SlideShare a Scribd company logo
1 of 22
Nisar Ahmed
                    Sheikh Muhammad Arshad


HITEC University Taxila                Supervised By:
Department of Electrical Engineering   Dr. Jameel Ahmed
• To develop a complete solution for digital radiographic
  image enhancement for improved visualization and better
  diagnosis.
• The paper encourages radiologists to become familiar with
  these techniques, to evaluate them, and to incorporate
  them into specific display protocols.
• The aim of image enhancement is to improve the
  interpretability or perception of information in image for
  human viewers, it case of radiographic images it help the
  radiologist in better diagnosis.
• The basic working of the application is:-


        Input Image    Processing   Better Image




                      Enhancement
                       Technique
• Contrast Enhancement
  o Linear Contrast Stretching
  o Histogram Equalization
  o Contrast Limited Adaptive Histogram Equalization
  o Brightness Preserving Histogram Equalization
• Removing Noise
  o Median filter
  o Wiener Filter
  o Sigma Filter
• Image Sharpening
  o High Frequency Boosting
  o Edge Detection and Enhancement
• Image Contrast is the difference in appearance of two or
  more parts of an image seen simultaneously. An image
  must have good brightness contrast for proper vision. In a
  low contrast image we can’t distinguish clearly between
  different objects. Increasing the contrast makes the light
  areas become lighter and dark areas become darker. We
  use different techniques of histogram modification to
  improve the visual contrast of the image.
• Histogram is the graph of intensities with number of pixel
  lying at those intensity values.
• In linear contrast stretching the histogram of image matrix
  is linearly stretched over the entire range. This technique
  maps the intensities to new values such that the data is
  stretched to the whole spectrum. This technique produces
  useful results when the histogram of original image is
  concentrated in a narrow range of spectrum.
• This technique can’t produce better results in many cases.
Histogram equalization generates a gray map which
  redistribute all pixel values such as to produce uniform
  histogram. Histogram equalization spread out the most
  frequent intensity values to allow the areas of lower
  contrast to gain a higher contrast.
The principle disadvantages with histogram equalization are:-
   o The    histogram equalization method may result in over
     enhancement and saturation artifacts.
   o Histogram equalization can be found on the fact that it may
     significantly alter the brightness of an image.
• CLAHE computes multiple histograms, each corresponding
  to a distinct section to increase local contrast, rather than
  overall contrast. The image is divided into tiles and it
  operates on tiles rather than the entire image. Contrast of
  each tile is enhanced and then all the tiles are combined
  using bilinear interpolation to eliminate the artificially
  induced boundaries. The contrast especially in
  homogeneous areas is limited to avoid noise amplification.
• The principle disadvantage of this technique is it produces
  limited contrast enhancement due to local enhancement.
• BPHE is used to overcome the problem with simple
  histogram equalization. It computes the mean of the image
  and decomposes the image into two sub images based on
  the mean of the image. One of them is set of samples less
  than or equal to the mean whereas the other is the set of
  samples greater than the mean. Then two sub images are
  equalized independently based on their respective
  histograms. Thus the resulting equalized sub images are
  bounded by each other around the mean, which has an
  effect of preserving mean brightness.
• The only problem with this technique is, is take more
  computational time them histogram equalization.
The above images shows, in majority of cases adaptive histogram equalization
produces best result. Brightness preserving histogram equalization can be used if
needed.
Table 1: Contrast Enhancement
                            Advantages                             Disadvantages
Linear Contrast             Can produce good result by linear      Can’t produce much attractive results
                            stretching.                            in many cases.
HE                          This technique is best for visual      This technique may result in
                            perception especially when image       brightness shift because it does not
                            have close contrast data.              take mean brightness.
CLAHE                       This technique produces good results   This technique produce limited
                            when histogram equalization can’t      contrast enhancement due to local
                            produce attractive results.            enhancement.
BPHE                        Produce best results when HE           Take more time duce to separation
                            produces brightness shift.             into two images and appending after
                                                                   their enhancement.


