GUIDED BY: C.VENKATESH PRESENTED BY: S.FAHIMUDDIN C.VAMSI KRISHNA ASST.PROFESSOR M.V.KRISHNA REDDY...

25
using morphological image processing GUIDED BY: C.VENKATESH PRESENTED BY: S.FAHIMUDDIN C.VAMSI KRISHNA ASST.PROFESSOR M.V.KRISHNA REDDY (DEPT.ECE)

Transcript of GUIDED BY: C.VENKATESH PRESENTED BY: S.FAHIMUDDIN C.VAMSI KRISHNA ASST.PROFESSOR M.V.KRISHNA REDDY...

Page 1: GUIDED BY: C.VENKATESH PRESENTED BY: S.FAHIMUDDIN C.VAMSI KRISHNA ASST.PROFESSOR M.V.KRISHNA REDDY (DEPT.ECE)

Medical image analysis using morphological image processing

GUIDED BY:C.VENKATESH PRESENTED BY:S.FAHIMUDDIN C.VAMSI KRISHNAASST.PROFESSOR M.V.KRISHNA REDDY(DEPT.ECE)

Page 2: GUIDED BY: C.VENKATESH PRESENTED BY: S.FAHIMUDDIN C.VAMSI KRISHNA ASST.PROFESSOR M.V.KRISHNA REDDY (DEPT.ECE)

OVERVIEW1) Introduction2) Fitting And Hitting3) Morphological operations4) Results5) Conclusion

Page 3: GUIDED BY: C.VENKATESH PRESENTED BY: S.FAHIMUDDIN C.VAMSI KRISHNA ASST.PROFESSOR M.V.KRISHNA REDDY (DEPT.ECE)

IntroductionMorphological image processing is an important tool in digital image processing.The term morphology refers to the branch of biology that deals with the form and structure of animals and plants.Morphological image processing is generally based on the analysis of two valued image in terms of certain predetermined geometric shape known as structuring element.The morphological operations are applied on gray scale images in medical image analysis.The morphological image processing can also be used to educate the patient , about his health condition.

Page 4: GUIDED BY: C.VENKATESH PRESENTED BY: S.FAHIMUDDIN C.VAMSI KRISHNA ASST.PROFESSOR M.V.KRISHNA REDDY (DEPT.ECE)

Mathematical MorphologyMathematical morphology is a powerful methodology which was initiated in the late 1960s by G.Matheron and J.Serra at the Fontainebleau School of Mines in France.

Nowadays it offers many theoretic and algorithmic tools inspiring the development of research in the fields of signal processing, image processing, machine vision, and pattern recognition.

Page 5: GUIDED BY: C.VENKATESH PRESENTED BY: S.FAHIMUDDIN C.VAMSI KRISHNA ASST.PROFESSOR M.V.KRISHNA REDDY (DEPT.ECE)

Fitting and hitting

The structuring element is positioned at all possible locations in the binary image.

It is compared with the corresponding neighborhood of pixels.

The morphological operation resembles a ‘Binary’ correction.

The operation is logical than arithmetic in nature.Operations are FIT and HIT

Page 6: GUIDED BY: C.VENKATESH PRESENTED BY: S.FAHIMUDDIN C.VAMSI KRISHNA ASST.PROFESSOR M.V.KRISHNA REDDY (DEPT.ECE)

Fit

• The structuring element is said to FIT the image if each of its pixel and corresponding image pixel are ‘1’.•For the above example both S1,S2 fit the image at ‘A’.•The structuring element pixels set to ‘0’ are ignored when testing for a FIT.•S2 fits the image at ‘B’ and neither S1 nor S2 fits at ‘C’.•FIT concept corresponding to intersection (AND) operation.

Page 7: GUIDED BY: C.VENKATESH PRESENTED BY: S.FAHIMUDDIN C.VAMSI KRISHNA ASST.PROFESSOR M.V.KRISHNA REDDY (DEPT.ECE)

HitThe structuring element is said to hit the image if , for any of its pixels and corresponding image pixels are ‘1’.Here also we ignore image pixels for which the corresponding structuring element pixels is ‘0’.For the above example, S1 and S2 hit the image in neighborhood of ‘A’ , ‘B’.But at neighborhood ‘C’ only S1 hits the image. HIT concept corresponding to Union(OR) operation.

