10.Image Segmentation

10.1 Fundamentals

10.2 Point Line, and Edge Detection

10.2.1 Background -The magnitude of the response at the point is much stronger for second than for the first-order derivative -A second - order derivative is much more aggressive than a first - order derivative in enhancing shrp changes -The point detection should be based on the second derivative

10.2.2 Detection of Isolated Points -The idea is that the intensity of an isolated point will be quite different from its surroundings and thus will be easily detectable by this type of mask

10.2.3 Line Detection -The isolated points in the figure are points that also had similarly strong responses to the mask

10.2.4 Edge Models -Edge detection is the approach used most frequently for segmenting images based on abrupt changes in intensity

10.2.5 Basic Edge Detection 10.2.6 More Advanced Techniques for Edge Detection 10.2.7 Edge Linking and Boundary Detection

10.2.5 Basic Edge Detection -The image gradient and its properties -Gradient operators -Combining the gradient with thresholding

10.2.6 More Advanced Techniques for Edge Detection -The Marr-Hildreth edge detector -The Canny edge detector

10.2.7 Edge Linking and Boundary Detection -Local processing -Regional processing -Global processing using the Hough transform

10.3 Thresholding

10.3.1 Foundation -The basics of intensity thresholding -The role of noise in image thresholding -The role of illumination and reflectance

10.3.2 Basic Global Thresholding -This simple algorithm works well in situations where there is a reasonably clear valley between the modes of the histogram related to objects and background

10.3.3 Optimum Global Thresholding Using Otsu’s Method -The probability density function of the intensity levels of each class and the probability that each class occurs in a given application. -PDFs is not a trivial matter, so the problem usually is simplified by making workable assumptions about the form of the PDFs such as Gaussian fuctions.

10.3.4 Using Image Smoothing to Improve Global Thresholding -When noise cannot be reduced at the source, and thresholding is the segmentation method of choice, a technique that often enhances performance is to smooth the image prior to thresholding

10.3.5 Using Edges to Improve Global Thresholding -By varying the percentile at which the threshold is set we can even improve on the segmentation of the cell regions.

10.3.6 Multiple Thresholding -The thresholding method can be extended to an arbitrary number of thresholds, because the separability measure on which it is based also extends to an arbitrary number of classes -Image partitioning -Variable thresholding based on local image properties -Using moving averages

10.3.7 Multivariable Thresholding -A notable example is color imaging, where red, green and blue components are used to form a composite color image

10.4 Region-Based Segmentation

10.5 Segmentation Using Morphological Watersheds

10.6 The Use of Motion in Segmentation