Author Affiliations
1College of Artificial Intelligence, Yango University, Fuzhou, Fujian 350015, China2College of Physics and Information Engineering, Fuzhou University, Fuzhou, Fujian 350108, Chinashow less
Fig. 1. Tiansi operator
Fig. 2. Decomposing process of NSCT
Fig. 3. Flow chart of the proposed method
Fig. 4. Original images for experiment. (a) Lena; (b) cartoon image
Fig. 5. Edge detection results of Lena image. (a) Low frequency; (b) high frequency scale 1; (c) high frequency scale 2; (d) high frequency; (e) fusion result
Fig. 6. Edge detection results of cartoon image. (a) Low frequency; (b) high frequency scale 1; (c) high frequency scale 2; (d) high frequency; (e) fusion result
Fig. 7. Edge extraction results of Lena image. (a) Original image; (b) image with 10% noise; (c) extraction result with 10% noise; (d) image with 50% noise; (e) extraction result with 50% noise
Fig. 8. Edge extraction results of medical image 1. (a) Original image; (b) image with 10% noise; (c) extraction result with 10% noise; (d) image with 50% noise; (e) extraction result with 50% noise
Fig. 9. Edge extraction results of medical image 2. (a) Original image; (b) image with 10% noise; (c) extraction result with 10% noise; (d) image with 50% noise; (e) extraction result with 50% noise
Fig. 10. Extracted results of methods for Lena image. (a) Canny; (b) method in Ref. [7]; (c) method in Ref. [15]; (d) method in Ref. [20]; (e) proposed method
Fig. 11. Extracted results of methods for cartoon image. (a) Canny; (b) method in Ref. [7]; (c) method in Ref. [15]; (d) method in Ref. [20]; (e) proposed method
Fig. 12. Processing results of different methods for noisy Lena image. (a) Method in Ref. [7]; (b) method in Ref. [15]; (c) method in Ref. [16]; (d) method in Ref. [20]; (e) proposed method
Fig. 13. Processing results of different methods for noisy medical image 1. (a) Method in Ref. [7]; (b) method in Ref. [15]; (c) method in Ref. [16]; (d) method in Ref. [20]; (e) proposed method
Fig. 14. Processing results of different methods for noisy medical image 2. (a) Method in Ref. [7]; (b) method in Ref. [15]; (c) method in Ref. [16]; (d) method in Ref. [20]; (e) proposed method
Fig. 15. Comparison of results of different methods for different noise. (a) Lena image; (b) medical image 1; (c) medical image 2
Index | Canny | Method in Ref. [7] | Method in Ref. [15] | Method in Ref. [20] | Proposed method |
---|
α | 5064 | 1754 | 6872 | 9532 | 9841 | β | 6103 | 2678 | 8036 | 10529 | 10547 | R | 0.830 | 0.655 | 0.855 | 0.905 | 0.933 |
|
Table 1. Comparison of extracted results of Lena image by different methods
Index | Canny | Method in Ref. [7] | Method in Ref. [15] | Method in Ref. [20] | Proposed method |
---|
α | 7762 | 3378 | 10378 | 13213 | 15693 | β | 9284 | 5211 | 12053 | 14501 | 16802 | R | 0.836 | 0.648 | 0.861 | 0.911 | 0.934 |
|
Table 2. Comparison of extracted results for cartoon image by different methods