Research Article

Block-Extraction and Haar Transform Based Linear Singularity Representation for Image Enhancement

Table 2

The BV and DV values in the original image and the enhanced images by the NSCT method, Alpha-root method, and our proposed method. All of these values are obtained when the LPC-SI is the best.

Image
InputAlpha-rootingNSCTOur proposed
BVDVBVDVBVDVBVDV

Lena0.556.600.3413.380.4016.850.3618.38

House0.627.050.1224.140.2620.770.1232.33

Barbara0.6612.530.3332.570.4831.480.3733.50

Peppers0.6810.430.3119.740.4713.040.4231.02

Boat0.669.470.3315.430.4724.400.3423.07

Couple0.639.950.3424.200.4525.650.4030.47

Hill0.588.420.3018.520.4118.780.3421.81

Man0.538.600.2819.670.4821.660.3429.22

Cam.0.6011.010.2628.360.3635.620.3543.79

Fingerprint0.5318.950.3961.970.5710.470.5250.54