Fuzzy Enhancement Method for Color Medical Images Based on Color Space Conversion

Abstract

A new fuzzy enhancement method is put forward in the paper combining with Young-Helmholtz (Y-H) color space and fuzzy set theory. Color images with RGB tri-channels are transformed into Y-H color space by using Greaves transformation method. The colors image could be decomposed into chromaticity numbers matrix and intensity numbers matrix. The intensity numbers matrix is processed by using fuzzy enhancement arithmetic, while chromaticity numbers matrix keeps invariant. The primary chromaticity numbers matrix and enhanced intensity numbers matrix are processed by using Y-H inverse transformation. The method put forward in the paper have characteristics of efficiency, convenience and high speed. The method can achieve enhancement for color medical images without changing hue and saturation.

Color medical image enhancement based on adaptive equalization of intensity numbers matrix histogram

“…In order to prove the superiority of the method proposed in this paper, the enhancement results of the adaptive intensity numbers matrix histogram equalization method are compared with three common enhancement methods [17] , which are nonlinear transformation, multi-scale retinex algorithm (MSR) and guiding filter, as well as the intensity numbers matrix histogram equalization method mentioned in [11,17]. The original images are shown in Fig.…”

“…Reference [11] put forward the concept of intensity numbers matrix histogram of the color image for the first time, and the actual range of intensity numbers is confirmed as 0-√ 255 2 × 3, 0-442 in rounding. The intensity numbers matrix histogram of the color image is also a discrete function, which can be expressed as…”

“…Ding et al [10] proposed an image compression method by the singular value decomposition based on Y-H model. In 2013, the concept of "intensity numbers matrix histogram" and a kind of color medical image enhanced method based on color space transformation which are put forward in [11,12]. The color image can be enhanced without distortion by Y-H transformation and equalization of "intensity numbers matrix histogram", and finally be displayed in the RGB color space by inverse Y-H transformation.…”

“…2 Young-Helmholtz model [11,12] A pixel of a human retina image can be expressed by the three-channel information of color image as…”

“…The color image can be enhanced without distortion by Y-H transformation and equalization of "intensity numbers matrix histogram", and finally be displayed in the RGB color space by inverse Y-H transformation. In addition, the nonlinear extrapolation method [12] and fuzzy set theory [13] are combined with Y-H transformation for color image enhancement. In order to achieve better enhanced effect, a new method consists of Y-H transformation and the adaptive equalization of intensity numbers matrix histogram will be proposed and elaborated in this paper.…”