SIRG-BSU_3_used-important.pdf
- 1. A Survey on Image Segmentation 1 Image Segmentation : A vision for Development . Lecture 3 Dr. Ahmed Elngar Faculty of Computers and Artificial Intelligence Beni-Suef University Supervised by Computer Vision: Algorithms and Applications
- 2. Outline Definition Mechanism Types and comparison Mathematical Formulation & Example Advantages & Disadvantages Conclusion References 2
- 3. 3 What is Image Segmentation? • Image segmentation is the process of dividing a digital image into multiple parts called segments (objects). • Segment is sets of pixels. • The goal of segmentation is to simplify the image into an image that more meaningful and easier to analyze.
- 4. 4 What is Image Segmentation?
- 5. 5 What is Image Segmentation?
- 6. What is Image Segmentation? 6 • There’s only one object here – a dog. We can build a simple cat-dog classifier model and predict that there’s a dog in the given image. • In case we have multiple objects present, we then rely on the concept of Object Detection (OD).
- 7. How does image segmentation work? 7 • We can divide the image into various parts called segments. It’s not a great idea to process the entire image at the same time as there will be regions in the image which do not contain any information. By dividing the image into segments, we can use the important segments for processing the image. • An image is a collection or set of different pixels. We group together the pixels that have similar values using image segmentation.
- 8. USAGE 8 • Object detection builds a bounding box corresponding to each object in the image. But it tells us nothing about the shape of the object. • Image segmentation creates a pixel-wise mask for each object in the image. This technique gives us more information about the image.
- 9. Why do we need Image Segmentation? 9 • Cancer has long been a deadly illness. Even in today’s age of technological advancements, cancer can be fatal if we don’t identify it at an early stage. Detecting cancerous cell(s) as quickly as possible can potentially save millions of lives. Here, we can clearly see the shapes of all the cancerous cells. • Object detection will not be very useful here. We will only generate bounding boxes which will not help us in identifying the shape of the cells. • Image Segmentation make a MASSIVE impact here. They help us approach this problem in a more meaningful results.
- 10. What are Types of image segmentation? 10
- 11. • Semantic segmentation • Instance segmentation Types of image segmentation 11
- 12. Types of image segmentation 12 • Both the images are using image segmentation to identify and locate the people present: • In image 1, every pixel belongs to a particular class (either background or person). Also, all the pixels belonging to a particular class are represented by the same color (background as black and person as pink). This is an example of semantic segmentation • Image 2 has also assigned a particular class to each pixel of the image. However, different objects of the same class have different colors (Person 1 as red, Person 2 as green, background as black, etc.). This is an example of instance segmentation
- 13. Classification of image segmentation techniques: 13 A. Structural Segmentation Techniques : • There are techniques of image segmentation that dependent on the information of the structure of required portion of the image. the required region which is to be segmented. B. Stochastic Segmentation Techniques: • There are techniques of the image segmentation which his work dependent on the discrete pixel values of the image instead of the structural information of region. C. Hybrid Techniques: • There are techniques of the image segmentation that uses the concepts of both techniques. these uses discrete pixel and structural information together.
- 14. What is image segmentation Methods? 14
- 15. What is image segmentation Methods? 15 • Threshold Method • Edge Based Method • Region Based Method • Clustering Based Method • Watershed Based Method
- 16. Thresholding Method 16 • Thresholding methods are the simplest methods for image segmentation. These methods divide the image pixels with respect to their intensity level. These methods are used over images having lighter objects than background. The selection of these methods can be manual or automatic i.e. can be based on prior knowledge or information of image features. There are basically three types of thresholding: 1) Global Thresholding: This is done by using any appropriate threshold value T. This value of T will be constant for whole image. • If pixel intensities vary between 0 and 255. Then the threshold T = 127 was selected as the minimum between two modes on a histogram. • On the basis of T the output image can be obtained from original image as:
- 17. Thresholding Method (cont.) 2) Variable Thresholding: In this type of thresholding, the value of T can vary over the image. This can further be of two types: Local Threshold: chooses different threshold values for every pixel in the image based on an analysis of its neighboring pixels. This is to allow images with varying contrast levels where a global thresholding technique will not work satisfactorily. Adaptive Threshold: if an image has different lighting conditions in different areas. In that case, adaptive thresholding can help. determine the threshold for a pixel based on a small region around it. So we get different thresholds for different regions of the same image which gives better results for images with varying illumination . The threshold value is the mean of the neighbourhood area minus the constant C 3) Multiple Thresholding: In this type of thresholding, there are multiple threshold values like T0 and T1. By using these output image can be computed as: The values of thresholds can be computed with the help of the peaks of the image histograms. Simple algorithms can also be generated to compute these. 17
- 20. Edge Based Segmentation Method 20 • The edge detection techniques are well developed techniques of image processing on their own. • The edge based segmentation methods are based on the rapid change of intensity value in an image because a single intensity value does not provide good information about edges. • Edge detection techniques locate the edges where either the first derivative of intensity is greater than a particular threshold. • In edge based segmentation methods, first of all, the edges are detected and then are connected together to form the object boundaries to segment the required regions. • The basic two edge based segmentation methods are: Gray histograms and Gradient based methods. • To detect the edges one of the basic edge detection techniques like sobel operator, canny operator and Robert‟s operator etc can be used. • Result of these methods is basically a binary image. • These are the structural techniques based on discontinuity detection.
- 21. Edge Based Segmentation Method Cont.. 21
- 22. Edge Based Segmentation Method Cont.. 22 • Mathematical Formulation of Gradient Operators of an image f(x,y) is: • And For Laplacian operator we can use filters as • With Mathematical Formulation of image f(x,y) for laplacian is:
- 23. Edge Based Segmentation Method Cont.. 23
- 24. Region Based Segmentation Method 24 • The region-based segmentation methods are the methods that segments the image into various regions having similar characteristics. • There are two basic techniques based on this method: 1. Region growing methods: The region growing based segmentation methods are the methods that segments the image into various regions based on the growing of seeds (initial pixels). These seeds can be selected manually (based on prior knowledge) or automatically (based on particular application). we make these steps: • Calculate the mean of image pixels which integer value will be the thresholds of operation (T). • Select the nearly value of peak (bigger) value of pixels as P. • Subtract the value of P from neighbors and check if result < threshold(T) then the pixel belong to the region and put pixel value =1. Else this pixel is not belongs to region and put pixel value=0. • Repeat this operation on all pixels.
- 25. Region Based Segmentation Method Cont.. 25
- 26. Region Based Segmentation Method Cont.. 26
- 27. Region Based Segmentation Method Cont.. 27
- 28. Region Based Segmentation Method Cont.. 28
- 29. Region Based Segmentation Method Cont.. 29
- 30. Region Based Segmentation Method (cont.) 2. Region splitting and merging methods: The region splitting and merging based segmentation methods uses two basic techniques i.e. splitting and merging for segmenting an image into various regions. • Splitting stands for iteratively dividing an image into regions having similar characteristics • Merging contributes to combining the adjacent similar regions. 30
- 31. Region Based Segmentation Method (cont.) we are make this steps: • Divided image as four regions. • Determine min pixel and max pixel of the first region and subtract it. Threshold (T) should be less than or equal result (<=result). • Repeat previous step for all regions on if result more than T divide this region again Like this: • Next step to collect related regions by subtract max pixel of region from min pixel from another region if result <= T. collect to regions as one region. • Repeat previous step for all regions 31
- 32. Region Based Segmentation Method (cont.) 32