       The best among the above discussed technique is BPHE (brightness
       preserving histogram equalization) it produces good result while
       preserving the image mean brightness.
• Noise is the result of errors in the image acquisition
  process that result in pixel values that do not reflect the
  true intensities of the real organ.
• Radiographic images are prone to a variety of types of
  noise due to several reasons such as:-
   o If the image is scanned from an X-Ray film or CT image, the film
     grain is a source of noise. It can be a result of a damaged film or due
     to the scanner itself.
   o If the image is captured directly from digital X-Ray scanner or a CT
     scanner it can be due to mechanism of gathering the data.
• Linear Filtering is easiest method to remove certain type of
  noise. Averaging or mean filter can be used to accomplish this
  job. In averaging filter each pixel gets set to the average of its
  neighboring pixels. The problem with averaging filter is that
  edges of image get blurred.
• To overcome this problem we use selective mean filter such as
  sigma filter. It preserves edges better and is less sensitive to
  edges.
• The filter smoothes an image by taking an average over the
  neighboring pixels, but only includes those pixels that have a
  value not deviating from the current pixel by more than a given
  range.
• Edges having a value very different from the surrounding are not
  included in the average and, thus, completely eliminated from
  blurring.
• Median filter works in a similar way as averaging filter, the
  only difference is the output value of a pixel is determined
  by the median of the neighboring pixel rather than mean.
• The principle advantage of median filtering over averaging
  is that it is much less sensitive to extreme values. Therefore
  median filtering is better to remove noise while reducing
  the blurring of edges.
• Wiener filter often produce much better results than linear
  filter. It uses a pixel wise adaptive Wiener method based on
  statistics estimated from a local neighborhood of each
  pixel..
• This filter produces best output when noise is AWGN.
• The problem of this method over the previous one is it
  requires more computational time.
Table 2: Noise Reduction
                              Advantages                              Disadvantages
Median Filtering              Easy to implement.                      Image edges get blurred.
Sigma Filter                  Easy to implement by adding             Can’t be used for salt & pepper noise.
                              threshold in averaging filter.
Wiener Filter                 Produce best output when the noise is   Require high computational time.
                              additive white Gaussian noise.


      Sigma filter produce better result for CT and MRI images. It preserves the
      edges while removing the noise. Threshold can be adjusted to acquire the
      desired performance. However median filter also reduce noise effectively.
      Its results become good if we apply image sharpening filter after median
      filtering.
• In radiology, we want the recorded image to be a faithful
  representation of the organs that we want to see but every
  image is more or less blurry because image information
  spills over to neighboring pixels.
• When the image does not shows sharp details of its
  features it is called blurred image. Thus, image sharpening
  is fundamental in making images clear and useful.
• Image sharpening using Laplacian of Gaussian filter has
  been used for CT or MRI images and high frequency
  component boosting has been used in X-Ray and
  mammographic images.
• Contrast enhancement using histogram processing is an
  effective method, four techniques of histogram processing
  has been applied on a large number of digital radiographic
  images. BPHE has shown best results in majority of cases.
  Three techniques have been used for noise reduction
  among them sigma filter has shown better results.
  However median filter followed by image sharpening also
  show good results.
• Various aspects of image enhancement are catered for in
  the implementation and subsequent exercise of results,
  nevertheless, we understand that it is so demanding and
  absorbing area for research that the work could
  substantially be carried forward in following directions as
  a future work:
   o Improvement in selective noise reduction techniques.
   o Level correction of image by combining it with image segmentation.
Digital radiographic image enhancement for improved visualization

More Related Content

What's hot

Digital image processing techniques
Digital image processing techniquesDigital image processing techniques
Digital image processing techniquesShab Bi
 
Image enhancement techniques
Image enhancement techniquesImage enhancement techniques
Image enhancement techniquesBulbul Agrawal
 
Digital Image Processing_ ch2 enhancement spatial-domain
Digital Image Processing_ ch2 enhancement spatial-domainDigital Image Processing_ ch2 enhancement spatial-domain
Digital Image Processing_ ch2 enhancement spatial-domainMalik obeisat
 
Image restoration
Image restorationImage restoration
Image restorationAzad Singh
 
Gradient-Based Low-Light Image Enhancement
Gradient-Based Low-Light Image EnhancementGradient-Based Low-Light Image Enhancement
Gradient-Based Low-Light Image EnhancementMasayuki Tanaka
 
Image enhancement
Image enhancementImage enhancement
Image enhancementvsaranya169
 
Adaptive unsharp masking
Adaptive unsharp maskingAdaptive unsharp masking
Adaptive unsharp maskingRavi Teja
 
Digital image processing - Image Enhancement (MATERIAL)
Digital image processing  - Image Enhancement (MATERIAL)Digital image processing  - Image Enhancement (MATERIAL)
Digital image processing - Image Enhancement (MATERIAL)Mathankumar S
 
Frequency Domain Image Enhancement Techniques
Frequency Domain Image Enhancement TechniquesFrequency Domain Image Enhancement Techniques
Frequency Domain Image Enhancement TechniquesDiwaker Pant
 
image denoising technique using disctere wavelet transform
image denoising technique using disctere wavelet transformimage denoising technique using disctere wavelet transform
image denoising technique using disctere wavelet transformalishapb
 
