A new selective segmentation model for texture images and applications to medical images. (February 2019)

• Record Type: Journal Article
• Authors: Shah, Hassan; Badshah, Noor; Ullah, Fahim; Ullah, Asmat; Matiullah,
• Is Part Of: Biomedical signal processing and control. Volume 48(2019)
• Page Start: 234
• Page End: 247
• Publication Date: 2019-02
• Subjects: Active contours -- Texture images -- Level set -- Partial differential equation -- Additive operator splitting method; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2018.09.017
• Languages: English
• ISSNs: 1746-8094

Abstract

Highlights: A new model for selective segmentation of texture image is proposed. L 0 gradient norm is used for smoothing of texture. LGDF based model is used for selective segmentation. Abstract: Segmentation of texture images is an active area of image processing. Selective segmentation is the process of extracting a region of interest (ROI) in the image. In this paper, we propose a new model for selective segmentation of texture images, by incorporating geometrical constraints after smoothing the texture in image. The proposed model uses L 0 norm for smoothing of the texture and Badshah–Chen energy with local Gaussian kernel data fitting for selective segmentation. The proposed model is minimized to get gradient descent through Euler Lagrange's equation, which is then discretized through finite differences and the corresponding difference equation is solved by using additive operator splitting method. Experimental results of the proposed model are compared with the existing selective segmentation models and related models which are not based on selective segmentation. The model is further tested on medical images.