In computer vision, image segmentation is the process of partitioning a digital image into multiple segments (sets of pixels, also known as super pixels). The goal of segmentation is to simplify and / or change the representation of an image into something that is more meaningful and easier to analyze. Image segmentation is typically used to locate objects and boundaries (lines, curves, etc.) in images. More precisely, image segmentation is the process of assigning a tag to each pixel in an image such that pixels with the same tag share certain characteristics.
The result of image segmentation is a set of segments that collectively cover the entire image or a set of contours extracted from the image (see edge detection). Each of the pixels in a region is similar with respect to some calculated property or property, such as color, intensity, or texture. Adjacent regions are significantly different with respect to the same feature (s). When applied to a stack of images, typical in medical imaging, the resulting contours after image segmentation can be used to create 3D reconstructions with the help of interpolation algorithms like Marching Cubes.
The simplest method of image segmentation is called the threshold method. This method is based on a clip level (or threshold value) to convert a grayscale image to a binary image. There is also a balanced histogram threshold.
The key to this method is to select the threshold value (or values when multiple levels are selected). Several popular methods are used in the industry, including the maximum entropy method, the Otsu method (maximum variance), and k-grouping means.
Recently, methods for computed tomography (CT) imaging threshold have been developed. The key idea is that, unlike the Otsu method, thresholds are derived from radiographs rather than image (reconstructed).
New methods suggested the use of nonlinear thresholds based on multidimensional diffuse rules. In these works the decision on the belonging of each pixel to a segment is based on multidimensional rules derived from the fuzzy logic and evolutionary algorithms based on the environment of illumination of the image and its application.