Image enhancement techniques a review
Image enhancement techniques   a reviewImage enhancement techniques   a review
Image enhancement techniques a revieweSAT Journals
 
Modified Contrast Enhancement using Laplacian and Gaussians Fusion Technique
Modified Contrast Enhancement using Laplacian and Gaussians Fusion TechniqueModified Contrast Enhancement using Laplacian and Gaussians Fusion Technique
Modified Contrast Enhancement using Laplacian and Gaussians Fusion Techniqueiosrjce
 
Image Enhancement in Spatial Domain
Image Enhancement in Spatial DomainImage Enhancement in Spatial Domain
Image Enhancement in Spatial DomainDEEPASHRI HK
 
Image Thumbnail with Blur and Noise Information to Improve Browsing Experience
Image Thumbnail with Blur and Noise Information to Improve Browsing ExperienceImage Thumbnail with Blur and Noise Information to Improve Browsing Experience
Image Thumbnail with Blur and Noise Information to Improve Browsing ExperienceWaqas Tariq
 
Image pre processing-restoration
Image pre processing-restorationImage pre processing-restoration
Image pre processing-restorationAshish Kumar
 

What's hot (18)

Digital image processing techniques
Digital image processing techniquesDigital image processing techniques
Digital image processing techniques
 
2.image enhancement
2.image enhancement2.image enhancement
2.image enhancement
 
Image enhancement techniques
Image enhancement techniquesImage enhancement techniques
Image enhancement techniques
 
Digital Image Processing_ ch2 enhancement spatial-domain
Digital Image Processing_ ch2 enhancement spatial-domainDigital Image Processing_ ch2 enhancement spatial-domain
Digital Image Processing_ ch2 enhancement spatial-domain
 
Image restoration
Image restorationImage restoration
Image restoration
 
Gradient-Based Low-Light Image Enhancement
Gradient-Based Low-Light Image EnhancementGradient-Based Low-Light Image Enhancement
Gradient-Based Low-Light Image Enhancement
 
Image enhancement
Image enhancementImage enhancement
Image enhancement
 
Blurred image recognization system
Blurred image recognization systemBlurred image recognization system
Blurred image recognization system
 
Chap3
 Chap3 Chap3
Chap3
 
Adaptive unsharp masking
Adaptive unsharp maskingAdaptive unsharp masking
Adaptive unsharp masking
 
Digital image processing - Image Enhancement (MATERIAL)
Digital image processing  - Image Enhancement (MATERIAL)Digital image processing  - Image Enhancement (MATERIAL)
Digital image processing - Image Enhancement (MATERIAL)
 
Frequency Domain Image Enhancement Techniques
Frequency Domain Image Enhancement TechniquesFrequency Domain Image Enhancement Techniques
Frequency Domain Image Enhancement Techniques
 
image denoising technique using disctere wavelet transform
image denoising technique using disctere wavelet transformimage denoising technique using disctere wavelet transform
image denoising technique using disctere wavelet transform
 
Image enhancement techniques a review
Image enhancement techniques   a reviewImage enhancement techniques   a review
Image enhancement techniques a review
 
Modified Contrast Enhancement using Laplacian and Gaussians Fusion Technique
Modified Contrast Enhancement using Laplacian and Gaussians Fusion TechniqueModified Contrast Enhancement using Laplacian and Gaussians Fusion Technique
Modified Contrast Enhancement using Laplacian and Gaussians Fusion Technique
 
Image Enhancement in Spatial Domain
Image Enhancement in Spatial DomainImage Enhancement in Spatial Domain
Image Enhancement in Spatial Domain
 
Image Thumbnail with Blur and Noise Information to Improve Browsing Experience
Image Thumbnail with Blur and Noise Information to Improve Browsing ExperienceImage Thumbnail with Blur and Noise Information to Improve Browsing Experience
Image Thumbnail with Blur and Noise Information to Improve Browsing Experience
 
Image pre processing-restoration
Image pre processing-restorationImage pre processing-restoration
Image pre processing-restoration
 

Viewers also liked

Spatial filtering using image processing
Spatial filtering using image processingSpatial filtering using image processing
Spatial filtering using image processingAnuj Arora
 
Histogram equalization
Histogram equalizationHistogram equalization
Histogram equalization11mr11mahesh
 
