NSST and vector-valued C–V model based image segmentation algorithm

• Published in: IET image processing Vol. 14; no. 8; pp. 1614 - 1620
• Main Authors: Wang, Xianghai, Zhao, Xiaoyang, Zhu, Yihuan, Su, Xin
• Format: Journal Article
• Language: English
• Published: The Institution of Engineering and Technology 19.06.2020
• Subjects: automatic thresholding; diffusion process; image fusion; image processing; image segmentation; image segmentation algorithm; nonoverlapping regions; nonsubsampled shearlet transform; NSST; Research Article; transforms; unsupervised image segmentation methods; vector‐valued Chan‐Vese model; vector‐valued C‐V model; vector‐valued image; visual effects; image processing; NSST; image fusion; transforms; vector-valued Chan-Vese model; image segmentation algorithm; vector-valued image; vector-valued C-V model; unsupervised image segmentation methods; nonsubsampled shearlet transform; image segmentation; visual effects; automatic thresholding; nonoverlapping regions; diffusion process
• ISSN: 1751-9659; 1751-9667; 1751-9667
• DOI: 10.1049/iet-ipr.2018.5027

Image segmentation is a process of partitioning an image into non-overlapping regions. Existing unsupervised image segmentation methods include level set, automatic thresholding and region-based CV mode and so on. However, image segmentation as a key technology in the field of image processing has not been solved indeed, especially for images with complex texture. For this reason, the authors proposed a novel image segmentation algorithm based on NSST and the vector-valued Chan–Vese (C–V) model. First, they obtained a multi-scale representation by exploiting the non-subsampled shearlet transform (NSST) to extract multi-dimensional data in the image. Afterwards, they gave the vector-valued C–V model, and applied it to all subbands of NSST, which are treated as a vector-valued image. By comparing with other class methods, the experimental results show that the proposed method has better visual effects and lower error rates. But at the same time, it is a little time consuming. The proposed method is reasonable and effective, by taking full advantages of each subband's directional information during its diffusion process, compared with traditional C–V model.