Noise Reduction Method for Intestinal Image Acquired by Intestinal Robot

doi:10.16183/j.cnki.jsjtu.2020.245

Abstract

Abstract:

The wireless powered intestinal robot transmits the intestinal images taken by the image acquisition system to the external upper computer for diagnosis. However, the image transmission process will be interfered by the circuit structure and external environment, leading to noise in the collected images. Therefore, an image denoising algorithm based on non-subsampled contourlet transform (NSCT) is proposed to reduce the noise of the images collected by intestinal robots. First, histogram equalization pretreatment is adopted to improve the brightness and contrast of intestinal noise images. Next, NSCT transformation is performed on intestinal noise images and a residual network model is constructed to reduce the noise of frequency domain information after transformation. Finally, the denoised image is reconstructed by NSCT inverse transformation. The results show that the proposed algorithm can effectively reduce the influence of intestinal noise in complex environments, and better maintain the visual effect of the image. Compared with other intelligent algorithm models, both subjective and objective noise reduction effects are improved, with peak signal to noise ratio (PSNR) improved by 1.35 to 3.45 dB and structural similarity index measure (SSIM) improved by 0.0083 to 0.0252.

Key words: wireless powered intestinal robot, non-subsampled contourlet transform, convolutional neural network (CNN)

CLC Number:

XUE Rongrong, WANG Zhiwu, YAN Guozheng, ZHUANG Haoyu. Noise Reduction Method for Intestinal Image Acquired by Intestinal Robot[J]. Journal of Shanghai Jiao Tong University, 2021, 55(10): 1303-1309.

Figures/Tables 11

Fig.1

Fig.2

Fig.3

Fig.4

Fig.5

Fig.6

Fig.7

Fig.8

Fig.9

Tab.1

Tab.2

References 13

[1]	NING Y, WAN JUN M A. Study of image denoising in robot visual navigation system[J]. Journal of Measurement Science and Instrumentation, 2011, 2(1):21-24.
[2]	彭宇. 医学内窥镜图像的横纹消除算法仿真[J]. 计算机仿真, 2013, 30(7):417-420.
	PENG Yu. Medical endoscope image transverse striation elimination algorithm simulation[J]. Computer Simulation, 2013, 30(7):417-420.
[3]	DUDA K, ZIELINSKI T, DUPLAGA M. Computationally simple super-resolution algorithm for video from endoscopic capsule[C]// 2008 International Conference on Signals and Electronic Systems. Krakow, Poland: IEEE, 2008: 197-200.
[4]	JAIN V, SEUNG S. Natural image denoising with convolutional networks[C]// Advances in Neural Information Processing Systems, Vancouver B C, Canada: NIPS Foundation, 2009: 769-776.
[5]	ZHANG K, ZUO W M, CHEN Y J, et al. Beyond a Gaussian denoiser: Residual learning of deep CNN for image denoising[J]. IEEE Transactions on Image Processing, 2017, 26(7):3142-3155. doi: 10.1109/TIP.83 URL
[6]	ZOU S, LONG M, WANG X, et al. A CNN-based blind denoising method for endoscopic images[C]// Biomedical Circuits and Systems Conference (BioCAS). Nara, Japan: IEEE, 2019: 1-4.
[7]	刘刚. 基于无线供能的胃肠道视频胶囊内窥镜系统及肿瘤图像识别算法研究[D]. 上海: 上海交通大学, 2016.
	LIU Gang. Research of gastrointestinal video capsule endoscopy based on wireless power transmission and tumor image recognition[D]. Shanghai: Shanghai Jiao Tong University, 2016.
[8]	于佳欣. 便携式B型超声诊断设备图像的去噪算法研究与实现[D]. 黑龙江: 哈尔滨工业大学, 2019.
	YU Jiaxin. Research and implementation of image denoising algorithm for portable B-type ultrasonic diagnostic equipment[D]. Heilongjiang: Harbin Institute of Technology, 2019.
[9]	孙玉姣. 含噪运动模糊图像的恢复算法研究[D]. 陕西: 陕西师范大学, 2018.
	SUN Yujiao. Research on restoration algorithm of noise-motion fuzzy image[D]. Shaanxi: Shaanxi Normal University, 2018.
[10]	杨涛, 吴孙桃, 郭东辉. CMOS图像传感器电路噪声分析[J]. 厦门大学学报(自然科学版), 2012, 51(3):321-326.
	YANG Tao, WU Suntao, GUO Donghui. Analysis of noise behavior in CMOS image sensor[J]. Journal of Xiamen University (Natural Science), 2012, 51(3):321-326.
[11]	DA CUNHA A L, ZHOU J, DO M N. The nonsubsampled contourlet transform: Theory, design, and applications[J]. IEEE Transactions on Image Processing, 2006, 15(10):3089-3101. doi: 10.1109/TIP.2006.877507 URL
[12]	SEZER A, SEZER H B. Deep convolutional neural network-based automatic classification of neonatal hip ultrasound images: A novel data augmentation approach with speckle noise reduction[J]. Ultrasound in Medicine & Biology, 2020, 46(3):735-749. doi: 10.1016/j.ultrasmedbio.2019.09.018 URL
[13]	HEO K, LIM D H. Noise reduction using patch-based CNN in images[J]. Journal of the Korean Data and Information Science Society, 2019, 30(2):349-363. doi: 10.7465/jkdi.2019.30.2.349 URL

PSNR	CNN	NSCT-CNN	NSCT-残差CNN
A	24.52	26.83	28.73
B	24.37	28.85	29.68
C	25.63	25.14	26.45
均值	24.84	26.94	28.29

PSNR	CNN	NSCT-CNN	NSCT-残差CNN
A	0.8832	0.9091	0.9139
B	0.8901	0.9079	0.9123
C	0.8778	0.8848	0.9005
均值	0.8837	0.9006	0.9089