Jadwal dan daftar peserta yang wajib ujian tkb cpns ta 2014
Jadwal dan daftar peserta yang wajib ujian tkb cpns ta 2014Jadwal dan daftar peserta yang wajib ujian tkb cpns ta 2014
Jadwal dan daftar peserta yang wajib ujian tkb cpns ta 2014Hendra Sirait
 
FINAL_9_15_14_EDImplementa
FINAL_9_15_14_EDImplementaFINAL_9_15_14_EDImplementa
FINAL_9_15_14_EDImplementagilmore6
 
Clarion Corporate Presentation
Clarion Corporate PresentationClarion Corporate Presentation
Clarion Corporate PresentationClarion Marketing
 
Sourajit Aiyer - South Asian Federation of Exchanges, Pakistan - Triggers Tha...
Sourajit Aiyer - South Asian Federation of Exchanges, Pakistan - Triggers Tha...Sourajit Aiyer - South Asian Federation of Exchanges, Pakistan - Triggers Tha...
Sourajit Aiyer - South Asian Federation of Exchanges, Pakistan - Triggers Tha...South Asia Fast Track
 
Moscoso-Espinosa-Chango
Moscoso-Espinosa-ChangoMoscoso-Espinosa-Chango
Moscoso-Espinosa-ChangoChivo Espinosa
 
Kaliteli sofralik uzum yetistiriciligi
Kaliteli sofralik uzum yetistiriciligi Kaliteli sofralik uzum yetistiriciligi
Kaliteli sofralik uzum yetistiriciligi adex25
 
Social Media and Financial Communications
Social Media and Financial CommunicationsSocial Media and Financial Communications
Social Media and Financial CommunicationsMWWPR
 
Dazed and confused toc analysis
Dazed and confused toc analysisDazed and confused toc analysis
Dazed and confused toc analysisjessiekeegan
 
2014 REVISTA MEXICANA DE CIENCIAS GEOLÓGICAS - Study of Cedral Horses and the...
2014 REVISTA MEXICANA DE CIENCIAS GEOLÓGICAS - Study of Cedral Horses and the...2014 REVISTA MEXICANA DE CIENCIAS GEOLÓGICAS - Study of Cedral Horses and the...
2014 REVISTA MEXICANA DE CIENCIAS GEOLÓGICAS - Study of Cedral Horses and the...Ruben LLumihucci
 
Sourajit Aiyer - Finance Monthly Magazine, UK - Catching Up On The India Stor...
Sourajit Aiyer - Finance Monthly Magazine, UK - Catching Up On The India Stor...Sourajit Aiyer - Finance Monthly Magazine, UK - Catching Up On The India Stor...
Sourajit Aiyer - Finance Monthly Magazine, UK - Catching Up On The India Stor...South Asia Fast Track
 

Viewers also liked (20)

Spatial filtering using image processing
Spatial filtering using image processingSpatial filtering using image processing
Spatial filtering using image processing
 
Histogram equalization
Histogram equalizationHistogram equalization
Histogram equalization
 
Jadwal dan daftar peserta yang wajib ujian tkb cpns ta 2014
Jadwal dan daftar peserta yang wajib ujian tkb cpns ta 2014Jadwal dan daftar peserta yang wajib ujian tkb cpns ta 2014
Jadwal dan daftar peserta yang wajib ujian tkb cpns ta 2014
 
FINAL_9_15_14_EDImplementa
FINAL_9_15_14_EDImplementaFINAL_9_15_14_EDImplementa
FINAL_9_15_14_EDImplementa
 
Clarion Corporate Presentation
Clarion Corporate PresentationClarion Corporate Presentation
Clarion Corporate Presentation
 
PIA AA AD16.
PIA AA AD16.PIA AA AD16.
PIA AA AD16.
 
Phrasal verbs
Phrasal   verbsPhrasal   verbs
Phrasal verbs
 
Pat7.6 253
Pat7.6 253Pat7.6 253
Pat7.6 253
 
Sourajit Aiyer - South Asian Federation of Exchanges, Pakistan - Triggers Tha...
Sourajit Aiyer - South Asian Federation of Exchanges, Pakistan - Triggers Tha...Sourajit Aiyer - South Asian Federation of Exchanges, Pakistan - Triggers Tha...
Sourajit Aiyer - South Asian Federation of Exchanges, Pakistan - Triggers Tha...
 
