An analysis of denoising neural networks for noise removal in images

• Autorzy: Ramakotti Raksha , Paneerselvam Surekha , Kumar Vinodh , Kumar Sachin , Evangeline Jebarani

Identyfikatory

DOI

10.15199/48.2023.02.04

Warianty tytułu

PL

(Analiza możliwości wykorzysyania sieci neuronowych do odszumiania obrazu

• Języki publikacji: EN

Abstrakty

EN

Clean images, when subjected to prolonged transmission, improper image acquisition or conditioned to multiple feature changes, lead to image tarnishing due to unwanted noisy pixels. This proposes to be a major threat in image-processing and computer vision fields. With the evolution of denoising models in the field of Neural Networks, efficient noise removal has become achievable, in a real-time scenario. In this work, two approaches to noise modelling have been considered, i.e., noise as an inverse problem and noise as a residual problem, this has been done by constructing convolutional auto encoders and denoising convolutional networks and their performance in the process of noise removal has been evaluated based on Peak Signal to Noise Ratio (PSNR) and Structural Similarity Index (SSIM).

PL

Czyste obrazy poddane przedłużonej transmisji, niewłaściwej akwizycji obrazu lub poddane wielokrotnym zmianom cech prowadzą do zmatowienia obrazu z powodu niechcianych zaszumionych pikseli. Sugeruje to, że jest to poważne zagrożenie w dziedzinie przetwarzania obrazu i widzenia komputerowego. Wraz z ewolucją modeli odszumiania w dziedzinie sieci neuronowych, efektywne usuwanie hałasu stało się osiągalne w scenariuszu czasu rzeczywistego. W niniejszej pracy rozważono dwa podejścia do modelowania hałasu, tj. hałas jako problem odwrotny i hałas jako problem rezydualny. Dokonano tego poprzez skonstruowanie autoenkoderów splotowych i odszumianie sieci splotowych, a ich wydajność w procesie usuwania hałasu oceniane na podstawie stosunku sygnału szczytowego do szumu (PSNR) i wskaźnika podobieństwa strukturalnego (SSIM).

Słowa kluczowe

EN

denoising models; autoencoders; residual network; deep learning

PL

modele odszumiania; automatyczne kodery; sieci rezydualne; głębokie uczenie

• Wydawca: Wydawnictwo SIGMA-NOT
• Czasopismo: Przegląd Elektrotechniczny
• Rocznik: 2023
• Tom: R. 99, nr 2
• Strony: 27--31
• Opis fizyczny: Bibliogr. 22 poz., rys., tab.

