A principal component fusion-based thresholded bin-stretching for CT image enhancement

Computed tomography (CT) images play an important role in the medical field to diagnose unhealthy organs, the structure of the inner body, and other diseases. The acquisition of CT images is a challenging task because a sufficient amount of electromagnetic wave is required to capture better contrast images, but for some unavoidable reason, CT machine captures degraded images like low contrast, dark images, and noisy images. So, the enhancement of the CT images is required to visualize the internal body structure. For enhancing the degraded CT image, a novel enhancement technique is produced on the basis of multilevel Thresholding (MLT)-based bin-stretching with power law transform (PLT). Initially, the distorted CT image is processed using an MLT-based bin-stretching approach to improve the contrast of the image. After that, a median filter is applied to the processed image using MLT-based bin-stretching to eliminate the impulse noise. Now, adaptive PLT is applied to the processed filtered image to improve the overall contrast of the image. Finally, contrast improved image and processed image by histogram equalization are fused using the principle component analysis method to control the over-improved portion of the image using PLT. The enhanced image is found in the form of a fused image. The qualitative and quantitative parameters are much better than the other recently introduced enhancement methods.