Redes complejas
Redes complejasRedes complejas
Redes complejas
 
Jenkins on-mac
Jenkins on-macJenkins on-mac
Jenkins on-mac
 
Moscoso-Espinosa-Chango
Moscoso-Espinosa-ChangoMoscoso-Espinosa-Chango
Moscoso-Espinosa-Chango
 
Tik
TikTik
Tik
 
Kaliteli sofralik uzum yetistiriciligi
Kaliteli sofralik uzum yetistiriciligi Kaliteli sofralik uzum yetistiriciligi
Kaliteli sofralik uzum yetistiriciligi
 
Tugas 4
Tugas 4Tugas 4
Tugas 4
 
Social Media and Financial Communications
Social Media and Financial CommunicationsSocial Media and Financial Communications
Social Media and Financial Communications
 
Dazed and confused toc analysis
Dazed and confused toc analysisDazed and confused toc analysis
Dazed and confused toc analysis
 
RAPPORTO EXPORT ABRUZZO
RAPPORTO EXPORT ABRUZZORAPPORTO EXPORT ABRUZZO
RAPPORTO EXPORT ABRUZZO
 
2014 REVISTA MEXICANA DE CIENCIAS GEOLÓGICAS - Study of Cedral Horses and the...
2014 REVISTA MEXICANA DE CIENCIAS GEOLÓGICAS - Study of Cedral Horses and the...2014 REVISTA MEXICANA DE CIENCIAS GEOLÓGICAS - Study of Cedral Horses and the...
2014 REVISTA MEXICANA DE CIENCIAS GEOLÓGICAS - Study of Cedral Horses and the...
 
Sourajit Aiyer - Finance Monthly Magazine, UK - Catching Up On The India Stor...
Sourajit Aiyer - Finance Monthly Magazine, UK - Catching Up On The India Stor...Sourajit Aiyer - Finance Monthly Magazine, UK - Catching Up On The India Stor...
Sourajit Aiyer - Finance Monthly Magazine, UK - Catching Up On The India Stor...
 

Similar to Digital radiographic image enhancement for improved visualization

ModuleII092.pdf
ModuleII092.pdfModuleII092.pdf
ModuleII092.pdfSamrajECE
 
Histogram Based Contrast Enhn
Histogram Based Contrast EnhnHistogram Based Contrast Enhn
Histogram Based Contrast EnhnTulsi Chandan
 
An image enhancement method based on gabor filtering in wavelet domain and ad...
An image enhancement method based on gabor filtering in wavelet domain and ad...An image enhancement method based on gabor filtering in wavelet domain and ad...
An image enhancement method based on gabor filtering in wavelet domain and ad...nooriasukmaningtyas
 
X-Ray Image Enhancement using CLAHE Method
X-Ray Image Enhancement using CLAHE MethodX-Ray Image Enhancement using CLAHE Method
X-Ray Image Enhancement using CLAHE MethodIRJET Journal
 
A review on image enhancement techniques
A review on image enhancement techniquesA review on image enhancement techniques
A review on image enhancement techniquesIJEACS
 
CONTRAST ENHANCEMENT AND BRIGHTNESS PRESERVATION USING MULTIDECOMPOSITION HIS...
CONTRAST ENHANCEMENT AND BRIGHTNESS PRESERVATION USING MULTIDECOMPOSITION HIS...CONTRAST ENHANCEMENT AND BRIGHTNESS PRESERVATION USING MULTIDECOMPOSITION HIS...
CONTRAST ENHANCEMENT AND BRIGHTNESS PRESERVATION USING MULTIDECOMPOSITION HIS...sipij
 
project presentation-90-MCS-200003.pptx
project presentation-90-MCS-200003.pptxproject presentation-90-MCS-200003.pptx
project presentation-90-MCS-200003.pptxNiladriBhattacharjee10
 
Enhancement of Medical Images using Histogram Based Hybrid Technique
Enhancement of Medical Images using Histogram Based Hybrid TechniqueEnhancement of Medical Images using Histogram Based Hybrid Technique
Enhancement of Medical Images using Histogram Based Hybrid TechniqueINFOGAIN PUBLICATION
 
A DISCUSSION ON IMAGE ENHANCEMENT USING HISTOGRAM EQUALIZATION BY VARIOUS MET...
A DISCUSSION ON IMAGE ENHANCEMENT USING HISTOGRAM EQUALIZATION BY VARIOUS MET...A DISCUSSION ON IMAGE ENHANCEMENT USING HISTOGRAM EQUALIZATION BY VARIOUS MET...
A DISCUSSION ON IMAGE ENHANCEMENT USING HISTOGRAM EQUALIZATION BY VARIOUS MET...pharmaindexing
 
A Comparative Study on Image Contrast Enhancement Techniques
A Comparative Study on Image Contrast Enhancement TechniquesA Comparative Study on Image Contrast Enhancement Techniques
A Comparative Study on Image Contrast Enhancement TechniquesIRJET Journal
 
