Medical images fusion using two-stage combined model DWT and DCT

Abstract

The purpose of image enhancement is to improve the interpretation or perception of information in the image for viewers and the input of automated processing systems. Combining a multicenter image is a way of combining several images on a screen, focusing on different objects so that all objects appear in focus in the final image. Wavelet transform and cosine transform are used in many image processing applications, including image fusion. This paper's technique will combine DWT and DCT in two steps for medical MRI and PET images, eventually extracting the combined image. Input images are first divided into 8-pixel blocks in which DCT coefficients are extracted. After extracting the DCT coefficients, the first step of the combination takes place. The re-images will then be combined with the DWT conversion. According to the presented data, the proposed method achieved up to 5% better combination and, as a result, better image quality than the singlestage DWT and DCT methods.

Advancements In Multi-Modality Medical Image Fusion: A Comprehensive Review

“…Kapinaiah et al [13] proposed and compared various image enhancement techniques for improving the quality of MRI images. For medical MRI with PET imaging, Ehsan et al [14] combined DWT with DCT in two phases, eventually obtaining the composite image. Initially, DCT coefficients are retrieved from input images that have been separated into 8-pixel blocks.…”

Machine Interpretation of Ballet Dance: Alternating Wavelet Spatial and Channel Attention Based Learning Model

“…The other transformation that has the ability to nullify the information loss in DCT is the discrete wavelet transform (DWT). The conventional advantage of DWT lies in its ability to generate contextual image features in orthogonal space [10]. Specifically, 3D DWT was applied to extract relational features from video data [11].…”