[논문]Modified Gaussian Filter based on Fuzzy Membership Function for AWGN Removal in Digital Images

Cheon, Bong-Won; Kim, Nam-Ho

doi:10.6109/jicce.2021.19.1.54

Modified Gaussian Filter based on Fuzzy Membership Function for AWGN Removal in Digital Images 원문보기

Journal of information and communication convergence engineering, v.19 no.1, 2021년, pp.54 - 60

Cheon, Bong-Won (Department of Smart Robot Convergence and Application Engineering, Pukyong National University) , Kim, Nam-Ho (Department of Control and Instrumentation Engineering, Pukyong National University)

Abstract ▼ AI-Helper

Various digital devices were supplied throughout the Fourth Industrial Revolution. Accordingly, the importance of data processing has increased. Data processing significantly affects equipment reliability. Thus, the importance of data processing has increased, and various studies have been conducted on this topic. This study proposes a modified Gaussian filter algorithm based on a fuzzy membership function. The proposed algorithm calculates the Gaussian filter weight considering the standard deviation of the filtering mask and computes an estimate according to the fuzzy membership function. The final output is calculated by adding or subtracting the Gaussian filter output and estimate. To evaluate the proposed algorithm, simulations were conducted using existing additive white Gaussian noise removal algorithms. The proposed algorithm was then analyzed by comparing the peak signal-to-noise ratio and differential image. The simulation results show that the proposed algorithm has superior noise reduction performance and improved performance compared to the existing method.

주제어

표/그림 (9)

그림 Fig. 1. Membership function of proposed algorithm.
그림 Fig. 2. Example of fuzzy membership function.
그림 Fig. 3. Membership function output calculation.
그림 Fig. 4. Flowchart of proposed algorithm.
그림 Fig. 5. Test image: (a) boat image, (b) noisy boat image, (c) barbara image, (d) noisy barbara image, (e) goldhill image, (f) noisy goldhill image.
표 Table 1. PSNR comparison of Boat image
표 Table 2. PSNR comparison of Barbara image
표 Table 3. PSNR comparison of Goldhill image
그림 Fig. 6. Simulation results and differential images.

AI 본문요약
AI-Helper

* AI 자동 식별 결과로 적합하지 않은 문장이 있을 수 있으니, 이용에 유의하시기 바랍니다.

제안 방법

8. The differential image was calculated by applying the absolute value and multiple of four to the pixel value difference between the two images to distinctively compare the filtering results with the original image.
image. The proposed algorithm calculates five membership functions according to the pixel value distribution to calculate the weight according to the pixel value. The membership function classifies images into VD (very dark), DK (dark), MD (mid), BR (bright), and VB (very bright) according to the pixel value based on an 8-bit gray image.
The proposed algorithm calculates the fuzzy membership function using a quadratic function based on the maximum, min- imum, and mean values of all pixel values in the image.
This study proposed an algorithm that removes noise by comparing pixel values using the fuzzy membership function in the AWGN environment. The proposed algorithm calculated an estimate according to the correlation of the membership function values between the input and surrounding pixel values.
This study proposes a modified Gaussian filter algorithm that calculates its output using an estimate according to the standard deviation of pixels inside the filtering mask, the input image, and fuzzy membership function [17-20]. The proposed algorithm determines a Gaussian filter coefficient according to the standard deviation, and an estimate is calculated according to the membership degree after setting the fuzzy membership function.

데이터처리

the AWGN environment. The proposed algorithm calculated an estimate according to the correlation of the membership function values between the input and surrounding pixel values. The final output was obtained by adding or subtracting the output of the space weight filter and estimation.
The proposed algorithm determines a Gaussian filter coefficient according to the standard deviation, and an estimate is calculated according to the membership degree after setting the fuzzy membership function. The final output is calculated by adding or subtracting the Gaussian filter output, and an estimate is obtained using the fuzzy membership function.

이론/모형

In this study, the Baboon, Barbara, and Goldhill images, which are 512×512 sized 8-bit gray images damaged by AWGN with σ=10, as shown in Fig. 5, were simulated using MATLAB. Additionally, the performance of the proposed algorithm was compared with the existing AF, EDWF, and FLBF using different images and PSNR [21-23].
Generally, the membership function of the triangular fuzzy number is used extensively because it is easy to implement and express; however, the membership value changes significantly at the highest and lowest points. The proposed algorithm calculates the membership function using a quadratic function to emphasize the smoothness of the fuzzy logic [9].

