Image Enhancement via Subimage Histogram Equalization Based on Mean and Variance

Table 1

Properties of the proposed MVSIHE and other HE-based methods.

Methods	Implementation steps	Main focus
DSIHE	(1) HS using probability density function	(1) Contrast enhancement
	(2) HE	(2) Detail preservation
RMSHE	(1) HS using mean brightness ()	(1) Mean brightness preservation
	(2) HC using the middle gray level	(2) Detail preservation
	(3) HE
MMBEBHE	(1) HS using minimum mean brightness error	(1) Mean brightness reservation
	(2) HE
RSIHE	(1) HS using median brightness ()	(1) Mean brightness preservation
	(2) HE
ESIHE	(1) HC using the average number of intensity occurrence	(1) Mean brightness preservation
	(2) HS using exposure threshold	(2) Enhancement rate restriction
BHEMHB	(1) HS using median brightness ()	(1) Mean brightness preservation
	(2) Modification of histogram bins	(2) Detail preservation
	(3) HE
MVSIHE	(1) HS using mean and variance brightness ()	(1) Mean brightness preservation
	(2) Modification of histogram bins	(2) Detail preservation
	(3) HE	(3) Contrast enhancement
	(4) Fuse processed image with input image

indicates histogram segmentation, HC indicates histogram clipping, and HE indicates histogram equalization.