Twórcy

autor

Ramakotti Raksha

• Amrita School of Engineering, Bengaluru, India

• https://orcid.org/0000-0001-8982-3879

autor

Paneerselvam Surekha

• Amrita School of Engineering, Bengaluru, India

• https://orcid.org/0000-0003-4749-0564

autor

Kumar Vinodh

• New Horizon College of Engineering, Bengaluru, India

• https://orcid.org/0000-0002-3009-1658

autor

Kumar Sachin

• South Ural State University, Chelyabinsk, Russian Federation

• https://orcid.org/0000-0003-3949-0302

autor

Evangeline Jebarani

• SNS College of Engineering, Coimbatore India

• https://orcid.org/0000-0002-2762-285X

Bibliografia

• [1] Tian, Chunwei, Yong Xu, and Wangmeng Zuo. "Image denoising using deep CNN with batch renormalization." Neural Networks 121 (2020): 461-473.
• [2] Tian, Chunwei, Yong Xu, Lunke Fei, Junqian Wang, Jie Wen, and Nan Luo. "Enhanced CNN for image denoising." CAAI Transactions on Intelligence Technology 4, no. 1 (2019): 17-23.
• [3] Tian, Chunwei, Lunke Fei, Wenxian Zheng, Yong Xu, Wangmeng Zuo, and Chia-Wen Lin. "Deep learning on image denoising: An overview." Neural Networks (2020).
• [4] Akarsh, S., K. Simran, Prabaharan Poornachandran, Vijay Krishna Menon, and K. P. Soman. "Deep learning framework and visualization for malware classification." In 2019 5th International Conference on Advanced Computing & Communication Systems (ICACCS), pp. 1059-1063. IEEE, 2019.
• [5] Selvin, Sreelekshmy, R. Vinayakumar, E. A. Gopalakrishnan, Vijay Krishna Menon, and K. P. Soman. "Stock price prediction using LSTM, RNN and CNN-sliding window model." In 2017 international conference on advances in computing, communications and informatics (icacci), pp. 1643-1647. IEEE, 2017.
• [6] Subbiah, Uma, Rahul Vinod Kumar, Shruti Ajithkumar Panicker, R. Aathith Bhalaje, and S. Padmavathi. "An Enhanced Deep Learning Architecture for the Classification of Cancerous Lymph Node Images." In 2020 SecondInternational Conference on Inventive Research in Computing Applications (ICIRCA), pp. 381-386. IEEE, 2020.
• [7] Srinivasan, Sriram, Vinayakumar Ravi, V. Sowmya, Moez Krichen, Dhouha Ben Noureddine, Shashank Anivilla, and Soman Kp. "Deep convolutional neural network based image spam classification." In 2020 6th conference on data science and machine learning applications (CDMA), pp. 112-117. IEEE, 2020.
• [8] Chaumont, Marc. "Deep learning in steganography and steganalysis." In Digital Media Steganography, pp. 321-349. Academic Press, 2020.
• [9] Raksha, R., and P. Surekha. "A Cohesive Farm Monitoring and Wild Animal Warning Prototype System using IoT and Machine Learning." In 2020 International Conference on Smart Technologies in Computing, Electrical and Electronics (ICSTCEE), pp. 472-476. IEEE, 2020.
• [10] Bajaj, Komal, Dushyant Kumar Singh, and Mohd Aquib Ansari. "Autoencoders based deep learner for image denoising." Procedia Computer Science 171 (2020): 1535-1541.
• [11] Zhang, Jinsong, Yi Zhang, Lianfa Bai, and Jing Han. "Lossless-constraint denoising based auto-encoders." Signal Processing: Image Communication 63 (2018): 92-99.
• [12] Akaash, B., and R. Aarthi. "An Analysis of Rainstreak Modeling as a Noise Parameter Using Deep Learning Techniques." In Advances in Computing and Network Communications, pp. 465-477. Springer, Singapore, 2021.
• [13] Nishio, Mizuho, Chihiro Nagashima, Saori Hirabayashi, Akinori Ohnishi, Kaori Sasaki, Tomoyuki Sagawa, Masayuki Hamada, and Tatsuo Yamashita. "Convolutional auto-encoder for image denoising of ultra-low-dose CT." Heliyon 3, no. 8 (2017): e00393.
• [14] Tian, Chunwei, Yong Xu, Lunke Fei, Junqian Wang, Jie Wen, and Nan Luo. "Enhanced CNN for image denoising." CAAI Transactions on Intelligence Technology 4, no. 1 (2019): 17-23.
• [15] Haque, Kazi Nazmul, Mohammad Abu Yousuf, and Rajib Rana. "Image denoising and restoration with CNN-LSTM Encoder Decoder with Direct Attention." arXiv preprint arXiv:1801.05141 (2018).
• [16] Peng, P., Jalali, S., & Yuan, X. (2020). Solving inverse problems via auto-encoders. IEEE Journal on Selected Areas in Information Theory, 1(1), 312-323.
• [17] Zhang, Kai, Wangmeng Zuo, Yunjin Chen, Deyu Meng, and Lei Zhang. "Beyond a gaussian denoiser: Residual learning of deep cnn for image denoising." IEEE transactions on image processing 26, no. 7 (2017): 3142-3155.
• [18] Lin, Tsung-Yi, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Dollár, and C. Lawrence Zitnick. "Microsoft coco: Common objects in context." In European conference on computer vision, pp. 740-755. Springer, Cham, 2014.
• [19] Martin, David, Charless Fowlkes, Doron Tal, and Jitendra Malik. "A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics." In Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001, vol. 2, pp. 416-423. IEEE, 2001.
• [20] Ioffe, Sergey, and Christian Szegedy. "Batch normalization: Accelerating deep network training by reducing internal covariate shift." In International conference on machine learning, pp. 448-456. PMLR, 2015.
• [21] Hore, A., & Ziou, D. (2010, August). Image quality metrics: PSNR vs. SSIM. In 2010 20th international conference on pattern recognition (pp. 2366-2369). IEEE.
• [22] Wang, Z., Bovik, A. C., Sheikh, H. R., & Simoncelli, E. P. (2004). Image quality assessment: from error visibility to structural similarity. IEEE transactions on image processing, 13(4), 600-612.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa nr SONP/SP/546092/2022 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2024).