Abstract
The high contrast for images taken of a human body by the medical apparatuses is quite
important to diagnose the patient case perfectly. In this paper, a strategy for enhancing the
contrast of Computed Tomography (CT scan) and Magnetic Resonance Imaging (MRI) is
suggested. The strategy consists of two stages: pre-processing and then enhancement, either
using Gaussian blur or not. The pre-processing stage involves an image smoothing, convert the
image color space from RGB to YCrCb. The brightness compound (Y) is implied withe the
Supper Resolution Convolution Neural Network (SRCNN) in order to raise image resolution,
and then the images are returned to color space RGB using transformation equations. The
measures of Peak-Signal to Noise Ratio (PSNR), Structural Similarity Index (SSIM), Mean
Square Error (MSE) and Universal Quality index (UQI) were used to assess the quality of
enhanced images.
important to diagnose the patient case perfectly. In this paper, a strategy for enhancing the
contrast of Computed Tomography (CT scan) and Magnetic Resonance Imaging (MRI) is
suggested. The strategy consists of two stages: pre-processing and then enhancement, either
using Gaussian blur or not. The pre-processing stage involves an image smoothing, convert the
image color space from RGB to YCrCb. The brightness compound (Y) is implied withe the
Supper Resolution Convolution Neural Network (SRCNN) in order to raise image resolution,
and then the images are returned to color space RGB using transformation equations. The
measures of Peak-Signal to Noise Ratio (PSNR), Structural Similarity Index (SSIM), Mean
Square Error (MSE) and Universal Quality index (UQI) were used to assess the quality of
enhanced images.