ANALYSIS OF IMAGE ENHANCEMENT TECHNIQUES USING MATLAB
ANALYSIS OF IMAGE ENHANCEMENT TECHNIQUES USING MATLABANALYSIS OF IMAGE ENHANCEMENT TECHNIQUES USING MATLAB
ANALYSIS OF IMAGE ENHANCEMENT TECHNIQUES USING MATLABJim Jimenez
 
Paper on image processing
Paper on image processingPaper on image processing
Paper on image processingSaloni Bhatia
 
research paper Ijetae 0812 23
research paper Ijetae 0812 23research paper Ijetae 0812 23
research paper Ijetae 0812 23Punit Karnani
 
Image Enhancement using Guided Filter for under Exposed Images
Image Enhancement using Guided Filter for under Exposed ImagesImage Enhancement using Guided Filter for under Exposed Images
Image Enhancement using Guided Filter for under Exposed ImagesDr. Amarjeet Singh
 
A Novel Framework For Preprocessing Of Breast Ultra Sound Images By Combining...
A Novel Framework For Preprocessing Of Breast Ultra Sound Images By Combining...A Novel Framework For Preprocessing Of Breast Ultra Sound Images By Combining...
A Novel Framework For Preprocessing Of Breast Ultra Sound Images By Combining...IRJET Journal
 

Similar to Digital radiographic image enhancement for improved visualization (20)

ModuleII092.pdf
ModuleII092.pdfModuleII092.pdf
ModuleII092.pdf
 
Histogram Based Contrast Enhn
Histogram Based Contrast EnhnHistogram Based Contrast Enhn
Histogram Based Contrast Enhn
 
An image enhancement method based on gabor filtering in wavelet domain and ad...
An image enhancement method based on gabor filtering in wavelet domain and ad...An image enhancement method based on gabor filtering in wavelet domain and ad...
An image enhancement method based on gabor filtering in wavelet domain and ad...
 
X-Ray Image Enhancement using CLAHE Method
X-Ray Image Enhancement using CLAHE MethodX-Ray Image Enhancement using CLAHE Method
X-Ray Image Enhancement using CLAHE Method
 
A review on image enhancement techniques
A review on image enhancement techniquesA review on image enhancement techniques
A review on image enhancement techniques
 
CONTRAST ENHANCEMENT AND BRIGHTNESS PRESERVATION USING MULTIDECOMPOSITION HIS...
CONTRAST ENHANCEMENT AND BRIGHTNESS PRESERVATION USING MULTIDECOMPOSITION HIS...CONTRAST ENHANCEMENT AND BRIGHTNESS PRESERVATION USING MULTIDECOMPOSITION HIS...
CONTRAST ENHANCEMENT AND BRIGHTNESS PRESERVATION USING MULTIDECOMPOSITION HIS...
 
project presentation-90-MCS-200003.pptx
project presentation-90-MCS-200003.pptxproject presentation-90-MCS-200003.pptx
project presentation-90-MCS-200003.pptx
 
NOISE FILTERS IN IMAGE PROCESSING
NOISE FILTERS IN IMAGE PROCESSINGNOISE FILTERS IN IMAGE PROCESSING
NOISE FILTERS IN IMAGE PROCESSING
 
Enhancement of Medical Images using Histogram Based Hybrid Technique
Enhancement of Medical Images using Histogram Based Hybrid TechniqueEnhancement of Medical Images using Histogram Based Hybrid Technique
Enhancement of Medical Images using Histogram Based Hybrid Technique
 
A DISCUSSION ON IMAGE ENHANCEMENT USING HISTOGRAM EQUALIZATION BY VARIOUS MET...
A DISCUSSION ON IMAGE ENHANCEMENT USING HISTOGRAM EQUALIZATION BY VARIOUS MET...A DISCUSSION ON IMAGE ENHANCEMENT USING HISTOGRAM EQUALIZATION BY VARIOUS MET...
A DISCUSSION ON IMAGE ENHANCEMENT USING HISTOGRAM EQUALIZATION BY VARIOUS MET...
 
