 2, left: After Perona-Malik Smoothing. Row 2, right: After GSM classification system. Row 3, left: Binarization with only CO class (K = 1). Row 3, right: Binarization with merging CO, C1, and C2 classes (K > 1). Row 4, left: Binarization after CCA (K = 1). Row 4, right: Binarization after CCA (K > 1).

ID. In the second row the left image shows the computer-estimated boundary of the image (K = 1), using the region-to-boundary algorithm. In the second row the right image shows the computer-estimated boundary of the image (K > 1), using the region-to-boundary algorithm. In the third row the left image shows the original image on which is overlayed the ideal ground truth boundary, the artifacted boundary (K = 1), and the corrected boundary (K > 1). In the third row the right image shows the original image on which is overlayed the ideal ground truth boundary, the artifacted boundary (K = 1), and the corrected boundary (K > 1).

Figure 9.34: Results on synthetic image with noise variance, a2 = 500 using GSM method. Row 5, left: After assign ID (K = 1). Row 5, right: After assign ID (K > 1). Row 6, left: After region to boundary (K = 1). Row 6, right: After region to boundary (K > 1). Row 7, left: Overaly generation with and without crescent moon. Row 8, right: Overaly generation with and wihout crescent moon.

Figure 9.34: Results on synthetic image with noise variance, a2 = 500 using GSM method. Row 5, left: After assign ID (K = 1). Row 5, right: After assign ID (K > 1). Row 6, left: After region to boundary (K = 1). Row 6, right: After region to boundary (K > 1). Row 7, left: Overaly generation with and without crescent moon. Row 8, right: Overaly generation with and wihout crescent moon.

Was this article helpful?

## Post a comment