Histogram Theory
Transcript of Histogram Theory
-
8/4/2019 Histogram Theory
1/26
By
Debashree GhoshAsst. Prof./BME
ALPHA COLLEGE OF ENGINEERINGThirumazhisai, Chennai- 124
-
8/4/2019 Histogram Theory
2/26
Introduction
Increases the global contrast of images
Especially when the usable data of the image
is represented by close contrast values.
This allows for areas of lower local contrast to
gain a higher contrast.
-
8/4/2019 Histogram Theory
3/26
Histogram
Consider a image {x} and let nk be the numberof occurrences of gray level rk.
The probability of an occurrence of a pixel oflevel kin the image is
Also called normalized histogram Note: Sum of all components of the normalized histogram is
equal to 1
-
8/4/2019 Histogram Theory
4/26
-
8/4/2019 Histogram Theory
5/26
-
8/4/2019 Histogram Theory
6/26
Histogram Equalization
For any r transformed pixel value
s=T(r) 0
-
8/4/2019 Histogram Theory
7/26
Contd
ps(s) and pr(r) are PDF of random variables s
and r, respectively.
s is determined by gray level PDF of original
image dummy variable of integration
Right side of the equation if cumulative
distribution function Since PDFs are +ve , it follows that this transformation is
singled valued and monotonically increasing
Similarly Integral of PDF is in the range of [0,1]
-
8/4/2019 Histogram Theory
8/26
Contd.
We can find the value of ps (s)
0
-
8/4/2019 Histogram Theory
9/26
-
8/4/2019 Histogram Theory
10/26
Contd
Discrete Formulation
-
8/4/2019 Histogram Theory
11/26
Original Image
-
8/4/2019 Histogram Theory
12/26
Value Count Value Count Value Count Value Count Value Count
52 1 64 2 72 1 85 2 113 1
55 3 65 3 73 2 87 1 122 1
58 2 66 2 75 1 88 1 126 1
59 3 67 1 76 1 90 1 144 1
60 1 68 5 77 1 94 1 154 1
61 4 69 3 78 1 104 2
62 1 70 4 79 2 106 1
63 2 71 2 83 1 109 1
-
8/4/2019 Histogram Theory
13/26
Value cdf Value cdf Value cdf Value cdf Value cdf
52 1 64 19 72 40 85 51 113 60
55 4 65 22 73 42 87 52 122 61
58 6 66 24 75 43 88 53 126 62
59 9 67 25 76 44 90 54 144 63
60 10 68 30 77 45 94 55 154 64
61 14 69 33 78 46 104 57
62 15 70 37 79 48 106 58
63 17 71 39 83 49 109 59
-
8/4/2019 Histogram Theory
14/26
The general histogram equalization formula is:
Where cdfmin is the minimum value of the
cumulative distribution function (in this case 1)
For example, the cdf of 78 is 46:
-
8/4/2019 Histogram Theory
15/26
Equalized values
-
8/4/2019 Histogram Theory
16/26
-
8/4/2019 Histogram Theory
17/26
Example
-
8/4/2019 Histogram Theory
18/26
Contd..
-
8/4/2019 Histogram Theory
19/26
Histogram Matching
The Enhancement on a uniform histogram is
not the best approach
Use specific shape of histogram
Histogram matching also called as hostogram
spacification.
-
8/4/2019 Histogram Theory
20/26
Contd
r and z are continuous gray levels
pr(r) and pz (z) denotes correspondingcontinuous probability density functions.
Step1:
Step2:
Step3:
-
8/4/2019 Histogram Theory
21/26
Discrete Gray Level
Gjhk
-
8/4/2019 Histogram Theory
22/26
-
8/4/2019 Histogram Theory
23/26
Original Image and its Histogram
-
8/4/2019 Histogram Theory
24/26
Histogram equalization
-
8/4/2019 Histogram Theory
25/26
-
8/4/2019 Histogram Theory
26/26