Improved K-Means Clustering with Colour Classification for Segmentation of Fruit Images

Monali Dahapute, Amit Welekar


In this paper we are proposing an improved clustering algorithm along with colour classification technique to segment the fruit images. This algorithm will provide more precise image segmentation for irregular shaped fruits such as banana, papaya, mango etc captured under natural illumination. Earlier segmentation methods are not suitable for fruit images captured in natural light; as they were sensitive to various colour intensity predisposed by the sunlight illumination.Natural illumination tempt uneven amount of light intensity on the surface of the object, resulting in low quality image segmentation. This improved algorithm will deal with problem of light effect due to natural illumination for irregular fruit images.

Full Text:


Copyright (c) 2016 Monali Dahapute, Amit Welekar

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.


All published Articles are Open Access at 

Paper submission: