Illumination-reflectance based novel approach for level set evolution

Image segmentation is a major task in many real time applications such as medical imaging, pattern recognition, artificial intelligence etc. Performing segmentation using conventional level set methods on images which are captured under various lighting conditions and shadows lead to improper results. The profoundness and accuracy of segmentation greatly depends on the amount of the illumination and reflectance components present in the images. Here in this paper we present a novel segmentation method by introducing a new force function on the level sets evolution based on reflectance & illumination present in the image. This method is successfully implemented on images suffering from above mentioned problems.