16 January 2023 in IEEE Transactions on Fuzzy Systems
Noisy image segmentation using fuzzy c-mean clustering (FCM) algorithm is an important direction in the field of image segmentation, among which FCM using local information or non-local information constraints has made some progress. However, as the noise density increases, the local information cannot restore the real image. The non-local information-based segmentation method overly retains the noise and thus produces false edges resulting in the degradation of image segmentation accuracy. To address these problems, this paper use the regional and local information to develop an adaptive FCM image segmentation algorithm(RLFCM). First, the regional information and local information are obtained by the regional information filtering method and the local information filtering method. Then the weighted image is constructed in a certain way. Secondly, to make the objective function adaptively adjust the constraint ratio of the original image and the weighted image pixel by pixel, the degree of constraint is adaptively changed by using the difference between them as the coefficients of both through certain transformation. Finally, to speed up the convergence of the objective function, we add the number of clustering samples to the denominator of the objective function by certain transformations to reduce the number of iterations of the objective function. The proposed algorithm achieves more than 90% in image segmentation accuracy (SA), and mean Intersection-over-Union (mIoU) through synthetic and real-world image tests and acquires good performance in other indexes.
9 April 2025 in IEEE Signal Processing Letters
Deep convolutional networks have achieved remarkable success in superpixel segmentation. However, they only focus on local features ignoring global attributes. The visual Mamba demonstrates an exceptional capability to capture long-range dependencies and offers a lower computational cost compared to the Transformer. Building on this inspiration, we propose a novel superpixel segmentation with Mamba, termed SSMamba. In SSMamba, Mamba is integrated into a global-local architecture, enabling efficient interaction between global attributes and local features to produce high-quality superpixels. The designed activation function further enhances the effectiveness of SSMamba. Extensive experiments on four public datasets demonstrate that SSMamba outperforms existing state-of-the-art methods, achieving competitive average values of ASA = 0.9541, BR = 0.8768, BP = 0.2124, UE = 0.0910, and CO = 0.3698.
14 July 2021 in IET Image Processing
For region growing image segmentation, seed selection and image noise are two major concerns causing negative segmentation performance. This paper proposes a regional growth algorithm based on the Gaussian pyramid (GPRG), which automatically selects seed points and optimizes the growth path. To achieve automatic seed selection, Gaussian difference pyramid generated by the Gaussian pyramid is required. The growing seed of the salient target in an image is acquired by searching for extremums in each image of the Gaussian difference pyramid. For growing path optimization, edge changing direction is updated according to different Gaussian difference pyramid images with sizes from small to large. The edge of region growing is determined by the edge of the salient target in an image. Segmentation experiments show that this algorithm is able to automatically select seeds and accurately segment the salient target in an image with and without image noise. Performances in terms of segmentation accuracy (SA), mean intersection‐over‐union (mIoU) and E‐measure are superior compared with other methods.