HE stain images play a crucial role in the medical imaging process. Often these images are regarded as of golden standards by physicians for the quality and accuracy. These images are fuzzy by nature, and hence, traditional hard-based techniques are not able to deal with this. Thereby, a decrease in the accuracy of the analysis process may be experienced. Preprocessing of these images is utmost needed so that the fuzziness may be removed to a satisfactory level. A new approach for tackling this problem is introduced in this chapter. The proposed technique is soft computing-based advanced adaptive ameliorated CLAHE. The experimental results demonstrate the superiority of the proposed approach than the other traditional techniques.
TopFollowing are some important contribution in this field. These works are carefully studied and the methodology behind them are mentioned below:
In (Ensafi and Tizhoosh, 2005), the authors proved that the type-2 fuzzy logic system is able to perform better contrast enhancement than the type-1 fuzzy counterpart. They have introduced a new membership function for the type-2 fuzzy enhancement; this technique is actually an extended type-2 version of the type-1 adaptive fuzzy histogram hyperbolization.
A novel method FACE (Fuzzy Automatic Contrast Enhancement) is introduced in (Lin and Lin, 2016) which first performs fuzzy clustering to segment the input image where the pixels with similar colors in the CIELAB color space are classified into similar clusters with smaller characteristics. In each cluster, pixels are spread out from the center to enhance the contrast. The authors introduced a universal contrast enhancement variable and optimize its value to maximize entropy value.
Chaira introduced a medical image contrast enhancement technique based on type-2 fuzzy set (Chaira, 2013) (Chaira, 2014). Hamacher T co-norm is used as an aggregation operator to form a new membership function with proper upper and lower membership function. The enhanced image is the one with the new membership function.
Tizhoosh et al. (1995) used fuzzy histogram hyperbolization for contrast improvement. The local adaptive feature is used in two previous fuzzy enhancement techniques: minimization of fuzziness and fuzzy histogram hyperbolization and obtained results far better than their global version (Tizhoosh, Krell, and Michaelis, 1997). Tizhoosh (2005) in used the type-2 fuzzy set-based technique for thresholding images through a new measure of ultrafuzziness. The efficiency of the proposed technique is verified by thresholding laser cladding images.