Figure 1.
Illustration for of an RGB color space image. (a) The image U is split into its corresponding channels U, U, and U, respectively, from left to right; (b) the embedding dimension pattern of size having m; (c) X and X for K = K1, K2, and K3 being the R, G, and B color channels, respectively.
Figure 1.
Illustration for of an RGB color space image. (a) The image U is split into its corresponding channels U, U, and U, respectively, from left to right; (b) the embedding dimension pattern of size having m; (c) X and X for K = K1, K2, and K3 being the R, G, and B color channels, respectively.
Figure 2.
Illustration for of an RGB color space image having m = [ 2,2,2]. (a) A portion of the colored image with its R, G, and B channels; (b) the scanning pattern or embedding dimension with m that is a cube; (c) X and X, the fixed and moving templates defined above.
Figure 2.
Illustration for of an RGB color space image having m = [ 2,2,2]. (a) A portion of the colored image with its R, G, and B channels; (b) the scanning pattern or embedding dimension with m that is a cube; (c) X and X, the fixed and moving templates defined above.
Figure 3.
Illustration for of RGB color space image having m. (a) A portion of the colored image with its R, G, and B channels; (b) the scanning pattern or embedding dimension with m that is a cuboid; (c) the fixed and moving templates defined above.
Figure 3.
Illustration for of RGB color space image having m. (a) A portion of the colored image with its R, G, and B channels; (b) the scanning pattern or embedding dimension with m that is a cuboid; (c) the fixed and moving templates defined above.
Figure 4.
Colored Brodatz texture (CBT) images of different colored irregularity degrees [
41,
42]. (
a–
i) CBT images that are used for the validation test (
Section 4.3) to compare the entropy values of each colored texture to its corresponding sub-images in three color spaces (RGB, HSV, and YUV); (
f) is used again for studying the sensitivity of the proposed measures to different initial parameters (
Section 4.1).
Figure 4.
Colored Brodatz texture (CBT) images of different colored irregularity degrees [
41,
42]. (
a–
i) CBT images that are used for the validation test (
Section 4.3) to compare the entropy values of each colored texture to its corresponding sub-images in three color spaces (RGB, HSV, and YUV); (
f) is used again for studying the sensitivity of the proposed measures to different initial parameters (
Section 4.1).
Figure 5.
Dermoscopic images segmentation for choosing the region of interest (ROI). (a) an example of the dermoscopic image for a pigmented skin lesion; (b,c) the contouring and segmentation of the lesion; (d) the ROI as the central pixels.
Figure 5.
Dermoscopic images segmentation for choosing the region of interest (ROI). (a) an example of the dermoscopic image for a pigmented skin lesion; (b,c) the contouring and segmentation of the lesion; (d) the ROI as the central pixels.
Figure 6.
results for the red, green, and blue channels (left to right) of the colored Brodatz image,
Figure 4f, with varying
r and
m.
Figure 6.
results for the red, green, and blue channels (left to right) of the colored Brodatz image,
Figure 4f, with varying
r and
m.
Figure 7.
results with varying
r and
m of the colored Brodatz image,
Figure 4f.
Figure 7.
results with varying
r and
m of the colored Brodatz image,
Figure 4f.
Figure 8.
results with varying
r and
m of the colored Brodatz image,
Figure 4f.
Figure 8.
results with varying
r and
m of the colored Brodatz image,
Figure 4f.
Figure 9.
mean and standard deviation for MIX(p) images with 10 repetitions.
Figure 9.
mean and standard deviation for MIX(p) images with 10 repetitions.
Figure 10.
mean and standard deviation for MIX(p) images with 10 repetitions.
Figure 10.
mean and standard deviation for MIX(p) images with 10 repetitions.
Figure 11.
mean and standard deviation for MIX(p) images.
Figure 11.
mean and standard deviation for MIX(p) images.
Figure 12.
results for the 144 sub-images and 300 × 300 pixels of the CBT in the three color spaces: RGB, HSV, and YUV, with , , and being the first, second, and third channel, respectively. The mean of the 144 sub-images is displayed as a “∘” sign and the value for the 300 × 300 pixels is displayed as “*”.
Figure 12.
results for the 144 sub-images and 300 × 300 pixels of the CBT in the three color spaces: RGB, HSV, and YUV, with , , and being the first, second, and third channel, respectively. The mean of the 144 sub-images is displayed as a “∘” sign and the value for the 300 × 300 pixels is displayed as “*”.
Figure 13.
results for the 144 sub-images and 300 × 300 pixels of the CBT in the three color spaces: RGB, HSV, and YUV. The mean of the 144 sub-images is displayed as a “∘” sign and the value for the 300 × 300 pixels is displayed as “*”.
Figure 13.
results for the 144 sub-images and 300 × 300 pixels of the CBT in the three color spaces: RGB, HSV, and YUV. The mean of the 144 sub-images is displayed as a “∘” sign and the value for the 300 × 300 pixels is displayed as “*”.
Figure 14.
and Haralick feature p-values of 40 melanoma and 40 melanocytic nevi dermoscopic images in the 3 color spaces: RGB, HSV, and YUV. d represents the inter-pixel distances for the co-occurrence matrices.