Page 8: GUIDED BY: C.VENKATESH PRESENTED BY: S.FAHIMUDDIN C.VAMSI KRISHNA ASST.PROFESSOR M.V.KRISHNA REDDY (DEPT.ECE)

Fitting and hittingIn the given image A,B,C are the three positions where the S1 and S2 structuring elements are positioned.

1 1 1 S1= 0 1 0 1 1 1

1 1 1S2= 1 1 1 0 1 0

Page 9: GUIDED BY: C.VENKATESH PRESENTED BY: S.FAHIMUDDIN C.VAMSI KRISHNA ASST.PROFESSOR M.V.KRISHNA REDDY (DEPT.ECE)

Morphological Operations The four most basic operations in mathematical morphology are dilation, erosion, opening and Closing :

Dilation Erosion

Opening Closing

Page 10: GUIDED BY: C.VENKATESH PRESENTED BY: S.FAHIMUDDIN C.VAMSI KRISHNA ASST.PROFESSOR M.V.KRISHNA REDDY (DEPT.ECE)

DilationDilation : “Grow image regions”.The growing depends on choice of structuring

element.Dilation make an object by adding pixels around

its edges.The dilation of an image ‘A’ by a structuring

element ‘B’ is written as AB 1 if ‘B’ hits ‘A’G(x , y)= 0 otherwiseThe results of dilation are influenced not

only by the size of structuring element but also its shape.

It can be performed on both binary and grey tone images.

Page 11: GUIDED BY: C.VENKATESH PRESENTED BY: S.FAHIMUDDIN C.VAMSI KRISHNA ASST.PROFESSOR M.V.KRISHNA REDDY (DEPT.ECE)

DilationThe basic effect of the operator on a binary image is to gradually enlarge the boundaries of regions of foreground pixels (i.e. white pixels, typically). Thus areas of foreground pixels grow in size while holes within those regions become smaller.

Page 12: GUIDED BY: C.VENKATESH PRESENTED BY: S.FAHIMUDDIN C.VAMSI KRISHNA ASST.PROFESSOR M.V.KRISHNA REDDY (DEPT.ECE)

Erosion Erosion : shrink image regions The shrink depends on the choice of structuring

element. It makes an object smaller by removing or eroding

away the pixels on its edges. The erosion of an image ‘A’ by a structuring element

‘B’ is denoted by A Θ B .

G(x , y)= 1 if ‘B’ fits ‘A’ 0 otherwise

Erosion is the morphological operation it can be performed on both binary and grey images.

Page 13: GUIDED BY: C.VENKATESH PRESENTED BY: S.FAHIMUDDIN C.VAMSI KRISHNA ASST.PROFESSOR M.V.KRISHNA REDDY (DEPT.ECE)

Erosion

•This erode away the boundaries of regions of foreground pixels (i.e. white pixels, typically).

•Thus areas of foreground pixels shrink in size, and holes within those areas become larger

Page 14: GUIDED BY: C.VENKATESH PRESENTED BY: S.FAHIMUDDIN C.VAMSI KRISHNA ASST.PROFESSOR M.V.KRISHNA REDDY (DEPT.ECE)

OpeningOpening : structured removal of image region

boundary pixelsIt is obtained by combining erosion and dilation.Opening “separates the objects”, generally

smoothes the contour of an image.The opening of an image ‘A’ by a structuring

element ‘B’ is denoted as A ○ B A ○ B = (A Θ B) BOpening operation is obtained by doing dilation

on eroded image.Opening involves one or more erosions followed

Page 15: GUIDED BY: C.VENKATESH PRESENTED BY: S.FAHIMUDDIN C.VAMSI KRISHNA ASST.PROFESSOR M.V.KRISHNA REDDY (DEPT.ECE)

Opening

A binary image containing a mixture of circles and lines. Suppose that we want to separate out the circles from the lines, so that they can be counted. Opening with a disk shaped structuring element 11 pixels in diameter gives

