Weak-Light Image Segmentation Based on Intercept Histogram and Otsu Fusion

Yanyang Zeng; Gaosen Xie; Jianchun Zhang

doi:10.3788/LOP202158.2010016

Journals >Laser & Optoelectronics Progress >Volume 58 >Issue 20 >Page 2010016 > Article

Laser & Optoelectronics Progress
Vol. 58, Issue 20, 2010016 (2021)

Weak-Light Image Segmentation Based on Intercept Histogram and Otsu Fusion

Yanyang Zeng, Gaosen Xie, and Jianchun Zhang^*

Author Affiliations

Computer Science and Technical College, Henan Polytechnic University, Jiaozuo, Henan 454003, China

show less

DOI: 10.3788/LOP202158.2010016 Cite this Article Set citation alerts

Yanyang Zeng, Gaosen Xie, Jianchun Zhang. Weak-Light Image Segmentation Based on Intercept Histogram and Otsu Fusion[J]. Laser & Optoelectronics Progress, 2021, 58(20): 2010016 Copy Citation Text

show less

Fig. 1. Regions in 2D histogram. (a) Histogram method; (b) line interpret histogram method

Download full size

Fig. 2. Directions about a pixel. (a) Eight directions of center pixel; (b) NW direction of edge of SW-NE direction

Download full size

Fig. 3. Algorithm segmentation results. (a) Original image; (b) result obtained by Otsu; (c) result obtained by directional fuzzy derivative; (d) fusion result

Download full size

Fig. 4. Algorithm segmentation results. (a) Original image 1; (b) Otsu; (c) 2D maximum entropy; (d) algorithm in Ref. [18]; (e) algorithm in Ref. [23]; (f) proposed method

Download full size

Fig. 5. Algorithm segmentation results. (a) Original image 2; (b) Otsu; (c) 2D maximum entropy; (d) algorithm in Ref. [18]; (e) algorithm in Ref. [23]; (f) proposed method

Download full size

Fig. 6. Algorithm segmentation results. (a) Original image 3; (b)Otsu; (c) 2D maximum entropy; (d) algorithm in Ref. [18]; (e) algorithm in Ref. [23]; (f) proposed method

Download full size

Fig. 7. Fuzzy derivative segmentation results. (a) Segmentation result of Fig. 4(a); (b) segmentation result of Fig. 5(a); (c) segmentation result of Fig. 6(a)

Download full size

Fig. 8. Algorithm segmentation results of image 1. (a) Original image; (b) Otsu; (c) 2D maximum entropy; (d) algorithm in Ref. [18]; (e) algorithm in Ref. [23]; (f) proposed method

Download full size

Fig. 9. Algorithm segmentation results of image 2. (a) Original image; (b) Otsu; (c) 2D maximum entropy; (d) algorithm in Ref. [18]; (e) algorithm in Ref. [23]; (f) proposed method

Download full size

Fig. 10. Algorithm segmentation results of image 3. (a) Original image; (b) Otsu; (c) 2D maximum entropy; (d) algorithm in Ref. [18]; (e) algorithm in Ref. [23]; (f) proposed method

Download full size

Fig. 11. Algorithm segmentation results of image 4. (a) Original image; (b) Otsu; (c) 2D maximum entropy; (d) algorithm in Ref. [18]; (e) algorithm in Ref. [23]; (f) proposed method

Download full size

Fig. 12. Algorithm segmentation results of image 5. (a) Original image; (b) Otsu; (c) 2D maximum entropy; (d) algorithm in Ref. [18]; (e) algorithm in Ref. [23]; (f) proposed method

Download full size

Algorithm	Parameter	Fig. 8	Fig. 9	Fig. 10	Fig. 11	Fig. 12
	RMSE	0.1852	0.1856	0.1878	0.1863	0.1898
Otsu	SSIM	0.9964	0.9964	0.9964	0.9964	0.9964
	PSNR	29.2957	29.2540	29.0510	29.1909	28.8709
2D maximumentropy	RMSE	0.2356	0.1516	0.2586	0.2781	0.2970
	SSIM	0.9940	0.9977	0.9927	0.9915	0.9902
	PSNR	25.1105	32.7700	23.4933	22.2315	21.0909
	RMSE	0.1686	0.1816	0.1520	0.2124	0.1954
Algorithm in Ref. [18]	SSIM	0.9989	0.9986	0.9992	0.9979	0.9983
	PSNR	30.9219	29.6318	32.7314	26.9148	28.3674
	RMSE	0.1838	0.1842	0.1852	0.1843	0.1885
Algorithm in Ref. [23]	SSIM	0.9964	0.9964	0.9964	0.9964	0.9963
	PSNR	29.4301	29.3874	29.2908	29.3744	28.9850
	RMSE	0.0292	0.0221	0.0435	0.0416	0.0416
Proposed method	SSIM	0.9998	0.9998	0.9998	0.9998	0.9998
	PSNR	61.3895	66.2616	54.4424	55.2410	55.2410

Table 1. Quantitative comparison of various segmentation methods

Algorithm	Parameter	Fig. 8	Fig. 9	Fig. 10	Fig. 11	Fig. 12
	RMSE	0.2275	0.2285	0.3065	0.2392	0.2275
Otsu	SSIM	0.9962	0.9961	0.9915	0.9959	0.9962
	PSNR	25.7245	25.6437	20.5404	24.8494	25.7172
2D maximumentropy	RMSE	0.2648	0.2007	0.2878	0.3047	0.3070
	SSIM	0.9941	0.9974	0.9927	0.9916	0.9907
	PSNR	23.0802	27.8986	21.6358	20.6448	20.5169
	RMSE	0.2162	0.1841	0.1749	0.2286	0.2170
Algorithm in Ref. [18]	SSIM	0.9980	0.9988	0.9990	0.9977	0.9980
	PSNR	26.6021	29.4007	30.2870	25.6402	26.5443
	RMSE	0.2270	0.2265	0.3045	0.2307	0.2261
Algorithm in Ref. [23]	SSIM	0.9962	0.9962	0.9916	0.9961	0.9962
	PSNR	25.7620	25.7962	20.6585	25.4761	25.8264
	RMSE	0.1431	0.1395	0.1644	0.1673	0.1429
Proposed method	SSIM	0.9995	0.9995	0.9993	0.9993	0.9995
	PSNR	33.7796	34.2118	31.3650	31.0643	33.7985

Table 2. Quantitative comparison of various segmentation methods

Yanyang Zeng, Gaosen Xie, Jianchun Zhang. Weak-Light Image Segmentation Based on Intercept Histogram and Otsu Fusion[J]. Laser & Optoelectronics Progress, 2021, 58(20): 2010016

Download Citation

Set citation alerts for the article

Tools

Set citation alerts for the article

Save the article for my favorites

Paper Information