Tchebichef Transform Domain-based Deep Learning Architecture for Image Super-resolution

Abstract

The recent outbreak of COVID-19 has motivated researchers to contribute in the area of medical imaging using artificial intelligence and deep learning. Super-resolution (SR), in the past few years, has produced remarkable results using deep learning methods. The ability of deep learning methods to learn the non-linear mapping from low-resolution (LR) images to their corresponding high-resolution (HR) images leads to compelling results for SR in diverse areas of research. In this paper, we propose a deep learning based image superresolution architecture in Tchebichef transform domain. This is achieved by integrating a transform layer into the proposed architecture through a customized Tchebichef convolutional layer (T CL). The role of T CL is to convert the LR image from the spatial domain to the orthogonal transform domain using Tchebichef basis functions. The inversion of the aforementioned transformation is achieved using another layer known as the Inverse Tchebichef convolutional Layer (IT CL), which converts back the LR images from the transform domain to the spatial domain. It has been observed that using the Tchebichef transform domain for the task of SR takes the advantage of high and lowfrequency representation of images that makes the task of superresolution simplified. We, further, introduce transfer learning approach to enhance the quality of Covid based medical images. It is shown that our architecture enhances the quality of Xray and CT images of COVID-19, providing a better image quality that helps in clinical diagnosis. Experimental results obtained using the proposed Tchebichef transform domain superresolution (TTDSR) architecture provides competitive results when compared with most of the deep learning methods employed using a fewer number of trainable parameters.

Fast and accurate computation of high‐order Tchebichef polynomials

“…16 Among other transforms, discrete Tchebichef transform (DTT) shows a high compression ratio because discrete Tchebichef moments (DTMs) show remarkable energy compaction and data decorrelation to other DOPs. 2,17,18 The potential application of DTPs is content-based image retrieval, 19 image compression, 20 color image compression, 21 seizure detection, 22 image watermarking, 23 classification of super-resolution images, 24 and video coding. 25 DTPs are generally a two-dimensional array with three parameters which are: (1) the size of the array N × N, (2) the parameter which represents the polynomial order (n), and (3) the parameter which represents the signal index (x).…”