GrowCut is a foreground extraction (background removal) tool, implemented as a plug-in for Photoshop-compatible graphics editors on MS Windows. It embodies the GML Matting algorithm formerly available as a separate plug-in. Adobe Photoshop selection plugins, based on experimental interactive image segmentation technology.

GrowCut is an interactive image cutout & matting tool designed to extract solid or opaque objects as well as objects having smooth or fuzzy edges. Image cutout is the process of removing or isolating an object in a picture. Using advanced image segmentation algorithms GrowCut surpasses all other existing cutout programs in feedback time, speed and ease of use. By drawing only vague strokes inside and outside the object, user can segment even most complex images.

1. Segmentation
Create precise cutouts easily by placing a few rough strokes inside and around the object. GrowCut saves a lot of time when you need to process many photos.

2. Matting
Improve the cutout quality by applying automated matting process that deals with opacity changes (blurry edges, hair, transparent elements). Handle the most complex cases by using effective refinement tools.

3 .The Result
Create clean, photorealistic composites using objects extracted with GrowCut.

Apply filters to the foreground object leaving the background intact, or vice versa.

GrowCut is an Adobe Photoshop-compatible (.8bf) plug-in and has been tested to work with the following host-applications:
1. Adobe Photoshop 7.0 or above (tested up to CS4)
2. Adobe Photoshop Elements 3.0 or above
3. Corel Paint Shop Pro 9.0 or above
4. Macromedia Fireworks 8.0 or above
5. PhotoFiltre Studio
6. Serif Photoplus
7. IrfanView
8. The GIMP

Image segmentation is an integral part of image processing applications like medical images analysis and photo editing. A wide range of computational vision algorithms can also benefit from existence of reliable and efficient image segmentation technique. For
instance, intermediate-level vision problems such as shape from silhouette, shape from stereo and object tracking could make use of reliable segmentation of the object of interest from the rest of the scene. Higher-level problems such as recognition and image indexing can also make use of segmentation results in matching.

Fully automated segmentation techniques are being constantly improved, however, no automated image analysis technique can be applied fully autonomously with guaranteed results in general case. That is why semi-automatic segmentation techniques that allow solving moderate and hard segmentation tasks by modest effort on the part of the user are becoming more and more popular.

The license of this software is Free Trial Software, the price is $80.00, you can free download and get a free trial.