Image segmentation is the process of partitioning an image into parts or regions. This division into parts is often based on the characteristics of the pixels in the image. For example, one way to find regions in an image is to look for abrupt discontinuities in pixel values, which typically indicate edges. These edges can define regions. Other methods divide the image into regions based on color values or texture.
|Segment image into foreground and background using active contours (snakes)|
|Binary image segmentation using Fast Marching Method|
|Segment image into two or three regions using geodesic distance-based color segmentation|
|Calculate weights for image pixels based on image gradient|
|Calculate weights for image pixels based on grayscale intensity difference|
|Select contiguous image region with similar gray values|
|Global image threshold using Otsu's method|
|Multilevel image thresholds using Otsu’s method|
|Global histogram threshold using Otsu's method|
|Adaptive image threshold using local first-order statistics|
|Find region boundaries of segmentation|
|2-D superpixel oversegmentation of images|
|Segment image into foreground and background using graph-based segmentation|
|Segment image into foreground and background using iterative graph-based segmentation|
|3-D superpixel oversegmentation of 3-D image|
|Burn binary mask into 2-D image|
|Overlay label matrix regions on 2-D image|
|Convert label matrix to cell array of linear indices|
This topic provides an overview of the Image Segmenter app and its capabilities.
Use graph cut to segment an image into foreground and background elements, using classification lines you draw over the image.
Use local graph cut (grabcut) to segment an image into foreground and background elements, using classification lines you draw over the image.
To segment circles from an image, use the Find Circles option in Image Segmenter app and specify a range of acceptable diameters.
Use the Auto Cluster option in Image Segmenter app to segment an image into foreground and background elements.
This example shows how to segment an image based on regions with similar color. You can display the image in different color spaces to differentiate objects in the image.
You can perform color thresholding on an image acquired from a live USB webcam.
Use point cloud control to segment an image by selecting a range of colors belonging to the object to isolate.
This example shows how to use texture segmentation to identify regions based on their texture.
This example shows how to perform land type classification based on color features using K-means clustering and superpixels.
This example shows how to perform a 3-D segmentation using active contours, and how to view the results using the Volume Viewer app.