Figure 14.
and Haralick feature p-values of 40 melanoma and 40 melanocytic nevi dermoscopic images in the 3 color spaces: RGB, HSV, and YUV. d represents the inter-pixel distances for the co-occurrence matrices.
Figure 15.
and Haralick feature p-values of 40 melanoma and 40 melanocytic nevi dermoscopic images in the 3 color spaces: RGB, HSV, and YUV. d represents the inter-pixel distances for the co-occurrence matrices.
Figure 15.
and Haralick feature p-values of 40 melanoma and 40 melanocytic nevi dermoscopic images in the 3 color spaces: RGB, HSV, and YUV. d represents the inter-pixel distances for the co-occurrence matrices.
Figure 16.
ROC curves for results of the 40 melanoma and 40 melanocytic nevi images in the RGB color space. The curves are for , , and from left to right.
Figure 16.
ROC curves for results of the 40 melanoma and 40 melanocytic nevi images in the RGB color space. The curves are for , , and from left to right.
Figure 17.
ROC curves for results of the 40 melanoma and 40 melanocytic nevi images in the RGB color space.
Figure 17.
ROC curves for results of the 40 melanoma and 40 melanocytic nevi images in the RGB color space.
Figure 18.
ROC curves for results of the 40 melanoma and 40 melanocytic nevi images in the RGB color space.
Figure 18.
ROC curves for results of the 40 melanoma and 40 melanocytic nevi images in the RGB color space.
Table 1.
Definition of the computed Haralick features [
43].
Table 1.
Definition of the computed Haralick features [
43].
Haralick Feature | Annotation |
---|
Uniformity (Energy) | |
Contrast | |
Correlation | |
Variance | |
Homogeneity | |
Entropy | |
Table 2.
Mann–Whitney U test p-values for , , and of 40 melanoma and 40 melanocytic nevi dermoscopic images in the 3 color spaces: RGB, HSV, and YUV, from top to bottom row, respectively.
Table 2.
Mann–Whitney U test p-values for , , and of 40 melanoma and 40 melanocytic nevi dermoscopic images in the 3 color spaces: RGB, HSV, and YUV, from top to bottom row, respectively.
| | |
---|
| | | | |
3.3 × | 7.0 × | 3.4 × | 9.0 × | 4.1 × |
2.9 × | 5.7 × | 1.5 × | 2.9 × | 2.9 × |
9.8 × | 1.7 × | 5.8 × | 4.5 × | 1.1 × |
Table 3.
Cohen’s d-values for , , and of 40 melanoma and 40 melanocytic nevi dermoscopic images in the 3 color spaces: RGB, HSV, and YUV.
Table 3.
Cohen’s d-values for , , and of 40 melanoma and 40 melanocytic nevi dermoscopic images in the 3 color spaces: RGB, HSV, and YUV.
| | | |
---|
| | | | | |
RGB | 1.50 | 1.89 | 1.97 | 2.71 | 2.19 |
HSV | 1.14 | 0.23 | 0.27 | 1.14 | 1.14 |
YUV | 1.10 | 0.58 | 0.70 | 1.00 | 1.09 |
Table 4.
ROC analysis for , , and results of 40 melanoma and 40 melanocytic nevi RGB images.
Table 4.
ROC analysis for , , and results of 40 melanoma and 40 melanocytic nevi RGB images.
| | | |
---|
| | | | | |
AUC | 0.884 | 0.945 | 0.930 | 0.964 | 0.950 |
Sensitivity | 0.825 | 0.925 | 0.900 | 0.925 | 0.925 |
Specificity | 0.850 | 0.850 | 0.825 | 0.950 | 0.900 |
Accuracy | 0.837 | 0.887 | 0.862 | 0.937 | 0.912 |
Precision | 0.846 | 0.860 | 0.837 | 0.948 | 0.902 |
Table 5.
ROC analysis for , , and results of 40 melanoma and 40 melanocytic nevi HSV images.
Table 5.
ROC analysis for , , and results of 40 melanoma and 40 melanocytic nevi HSV images.
| | | |
---|
| | | | | |
AUC | 0.771 | 0.376 | 0.406 | 0.771 | 0.771 |
Sensitivity | 0.650 | 0.325 | 0.225 | 0.650 | 0.650 |
Specificity | 0.850 | 0.600 | 0.850 | 0.850 | 0.850 |
Accuracy | 0.750 | 0.462 | 0.5375 | 0.750 | 0.750 |
Precision | 0.812 | 0.448 | 0.600 | 0.812 | 0.812 |
Table 6.
ROC analysis for , , and results of 40 melanoma and 40 melanocytic nevi images in YUV.
Table 6.
ROC analysis for , , and results of 40 melanoma and 40 melanocytic nevi images in YUV.
| | | |
---|
| | | | | |
AUC | 0.787 | 0.703 | 0.723 | 0.765 | 0.785 |
Sensitivity | 0.725 | 0.750 | 0.700 | 0.750 | 0.725 |
Specificity | 0.750 | 0.650 | 0.700 | 0.725 | 0.750 |
Accuracy | 0.737 | 0.700 | 0.700 | 0.737 | 0.737 |
Precision | 0.743 | 0.681 | 0.700 | 0.731 | 0.743 |