Publication Type : Book
Publisher : Springer Nature Singapore
Source : IoT Based Control Networks and Intelligent Systems: Proceedings of 3rd ICICNIS 2022 Pages 425-435, 2022
Url : https://link.springer.com/chapter/10.1007/978-981-19-5845-8_30
Campus : Amritapuri
School : School of Engineering
Department : Electronics and Communication
Year : 2022
Abstract : Many times, noise corrupts images, especially fluorescence microscopic data. Conventional methods for increasing the Signal to Noise ratio (SNR) of corrupted images, such as deconvolution frequently fail to achieve a high SNR since only an estimate of the point spread function is available due to modelling deficiencies or complications. In comparison to statistical approaches, deep learning methods significantly enhanced the SNR of reconstructed images. Deep learning algorithms are computationally simpler while still outperforming approaches that are computationally intensive. In this work, we attempt to reconstruct images using Variational Autoencoders and CycleGAN. Metrics like Peak Signal to Noise Ratio (PSNR) and Mean Square Error (MSE) are used for evaluating the quality of reconstruction.
Cite this Research Publication : Charan, M.G.K.S. et al. (2023). Fluorescence Microscopic Image Reconstruction Using Variational Autoencoder and CycleGAN. In: Joby, P.P., Balas, V.E., Palanisamy, R. (eds) IoT Based Control Networks and Intelligent Systems. Lecture Notes in Networks and Systems, vol 528. Springer, Singapore.