Image Filtering
Image FilteringImage Filtering
Image Filtering
 
A Comparative Study on Image Contrast Enhancement Techniques
A Comparative Study on Image Contrast Enhancement TechniquesA Comparative Study on Image Contrast Enhancement Techniques
A Comparative Study on Image Contrast Enhancement Techniques
 
ANALYSIS OF IMAGE ENHANCEMENT TECHNIQUES USING MATLAB
ANALYSIS OF IMAGE ENHANCEMENT TECHNIQUES USING MATLABANALYSIS OF IMAGE ENHANCEMENT TECHNIQUES USING MATLAB
ANALYSIS OF IMAGE ENHANCEMENT TECHNIQUES USING MATLAB
 
Paper on image processing
Paper on image processingPaper on image processing
Paper on image processing
 
Q01761119124
Q01761119124Q01761119124
Q01761119124
 
research paper Ijetae 0812 23
research paper Ijetae 0812 23research paper Ijetae 0812 23
research paper Ijetae 0812 23
 
Image Enhancement using Guided Filter for under Exposed Images
Image Enhancement using Guided Filter for under Exposed ImagesImage Enhancement using Guided Filter for under Exposed Images
Image Enhancement using Guided Filter for under Exposed Images
 
Ijetr021211
Ijetr021211Ijetr021211
Ijetr021211
 
Ijetr021211
Ijetr021211Ijetr021211
Ijetr021211
 
A Novel Framework For Preprocessing Of Breast Ultra Sound Images By Combining...
A Novel Framework For Preprocessing Of Breast Ultra Sound Images By Combining...A Novel Framework For Preprocessing Of Breast Ultra Sound Images By Combining...
A Novel Framework For Preprocessing Of Breast Ultra Sound Images By Combining...
 

More from Nisar Ahmed Rana

More from Nisar Ahmed Rana (8)

Digital Image Communication and Enhancement
Digital Image Communication and EnhancementDigital Image Communication and Enhancement
Digital Image Communication and Enhancement
 
Project Proposal
Project ProposalProject Proposal
Project Proposal
 
Project proposal
Project proposalProject proposal
Project proposal
 
Say No to Child Labour
Say No to Child LabourSay No to Child Labour
Say No to Child Labour
 
Project Launch
Project LaunchProject Launch
Project Launch
 
Gandhara Civilization
Gandhara CivilizationGandhara Civilization
Gandhara Civilization
 
SIFT vs other Feature Descriptor
SIFT vs other Feature DescriptorSIFT vs other Feature Descriptor
SIFT vs other Feature Descriptor
 
