Image segmentation

<p>In <a href="/facts/Digital_image_processing/zenalNCf">digital image processing</a> and <a href="/facts/Computer_vision/Tl2Yyk66">computer vision</a>, image segmentation is the process of partitioning a <a href="/facts/Digital_image/3TNT47Mv">digital image</a> into multiple image segments, also known as image regions or image objects (<a href="/facts/Set_(mathematics)/BfucfHMq">sets</a> of <a href="/facts/Pixel/UzwBvXBV">pixels</a>). 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 <a href="/facts/Boundary_tracing/kVLQuxxB">boundaries</a> (lines, curves, etc.) in images. More precisely, image segmentation is the process of assigning a label to every pixel in an image such that pixels with the same label share certain characteristics.
</p><p>The result of image segmentation is a set of segments that collectively cover the entire image, or a set of <a href="/facts/Contour_line/35Qten5r">contours</a> extracted from the image (see <a href="/facts/Edge_detection/9VplpIcS">edge detection</a>). Each of the pixels in a region are similar with respect to some characteristic or computed property, such as <a href="/facts/Color/XDvW7ESP">color</a>, <a href="/facts/Luminous_intensity/uUSDSAKR">intensity</a>, or <a href="/facts/Image_texture/tLQx6EP2">texture</a>. Adjacent regions are significantly different with respect to the same characteristic(s). When applied to a stack of images, typical in <a href="/facts/Medical_imaging/pL6JyJEp">medical imaging</a>, the resulting contours after image segmentation can be used to create <a href="/facts/3D_reconstruction/MlnAUm3l">3D reconstructions</a> with the help of geometry reconstruction algorithms like <a href="/facts/Marching_cubes/mYbQyPYD">marching cubes</a>.
</p>

Image segmentation open-in-new

Image segmentation