Fuzzy based energy model for Segmentation of images using hybrid image dataMS22

Segmentation of images having intensity inhomogeneity and texture is always challenging. A region based model is proposed for segmentation of images having intensity inhomogeneity and texture. The model uses local hybrid image data combined with fuzzy membership function, which helps the model to achieve global minimum. No re-initialization is not required. Due to the use of local intensity information of the hybrid image, the model works well in images having intensity inhomogeneity. For segmentation of texture images, the proposed model is combined with extended structure tensor (EST). The model works well in images having clutter background, and images having maximum, minimum or average intensity background.

This presentation is part of Minisymposium “MS22 - Mapping problems in imaging, graphics and vision (3 parts)
organized by: Ronald Lui (Chinese University of Hong Kong) , Ke Chen (University of Liverpool) .

Noor Badshah (University of Engineering and Technology Peshawar)
image enhancement, image reconstruction, image registration, image segmentation, inverse problems, partial differential equation models