Abstract The real world abounds with textured surfaces. Texture-based object segmentation is one of the early steps towards identification of surfaces and objects in an image. In this article, a feature-based segmentation (FBS) method is provided to isolate objects that consist
of similar texture patterns from an image based on the following features: inverse difference moment of gray-level co-occurrence matrix, contrast of Tamura, and gradient. In this article, a genetic algorithm is also provided to decide the most suitable values of the parameters used in the
FBS method. The experimental results show that the FBS method can provide expressive segmentation results.