Medical Image Enhancement Algorithm Based on Histogram Equalization and Dyadic Wavelet Transform

Abstract

Medical image are often deteriorated by various noises during acquisition or transmission, this will leads to low contrast and poor quality of the medical image, which further seriously affects clinical diagnosis and interpretation, In order to solve the image blur and edge loss problem in the process of collecting and transmitting medical image, a novel medical image enhancement algorithm based on histogram equalization and dyadic wavelet transform is proposed in this paper, Firstly, histogram equalization is performed to enhance medical image contrast, Secondly, the medical image is decomposed into four sub bands (LL, HL, LH, HH) by dyadic wavelet transform four times, where LL is low frequency, LH, HL, HH are respective for horizontal, vertical and the diagonal line high frequency component, and then The single-threshold enhancement function is used after equalizing the low-frequency coefficients of the fourth layer again. the double threshold enhancement function is performed on the horizontal high frequency coefficients of each layer which further enhance the image quality and compansate for the information lost during histogram equalization, adaptive enhancement function is performed on high frequency coefficients in vertical and diagonal directions of each layer, Finally, The enhanced image was obtained through the inverse dyadic wavelet transform by using processed low frequency and high frequency coefficients, Many simulation experiments show that our proposed algorithm achieves more favorable performance in handing medical images, this method can not only enhance an image's details but can also preserve its edge to increase human visibility, which can raise the rate of conformity in clinical diagnoses.