Gradient, Texture Driven Based Dynamic-Histogram Equalization For Medical Image Enhancement

Abstract

In many clinical diagnostic measurements, medical images play some significant role but often suffer from various types of noise and low-luminance, which causes some notable changes in overall system accuracy with misdiagnosis rate. To improve the visual appearance of object regions in medical images, image enhancement techniques are used as potential pre-processing techniques. Due to its simplicity and easiness of implementation, histogram equalization is widely preferred in many applications. But due to its mapping function based image transformation during enhancement process affect the biomedical patterns which are essential for diagnosis. To mitigate these issues in medical images, a new method based on gradient computations and Texture Driven based Dynamic histogram equalization (GTDDHE) is accomplished to increase the visual perception. The spatial texture pattern is also included to ensure the texture retention and associated control over its variations during histogram modifications. Experimental results on MRI, CT images, eyes images from medical image datasets and quantitative analysis by PSNR, structural similarity index measurement (SSIM), information entropy (IE) and validated that the proposed method offers improved quality with maximum retention of biomedical patterns across all types of medical images.