Medical Image Enhancement
Using Histogram Processing
Presentation-2Group No. 19
Prashant Sharma (131042)
Prashant Upadhaya (131043)
Ajeet Meena (121009)
JAYPEE UNIVERSITY OF ENGINEERING AND TECHNOLOGY,Guna (M.P.)
INTRODUCTION
• Medical Images are low contrast images
• To get better result for diagnosis we enhance medical images
• Contrast enhancement techniques such as HE, BBHE, DSIHE, etc. are used.
• BBHE and DSIHE are best suitable for medical images.
TEST IMAGE’S
BBHE(Brightness Preserving Bi-Histogram Equalization)
[Yeong, 1997][Sukhjinder et. al. 2012]
• Partitions Histogram in two sub-histograms and equalize them independently
• Proposed to minimize mean intensity change
• Ultimate goal is to preserve brightness and enhance contrast.
• Image parameters such as mean grayscale level used for partitioning
DSIHE(Dualistic Sub-image Histogram Equalization)
[Sukhjinder et. al. 2012]
• Image parameters such as median grayscale level used for partitioning.
• The input image is decomposed into two sub-images, being one dark and one bright.
• Then applies Histogram Equalization on two sub-images.
Mathematical Formulation For BBHE and DSIHE
• Input image X(i,j) with gray levels 0 to 255
• Image X(i, j) is segmented by a section with gray level of Xm
• Xm (mean in case of BBHE and median in case of DSIHE)
• The image is decomposed into two sub images XL and XU.
• X= XL U XU
XL={ X(I,j)|X(I,j) ≤ Xm, ∀ X(I,j) ∈ X } andXU={ X(I,j)|X(I,j) ≥ Xm, ∀ X(I,j) ∈ X }
• XL is composed by gray level of {I0, I1, ..., Im},XU is composed by gray level of {Im+1, Im+2, ..., IL-1}
• Respective probability density functions of the sub-images are:
pL(XK)=𝑛𝐿𝑘
𝑛𝐿Where k=1,2,…………,m
pU(XK)=𝑛𝑈𝑘
𝑛𝑈Where k=m+1,m+2,…………,L-1
• 𝑛𝐿𝑘 and 𝑛𝑈
𝑘 are the numbers of Xk
• 𝑛𝐿 = 𝑘=0𝑚 𝑛𝐿
𝑘 , 𝑛𝑈 = 𝑘=𝑚+1𝐿−1 𝑛𝑈
𝑘
• The respective cumulative density function for {X}L and {X}U are :
cL(Xk)= 𝑗=0𝑘 𝑝𝐿(𝑋𝑗)
and
cU(Xk)= 𝑗=𝑚+1𝐿−1 𝑝𝑈(𝑋𝑗)
• Transform function defined for exploiting the cumulative density functions:fL(Xk)=X0+(Xm-X0) cL(Xk)
and fU(Xk)=Xm+1+(XL-1-Xm+1) cU(Xk)
• Based on these transform functions, the decomposed sub-image are equalized independently.
• The composition of resulting equalized sub-images constitutes the output of BBHE or DSIHE
Y= fL(Xk) U fU(Xk)where
fL(Xk)={ fL(X(i,j)) | ∀ X(i,j) ∈ XL }and
fU(Xk)={ fU(X(i,j))| ∀ X(i,j) ∈ XU }
Algorithm forBBHE
(Brightness preserving Bi-Histogram Equalization)
Start
Original medical Image
Get histogram of original medical image
Calculate mean of the histogram
Divide the histogram on the basis of mean in two parts
Equalize each part independently using PDF and CDF
Stop
Combine both sub-images for final output
Algorithm forDSIHE
(Dualistic Sub-Image Histogram Equalization)
Start
Original medical Image
Get histogram of original medical image
Calculate median of the histogram
Divide the histogram on the basis of median in two parts
Equalize each part independently using PDF and CDF
Stop
Combine both sub-images for final output
Time Frame
• Implementation of algorithm in MATLAB.
• Result Gathering using medical images.
• Comparison of images on different parameters like:• AMBE(Absolute mean brightness error)• MD(Maximum Difference)• MSE(Mean Square Error)• NK(Normalized Cross Correlation)• PSNR(Peak Signal to Noise Ratio)
Conclusion
• Mathematical formulation of BBHE and DSIHE
• Flow chart of BBHE and DSIHE.
• Collection of medical images.
1. Rafael C. Gonzalez and Richard E. Woods, “Digital image processing. Pearson Education India” , 3rd edition, Prentice Hall, 2009.
2. Yeong-Taeg kim, “Contrast enhancement using Brightness Preserving Bi-Histogram Equalization”, IEEE Transactions on Consumer Electronics, 43(1), pp.1-8, Feb. 1997
3. Sukhjinder Singh, R.k. Bansal and Savina Bansal “Medical Image Enhancement Using Histogram Processing Techniques Followed by Median Filter” , International Journal of Image Processing and Application, 3(1), 2012, pp. 1-9
4. Mandeep Kaur and Ishdeep Singla “A Dualistic Sub-Image Histogram Equalization
Based Enhancement and Segmentation Techniques with NN for Medical Images “ , International Journal of Engineering and Science, Vol.05, Issue 01 (January 2015), PP: 15-19
Thank You