Texture segmentation refers to splitting of an image into homogeneous textured regions. The proposed approach is influenced by the multi-channel filtering theory of the human visual system. Authors have used gabor filter as a means of decomposing the textured mosaics into constituent magnitude response images which are subjected to non-linear function, in addition to this the results thus obtained are used in computing the texture energy as proposed by Jain et al. Subsequently, maximum texture energy is selected pixel wise out of these obtained feature images. The resultant image is normalized and smoothened for unnecessary perturbation and subjected to K-means clustering meanwhile pixel co-ordinates are also used as additional features. The method has been devised, enforced and tested on the benchmark texture mosaics. The empirical data along with performance measures have entrenched the efficacy of the proposed approach.