Page 16: GUIDED BY: C.VENKATESH PRESENTED BY: S.FAHIMUDDIN C.VAMSI KRISHNA ASST.PROFESSOR M.V.KRISHNA REDDY (DEPT.ECE)

ClosingClosing : structured filling in of image region and

boundary pixels.It is obtained by combining erosion and dilation.Closing join the objects, it tends to smooth sections

of contours but, as opposed to opening.It eliminates the holes and fills gaps in the contour.The closing of an image ‘A’ by a structuring

element ‘B is denoted as A ● B A● B = (A B) Θ BClosing is obtained by doing erosion on dilated

image.Closing Involves one or more dilations followed by

one erosion.

Page 17: GUIDED BY: C.VENKATESH PRESENTED BY: S.FAHIMUDDIN C.VAMSI KRISHNA ASST.PROFESSOR M.V.KRISHNA REDDY (DEPT.ECE)

Closing An image containing large holes and small holes. If it is desired to remove the small holes while retaining the large holes, then we can simply perform a closing with a disk-shaped structuring element with a diameter larger than the smaller holes, but smaller than the large holes.

Page 18: GUIDED BY: C.VENKATESH PRESENTED BY: S.FAHIMUDDIN C.VAMSI KRISHNA ASST.PROFESSOR M.V.KRISHNA REDDY (DEPT.ECE)

Results The morphological image processing operations is use to analyze the medical images.In this project the grey tone image of a patient suffering from tuberculosis is considered

(a) Original image

Page 19: GUIDED BY: C.VENKATESH PRESENTED BY: S.FAHIMUDDIN C.VAMSI KRISHNA ASST.PROFESSOR M.V.KRISHNA REDDY (DEPT.ECE)

ResultsBy performing dilation operation to original image the tiny white spots which are not visible in the original image are clearly visible in dilated image.It is very useful in diagnosis of T.B in depth.

(b)Dilated image

Page 20: GUIDED BY: C.VENKATESH PRESENTED BY: S.FAHIMUDDIN C.VAMSI KRISHNA ASST.PROFESSOR M.V.KRISHNA REDDY (DEPT.ECE)

ResultsBy performing erosion operation to original image ,the lung tissue which is in black color can be analyzed.If any fibrosis occurs ,the tissue appears to be partially white.In the original image ,as there is no defect , the same is reflected in the erosion.

(c)Eroded image

Page 21: GUIDED BY: C.VENKATESH PRESENTED BY: S.FAHIMUDDIN C.VAMSI KRISHNA ASST.PROFESSOR M.V.KRISHNA REDDY (DEPT.ECE)

ResultsoIn opening we can obtain smooth contour of the image

(d) Open image

Page 22: GUIDED BY: C.VENKATESH PRESENTED BY: S.FAHIMUDDIN C.VAMSI KRISHNA ASST.PROFESSOR M.V.KRISHNA REDDY (DEPT.ECE)

ResultsIn closing also we can obtained the smooth contour of the image

(e) Close image

Page 23: GUIDED BY: C.VENKATESH PRESENTED BY: S.FAHIMUDDIN C.VAMSI KRISHNA ASST.PROFESSOR M.V.KRISHNA REDDY (DEPT.ECE)

Conclusion

oThe morphological operations can enhance the image and analyze the depth of the disease from obtained corrected x-Ray images.oMedical image analysis : detection of tuberculosis disease from x-ray images.oIt is implemented in java , java platform provides a convenient representation for images.oThe gray scale operations are performed using console programming and it is fully console based.oThis produces an output image when input image and structuring element is given.

Page 24: GUIDED BY: C.VENKATESH PRESENTED BY: S.FAHIMUDDIN C.VAMSI KRISHNA ASST.PROFESSOR M.V.KRISHNA REDDY (DEPT.ECE)

Queries?

Page 25: GUIDED BY: C.VENKATESH PRESENTED BY: S.FAHIMUDDIN C.VAMSI KRISHNA ASST.PROFESSOR M.V.KRISHNA REDDY (DEPT.ECE)