Design and Implementation - Segmentation of Hand Bone for Bone Age Assessment - page 57

1

m=n=2
m=n=4
m=n=7
m=n=11
m=n=25

0.9

0.8

0.7

0.6

0.5

0.4

0.3

0.2

0.1

0

0 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9 1

Relative Brightness Difference (RBD)

Fig. 3.4 Illustration of the bound property of NBPS function range when the BPS curves in BPS
are normalized

One important feature of the proposed BPS is that it has revolutionized the tra-
ditional perception for brightness preservation which associates with minimizing
the brightness difference to better brightness preserving ability, which is incorrect
in the context of contrast enhancement on the ground that small brightness differ-
ence might indicate negligible contrast enhancement and this in turn will obscure
the pertinent information. Therefore, the proposed new concept is to optimize the
brightness different for better brightness preserving ability along with two impor-
tant properties: contrast enhancement and detail preservation. This regularization
function provides a new insight and technique in extending the flexibility of his-
togram equalization in brightness preservation so that it can be applied in various
types of images. The next section will discuss about the proposed metric used to
measure the contrast enhancement. This metric will finally be adopted in the final
regularization objective function.

(B) The Optimum Contrast Score (OCS) Function

The Optimum Contrast Score (OCS) is designed as a function that output a numer-
ical score which can be used to gauge the contrast enhancement corresponds to the
contrast change between the input image and the histogram equalized image. The
function is designed so that the contrast change is the function domain, p and q are
the parameters, and the bound values between 0 and 1 are the range. The detail of
the function is discussed as follows: