In this study, a novel restoration model for the data of optical coherence tomography (OCT) is proposed. An OCT device acquires a tomographic image of a specimen at the scale of a few micrometers using a near-infrared laser and has been frequently adopted to measure the structures of bio-tissues. In certain applications, OCT devices face the problem of extremely weak reflected light and require the help of image processing to estimate the distribution of reflected light hidden in various noises. OCT identifies tomographic structures by searching for peak interference locations and their intensities. Therefore, the challenge of OCT data restoration involves the problem of identifying the interference function and its deconvolution. In this study, a restoration method is given by reducing the problem to a regularized least-squares problem with a hard constraint for the latent refractive index distributions, and an algorithm is derived using a primal-dual splitting (PDS) framework. The PDS has the advantage of requiring no inverse matrix operation and is able to handle high-dimensional data. The significance of the proposed method is verified through simulations using artificial data, followed by an experiment conducted using actual observation of 64 × 64 × 5000 sized voxels.
This study proposes a convolutional nonlinear dictionary (CNLD) for image restoration using cascaded filter banks. Generally, convolutional neural networks (CNN) demonstrate their practicality in image restoration applications; however, existing CNNs are constructed without considering the relationship among atomic images (convolution kernels). As a result, there remains room for discussing the role of design spaces. To provide a framework for constructing an effective and structured convolutional network, this study proposes the CNLD. The backpropagation learning procedure is derived from certain image restoration experiments, and thereby the significance of CNLD is verified. It is demonstrated that the number of parameters is reduced while preserving the restoration performance.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.