Project launch
Project launchProject launch
Project launch
 

Digital radiographic image enhancement for improved visualization

  • 1. Nisar Ahmed Sheikh Muhammad Arshad HITEC University Taxila Supervised By: Department of Electrical Engineering Dr. Jameel Ahmed
  • 2. • To develop a complete solution for digital radiographic image enhancement for improved visualization and better diagnosis. • The paper encourages radiologists to become familiar with these techniques, to evaluate them, and to incorporate them into specific display protocols.
  • 3. • The aim of image enhancement is to improve the interpretability or perception of information in image for human viewers, it case of radiographic images it help the radiologist in better diagnosis. • The basic working of the application is:- Input Image Processing Better Image Enhancement Technique
  • 4. • Contrast Enhancement o Linear Contrast Stretching o Histogram Equalization o Contrast Limited Adaptive Histogram Equalization o Brightness Preserving Histogram Equalization • Removing Noise o Median filter o Wiener Filter o Sigma Filter • Image Sharpening o High Frequency Boosting o Edge Detection and Enhancement
  • 5. • Image Contrast is the difference in appearance of two or more parts of an image seen simultaneously. An image must have good brightness contrast for proper vision. In a low contrast image we can’t distinguish clearly between different objects. Increasing the contrast makes the light areas become lighter and dark areas become darker. We use different techniques of histogram modification to improve the visual contrast of the image. • Histogram is the graph of intensities with number of pixel lying at those intensity values.
  • 6. • In linear contrast stretching the histogram of image matrix is linearly stretched over the entire range. This technique maps the intensities to new values such that the data is stretched to the whole spectrum. This technique produces useful results when the histogram of original image is concentrated in a narrow range of spectrum. • This technique can’t produce better results in many cases.
  • 7. Histogram equalization generates a gray map which redistribute all pixel values such as to produce uniform histogram. Histogram equalization spread out the most frequent intensity values to allow the areas of lower contrast to gain a higher contrast. The principle disadvantages with histogram equalization are:- o The histogram equalization method may result in over enhancement and saturation artifacts. o Histogram equalization can be found on the fact that it may significantly alter the brightness of an image.
  • 8. • CLAHE computes multiple histograms, each corresponding to a distinct section to increase local contrast, rather than overall contrast. The image is divided into tiles and it operates on tiles rather than the entire image. Contrast of each tile is enhanced and then all the tiles are combined using bilinear interpolation to eliminate the artificially induced boundaries. The contrast especially in homogeneous areas is limited to avoid noise amplification. • The principle disadvantage of this technique is it produces limited contrast enhancement due to local enhancement.
  • 9. • BPHE is used to overcome the problem with simple histogram equalization. It computes the mean of the image and decomposes the image into two sub images based on the mean of the image. One of them is set of samples less than or equal to the mean whereas the other is the set of samples greater than the mean. Then two sub images are equalized independently based on their respective histograms. Thus the resulting equalized sub images are bounded by each other around the mean, which has an effect of preserving mean brightness. • The only problem with this technique is, is take more computational time them histogram equalization.
  • 10. The above images shows, in majority of cases adaptive histogram equalization produces best result. Brightness preserving histogram equalization can be used if needed.
  • 11. Table 1: Contrast Enhancement Advantages Disadvantages Linear Contrast Can produce good result by linear Can’t produce much attractive results stretching. in many cases. HE This technique is best for visual This technique may result in perception especially when image brightness shift because it does not have close contrast data. take mean brightness. CLAHE This technique produces good results This technique produce limited when histogram equalization can’t contrast enhancement due to local produce attractive results. enhancement. BPHE Produce best results when HE Take more time duce to separation produces brightness shift. into two images and appending after their enhancement. The best among the above discussed technique is BPHE (brightness preserving histogram equalization) it produces good result while preserving the image mean brightness.
  • 12. • Noise is the result of errors in the image acquisition process that result in pixel values that do not reflect the true intensities of the real organ. • Radiographic images are prone to a variety of types of noise due to several reasons such as:- o If the image is scanned from an X-Ray film or CT image, the film grain is a source of noise. It can be a result of a damaged film or due to the scanner itself. o If the image is captured directly from digital X-Ray scanner or a CT scanner it can be due to mechanism of gathering the data.
  • 13. • Linear Filtering is easiest method to remove certain type of noise. Averaging or mean filter can be used to accomplish this job. In averaging filter each pixel gets set to the average of its neighboring pixels. The problem with averaging filter is that edges of image get blurred. • To overcome this problem we use selective mean filter such as sigma filter. It preserves edges better and is less sensitive to edges. • The filter smoothes an image by taking an average over the neighboring pixels, but only includes those pixels that have a value not deviating from the current pixel by more than a given range. • Edges having a value very different from the surrounding are not included in the average and, thus, completely eliminated from blurring.
  • 14. • Median filter works in a similar way as averaging filter, the only difference is the output value of a pixel is determined by the median of the neighboring pixel rather than mean. • The principle advantage of median filtering over averaging is that it is much less sensitive to extreme values. Therefore median filtering is better to remove noise while reducing the blurring of edges.
  • 15. • Wiener filter often produce much better results than linear filter. It uses a pixel wise adaptive Wiener method based on statistics estimated from a local neighborhood of each pixel.. • This filter produces best output when noise is AWGN. • The problem of this method over the previous one is it requires more computational time.
  • 16.
  • 17.
  • 18. Table 2: Noise Reduction Advantages Disadvantages Median Filtering Easy to implement. Image edges get blurred. Sigma Filter Easy to implement by adding Can’t be used for salt & pepper noise. threshold in averaging filter. Wiener Filter Produce best output when the noise is Require high computational time. additive white Gaussian noise. Sigma filter produce better result for CT and MRI images. It preserves the edges while removing the noise. Threshold can be adjusted to acquire the desired performance. However median filter also reduce noise effectively. Its results become good if we apply image sharpening filter after median filtering.
  • 19. • In radiology, we want the recorded image to be a faithful representation of the organs that we want to see but every image is more or less blurry because image information spills over to neighboring pixels. • When the image does not shows sharp details of its features it is called blurred image. Thus, image sharpening is fundamental in making images clear and useful. • Image sharpening using Laplacian of Gaussian filter has been used for CT or MRI images and high frequency component boosting has been used in X-Ray and mammographic images.
  • 20. • Contrast enhancement using histogram processing is an effective method, four techniques of histogram processing has been applied on a large number of digital radiographic images. BPHE has shown best results in majority of cases. Three techniques have been used for noise reduction among them sigma filter has shown better results. However median filter followed by image sharpening also show good results.
  • 21. • Various aspects of image enhancement are catered for in the implementation and subsequent exercise of results, nevertheless, we understand that it is so demanding and absorbing area for research that the work could substantially be carried forward in following directions as a future work: o Improvement in selective noise reduction techniques. o Level correction of image by combining it with image segmentation.