성능/효과

55 [dB] compared to AF, EDWF, and FLBF, respec- tively. The proposed algorithm produced 29.07 [dB] in the Barbara image, which improved the noise by 4.09 [dB], 2.43 [dB], and 4.15 [dB] compared to each existing method, respectively. In the Goldhill image, the noise was 31.
The proposed algorithm produced 31.75 [dB] in the Boat image damaged by AWGN whose standard deviation was σ=10, and the noise was improved by 2.79 [dB], 0.85 [dB], and 2.55 [dB] compared to AF, EDWF, and FLBF, respec- tively. The proposed algorithm produced 29.
The results processed using the proposed algorithm showed that a sharp picture was verified compared to other existing methods, and the differential image was smaller even in the edge components where the pixel value was significantly changed, removing the AWGN.
The results processed with AF showed that a differential image was significantly displayed in the boundaries of the image, particularly in the mast and boundaries of the boat image and stripe areas in the Barbara image, resulting in poor performance.
The results processed with EDWF demonstrated that superior performance was displayed in the images for which the standard deviation of AWGN was relatively low; however, the PSNR comparison results showed that as the standard deviation increased, the noise removal performance was significantly degraded.
The results processed with FLBF demonstrated that excellent noise removal performance was displayed in images where the image pixel value was not significantly changed, but a differential image was displayed in areas where the edge components were strongly displayed, resulting in relatively poor performance.
The simulation results demonstrated that the proposed algorithm showed excellent performance, and the comparison results of the differential image and PSNR verified its superior characteristics.

참고문헌 (23)

T. K. Kim, I. H. Song, and S. H. Lee, "Noise reduction of HDR detail layer using a Kalman filter adapted to local image activity," Journal of Korea Multimedia Society, vol. 22, no. 1, pp. 10-17, Jan. 2019. DOI: 10.9717/kmms.2019.22.1.010.

원문보기 상세보기
P. S. V. S. Sridhar and R. Caytiles, "Efficient cloud data hosting availability," Asia-pacific Journal of Convergent Research Interchange, HSST, ISSN : 2508-9080, vol. 3, no. 2, pp. 11-19, Jun. 2017. DOI: 10.21742/APJCRI.2017.06.02.
S. Y. Kim, S. H. Yu, and J. C. Jeong, "Design and analysis of an image restoration using Wiener filter with a quality based hybrid algorithms," in Conference on The Institute of Electronics and Information Engineers, Incheon : Korea, pp. 430-433, 2018.
G. Thanakumar, S. Murugappriya, and G. R. Suresh, "High density impulse noise removal using BDND filtering algorithm," in 2014 International Conference on Communication and Signal Processing, Melmaruvathur : India, pp. 1958-1962, 2014.
K. Chithra and T. Santhanam, "Hybrid denoising technique for suppressing Gaussian noise in medical images," in 2017 IEEE International Conference on Power, Control, Signals and Instrumentation Engineering (ICPCSI), Chennai : India, pp. 1460-1463, 2017. DOI: 10.1109/ICPCSI.2017.8391954.
S. Y. Kim, S. H. Yu, and J. C. Jeong, "A Wiener filter using edge detection for Gaussian noise reduction," in Conference on The Institute of Electronics and Information Engineers, Incheon : Korea, pp. 430-433, 2018.
M. Chowdhury, J. Gao, and R. Islam, "Fuzzy logic based filtering for image de-noising," in 2016 IEEE International Conference on Fuzzy Systems, Vancouver, BC : Canada, pp. 2372-2376, 2016. DOI: 10.1109/FUZZ-IEEE.2016.7737990.
S. I. Jabbar, C. R. Day, and E. K. Chadwick, "Using fuzzy inference system for detection the edges of musculoskeletal ultrasound images," in 2019 IEEE International Conference on Fuzzy Systems, New Orleans, LA : USA, pp. 1-7, 2019. DOI: 10.1109/FUZZ-IEEE.2019.8858971.
R. C. Buenoa, P. H. F. Masottib, J. F. Justoc, D. A. Andradeb, M. S. Rochab, W. M. Torresb, and R. N. de Mesquitab, "Two-phaseflow bubble detection method applied to natural circulation system using fuzzy image processing," Journal of the Nuclear Engineering and Design, vol. 335, no. 15, pp. 255-264, Aug. 2018. DOI: 10.1016/j.nucengdes.2018.05.026.

상세보기
L. M. Herrera, M. I. C. Murguia, D. A. P. Urrutia, and J. A. R. Quintana, "Human image complexity analysis using a fuzzy inference system," in 2019 IEEE International Conference on Fuzzy Systems, New Orleans, LA : USA, pp. 1-6, 2019.
P. Mohajerani and V. Ntziachristos, "An inversion scheme for hybrid fluorescence molecular tomography using a fuzzy inference system," Journal of the IEEE Transactions on Medical Imaging, vol. 35, no. 12, pp. 381-390, Feb. 2016. DOI: 10.1109/TMI.2015.2475356.

상세보기
J. M. Mendel, H. Hagras, H. Bustince, and F. Herrera, "Comments on interval Type-2 fuzzy sets are generalization of interval-valued fuzzy sets: towards a wide view on their relationship," Journal of the IEEE Transactions on Fuzzy Systems, vol. 24, no. 1, pp. 249-250, Feb. 2016. DOI: 10.1109/TFUZZ.2015.2446508.

