4.1.
Introduction
This chapter describes several standard thresholding techniques. Thresholding is one of the simplest and most widely used image segmentation techniques. The goal of thresholding is to segment an image into regions of interest and to remove all other regions deemed inessential. The simplest thresholding methods use a single threshold in order to isolate objects of interest. In many cases, however, no single threshold provides a good segmentation result over an entire image. In such cases variable and multilevel threshold techniques based on various statistical measures are used. The material presented in this chapter provides some insight into different strategies of threshold selection.
4.2.
Global Thresholding
The global thresholding technique is used to isolate objects of interest having values different from the background. Each pixel is classified as either belonging to an object of interest or to the background. This is accomplished by assigning to a pixel the value 1 if the source image value is within a given threshold range and 0 otherwise [1]. A sampling of algorithms used to determine threshold levels can be found in Sections 4.6, 4.7, and 4.8.
The global thresholding procedure is straightforward. Let ÿ be the source
image and be a given threshold range. The thresholded image
is given by
"!$#%'&µÿ()&* ,+-./1023!$4/
for all 556 .
Two special cases of this methodology are concerned with the isolation of uniformly high values or uniformly low values. In the first the thresholded image will
be given by
7
"!$#ÿ()8* ,+-./0923!:4/
while in the second case
;=<
>!$#ÿ(&? @+A-9./0923!B49/A
where denotes the suitable threshold value.
Image Algebra Formulation
Let ÿ'5; be the source image and C be a given threshold range. The
thresholded result imageDE11
can be computed using the characteristic function
138 CHAPTER 4. THRESHOLDING TECHNIQUES The characteristic functions RDSTVUW(XYZ\[
and
RDST]U^ X YZ\[
can be used to isolate object of high values and low values, respectively.
Comments and Observations
Global thresholding is effective in isolating objects of uniform value placed against a background of different values. Practical problems occur when the background is non- uniform or when the object and background assume a broad range of values. Note also thatRDST]UJ_`a
Xcb
YOZ\[TdYU W ` YeZ\[9[;fYOU ^ X YZ\[9[g
4.3.
Semithresholding
Semithresholding is a useful variation of global thresholding [1]. Pixels whose values lie within a given threshold range retain their original values. Pixels with values lying outside of the threshold range are set to 0. For a source image
Z'h5i;j
and a threshold range klmCno, the semithresholded image
Rhpiqj is given by RYr[T s ZtYr[vu$w l'x ZtYyr[ x*n z {|}~1 u$ ~ for all r5h5 .
Regions of high values can be isolated using
RYr[;SGT s Z(Yr[vu$wZ(Yer[ n z {|}~ u: ~
and regions of low values can be isolated using
RYr[;SGT s Z(Yr[vu$wZ(Yer[ x n z {|}~ u: ~ g
Image Algebra Formulation
The image algebra formulation for the semithresholded image
Rhi;j
over the range of values klmno is R5SGTZfCU _G`a
Xb YOZ\[g
The images semithresholded over the unbounded sets kGn(m9
[
and
Y
mCno are given by RY7r[SGT]ZfUW(XYyZP[
and
RYr[;SGTZfCU ^ X YZ\[
m
4. 3 Semithresholding 139
Alternate Image Algebra Formulation
The semithresholded image can also be derived by restricting the source image to those points whose values lie in the threshold range, and then extending the restriction to with value . The image algebra formulation for this method of semithresholding is
5G OJG97\
If appropriate, instead of constructing a result over , one can construct the subimage
of
containing only those pixels lying in the threshold range, that is,
Gcy
Comments and Observations
Figures 4.3.2and4.3.3below show the thresholded and semithresholded images of the original image of the Thunderbirds in Figure 4.3.1.
Figure 4.3.1. Image of Thunderbirds .
140 CHAPTER 4. THRESHOLDING TECHNIQUES
Figure 4.3.3. Semithresholded image of Thunderbirds «¬V®¯1°±²e³C´1µe®\¶.
4.4.
Multilevel Thresholding
Global thresholding and semithresholding techniques (Sections 4.2 and 4.3) seg- ment an image based on the assumption that the image contains only two types of regions. Certainly, an image may contain more than two types of regions. Multilevel thresholding is an extension of the two earlier thresholding techniques that allows for segmentation of pixels into multiple classes [1].
For example, if the image histogram contains three peaks, then it is possible to segment the image using two thresholds. These thresholds divide the value set into three nonoverlapping ranges, each of which can be associated with a unique value in the resulting image. Methods for determining such threshold values are discussed in Sections 4.6, 4.7, and 4.8.
Let®'·5¸;¹ be the source image, and letº ²E» ¯¯1¯» º¼ be threshold values satisfying º ²½ º¿¾ ½ ¯¯1¯ ½ º¼ . These values partition¸ intoÀÁ5 intervals which are associated with
values à ² » ¯1¯¯ » à ¼AÄ ² in the thresholded result image. A typical sequence of result values
might be  » ¼ÆÅ ² ¼ » ¯1¯¯ » ² ¼
»Ç . The thresholded image «]·p¸;¹ is defined by
«µ7ȶÊÉ
ËÌ Ã² Í$Î]ºÆ²Ï ®(µOȶ Ã1Ð Í$ÎpºÐ;Ï ®tµÈ¶Ñ?ºÐÅ ² à ¼¿Ä ² Í$ÎÒ®(µÔÓ\¶Ñ?º ¼(Õ