3-D laser scanning image denoising based on HSSIM and residual ratio threshold

CUI Zhi; DENG Shuguang; XIAO Weichu

doi:10.7510/jgjs.issn.1001-3806.2015.05.018

In order to get better results of 3-D laser scanning image denoising, an improved sparse representation denoising algorithm was proposed by combining histogram structural similarity (HSSIM) and residual ratio threshold. The initial over-complete dictionary was applied in the sparse decomposition. The reconstruction error was replaced by similarity factor as fidelity factor. Then the residual ratio threshold was used as the iteration termination of the orthogonal matching pursuit algorithm to reconstruct the denoised image. Finally, the performance data of denoised image, such as peak signal-to-noise ratio(PSNR) and HSSIM, were obtained. The experimental results show that the proposed method could provide better PSNR and HSSIM results compared with the image denoising methods using db2 wavelet transform, multiscale curve wave transform and discrete cosine transform. Meanwhile, the structural features can be reserved effectively by the proposed method.

3-D laser scanning image denoising based on HSSIM and residual ratio threshold

1. School of Communication and Electronic Engineering, Hunan City University, Yiyang 413000, China

Received Date: 2014-07-24

Accepted Date: 2014-08-29

Available Online: 2015-09-25

Abstract: In order to get better results of 3-D laser scanning image denoising, an improved sparse representation denoising algorithm was proposed by combining histogram structural similarity (HSSIM) and residual ratio threshold. The initial over-complete dictionary was applied in the sparse decomposition. The reconstruction error was replaced by similarity factor as fidelity factor. Then the residual ratio threshold was used as the iteration termination of the orthogonal matching pursuit algorithm to reconstruct the denoised image. Finally, the performance data of denoised image, such as peak signal-to-noise ratio(PSNR) and HSSIM, were obtained. The experimental results show that the proposed method could provide better PSNR and HSSIM results compared with the image denoising methods using db2 wavelet transform, multiscale curve wave transform and discrete cosine transform. Meanwhile, the structural features can be reserved effectively by the proposed method.

HTML

Reference (13)

[1]	ZHANG H X. Study on building modeling based on 3-D laser scanning technology[J]. Laser Technology, 2014, 38(3): 431-434 (in Chinese).
[2]	XU Y F, XU J, ZHAO F L, et al. Laser active image denoising method based on wavelet transform[J]. High Power Laser and Particle Beams, 2009, 21(12): 1786-1790 (in Chinese).
[3]	CAI Z M, LAI J H. An over-complete learned dictionary-based image de-noising method[J]. Acta Electronica Sinica, 2009, 37(2): 347-350 (in Chinese).
[4]	ELAD M, AHARON M. Image denoising via sparse and redundant representations over learned dictionaries[J]. IEEE Transactions on Image Processing, 2006, 12(15):3736-3745.
[5]	WU U Q, LI L. Image denoising using kernel fuzzy clustering and regularization on sparse model[J]. Acta Photonica Sinica, 2014, 43(3): 1-7 (in Chinese).
[6]	WANG C, SU W M, GU H, et al. SAR image despeckling based on morphological component analysis[J]. Chinese Journal of Radio Science, 2013, 28(3): 448-454 (in Chinese).
[7]	WEI Y L, WEN X B, ZHOU Y L, et al. New self-adaptive method for image denoising based on sparse decomposition and clustering[J]. Journal of Computer Applications, 2013, 33(2): 476-479 (in Chinese).
[8]	MA L, DENG C Z, WANG S Q, et al. Feature-retained image de-noising via sparse representation[J]. Journal of Computer Applications, 2013, 33(5):1416-1419 (in Chinese).
[9]	DABOV K, FOI A, KATAKOVIK V, et al. Image denoising by sparse 3-D transform-domain collaborative filtering[J].IEEE Transactions on Image Processing, 2007, 16(8): 2080-2095.
[10]	FANG L Y, LI S T, MCNABB R, et al. Fast acquisition and reconstruction of optical coherence tomography images via sparse representation[J]. IEEE Transactions on Medical Imaging, 2013, 32(11): 2034-2049.
[11]	AHARON M, ELAD M, BRUCKSTEIN. K-SVD: an algorithm for designing overcomplete dictionaries for sparse representation[J]. IEEE Transactions on Image Processing, 2006, 54(11): 4311-4322.
[12]	ZHU L, LI Q L, ZHANG T, et al. Metric of image quality based on structural simnarity [J]. Opto-Electronic Engineering, 2007, 34(11): 108-113 (in Chinese).
[13]	LIANG W, QUE P W, CHEN L, et al. Residual ratio iteration termination condition for MP method[J]. Journal of Shanghai Jiaotong University, 2010, 44(2): 171-175 (in Chinese).

3-D laser scanning image denoising based on HSSIM and residual ratio threshold

Abstract

References

Proportional views

通讯作者: 陈斌, bchen63@163.com

Proportional views