상세보기
N. L. S. B. Albashah, S. C. Dass, V. S. Asirvadam, and F. Meriaudeau, "Segmentation of blood clot MRI images using intuitionistic fuzzy set theory," in 2018 IEEE-EMBS Conference on Biomedical Engineering and Sciences (IECBES), Sarawak : Malaysia, pp. 533-538, 2018. DOI: 10.1109/IECBES.2018.8626678.
A. D. Belsare, M. M. Mushrif, and M. A. Pangarkar, "Breast epithelial duct region segmentation using intuitionistic fuzzy based multi-texture image map," in 2017 14th IEEE India Council International Conference (INDICON), Roorkee : India, pp. 1-6, 2017.
S. Zhang, Z. Wang, D. Ding, H. Dong, F. E. Alsaadi, and T. Hayat, "Nonfragile H∞ fuzzy filtering with randomly occurring gain variations and channel fadings," IEEE Transactions on Fuzzy Systems, vol. 24, no. 3, pp. 505-518, Jun. 2016. DOI: 10.1109/TFUZZ.2015.2446509.

상세보기
P. Shi, Y. Zhang, M. Chadli, and R. K. Agarwal, "Mixed H-infinity and passive filtering for discrete fuzzy neural networks with stochastic jumps and time delays," IEEE Transactions on Neural Networks and Learning Systems, vol. 27, no. 4, pp. 903-909, Apr. 2016. DOI: 10.1109/TNNLS.2015.2425962.

상세보기
S. K. Nguang and W. Assawinchaichote, "H∞ filtering for fuzzy dynamical systems with D stability constraints," IEEE Transactions on Circuits and Systems I Fundamental Theory and Applications, vol. 50, no. 11, pp. 1503-1508, Nov. 2003. DOI: 10.1109/TCSI.2003.818624.

상세보기
M. Wang, J. Qui, and G. Feng, "A novel piecewise affine filtering design for T-S fuzzy affine systems using past output measurements," IEEE Transactions on Cybernetics, vol. 50, no. 4, pp. 1509-1518, Apr. 2020. DOI: 10.1109/TCYB.2018.2883476.

상세보기
P. Yiarayong, "On fuzzy quasi-prime ideals in near left almost rings," Songklanakarin Journal of Science and Technology, vol. 41, no. 2, pp. 471-482, Apr. 2019. DOI: 10.14456/sjst-psu.2019.59.
F. Pasila, "Credit scoring modeling of indonesian micro, small and medium enterprises using Neuro-fuzzy algorithm," in 2019 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE), New Orleans, LA : USA, pp. 1-6, 2019. DOI: 10.1109/FUZZ-IEEE.2019.8858841.
S. G. Kim and J. H. Yoon, "Fuzzy linear regression using Gaussian fuzzy numbers," Journal of Korean Institute of Intelligent Systems, vol. 30, no. 5, pp. 386-390, Oct. 2020. DOI: 10.5391/JKIIS.2020.30.5.386.

상세보기
J. Zhang, Z. Deng, K. S. Choi, and S. Wang, "Data-driven elastic fuzzy logic system modeling: constructing a concise system with human-like inference mechanism," IEEE Transactions on Fuzzy Systems, vol. 26, no. 4, pp. 2160-2173, Aug. 2018. DOI: 10.1109/TFUZZ.2017.2767025.

상세보기
K. Sato and H. Sato, "Structure preserving H 2 optimal model reduction based on Riemannian trust-region method," Journal of IEEE Transactions on Automatic Control, vol. 63, no. 2, pp. 505-512, Feb. 2018. DOI: 10.1109/TAC.2017.2723259.

상세보기

표제어: PCR

동의어: Packet Collision Rate

용어 설명 출처 목록 (6)

용어 설명: PCR은 세균 특이성이 있는 primer를 이용하여 적은 수의 세균이 있을지라도 쉽게 검출할 수 있는 유용한 방법이며, 이를 이용하여 구강 내 치면세균막이나 타액에서 직접 세균을 검출할 수 있게 되었다[8].

내보내기 구분	파일저장 인쇄 메일전송
구성항목	기본정보 상세정보 관리번호, 논문명, 저널/프로시딩명, 저자 , 발행년, 권, 호, 시작페이지, 끝페이지, 발행기관 관리번호, 논문명, 대등논문명, 저자 , 저널/프로시딩명, 발행기관, 발행년, 발행언어, 권, 호, 시작페이지, 끝페이지, ISBN, ISSN, 주제분야, 키워드, 초록(한글), 초록(영문), 저자(소속기관)
저장형식	Text(ASCII format) Excel format RefWorks Direct Export RIS format (for Reference Manager, ProCite, EndNote), Scholar's Aids, Mendeley
메일정보	받는사람 (필수) @ 보내는사람 (선택) @ 제목 내용 KISTI 검색결과 이메일 서비스
안내	총 건의 자료가 검색되었습니다. 다운받으실 자료의 인덱스를 입력하세요. (1-10,000) 검색결과의 순서대로 최대 10,000건 까지 다운로드가 가능합니다. 데이타가 많을 경우 속도가 느려질 수 있습니다.(최대 2~3분 소요) 다운로드 파일은 UTF-8 형태로 저장됩니다. 파일의 내용이 제대로 보이지 않을실 때는 웹브라우저 상단의 보기 -> 인코딩 -> 자동선택 여부를 확인하십시오. ~ Text(ASCII format) Excel format

연합인증