image segmentation is the process of automatically dividing an image into several parts and extracting the relevant data and information. Compared to the traditional Fuzzy C-Means algorithm, the Possibilistic C-Means ...
详细信息
image segmentation is the process of automatically dividing an image into several parts and extracting the relevant data and information. Compared to the traditional Fuzzy C-Means algorithm, the Possibilistic C-Means (PCM) algorithm has advantages in reducing the influence of noise on cluster center estimation. However, the PCM algorithm still shows poor clustering performance under high-intensity noise, which may lead to overlapping cluster centers. Considering the impact of neighborhood information of image pixels on the image segmentation results, this paper proposes a Vector-Based Possibilistic C-Means (VBPCM) algorithm. The algorithm incorporates neighborhood information and uses a vector representationmethod to describe image pixels. Additionally, an adjustable distance based on an exponential function is proposed to describe the similarity between vectors. The proposed VBPCM algorithm outperforms the conventional PCM, obtaining uplifiting gains of 4%, 2%, and 9% in Pixel Accuracy, Mean Pixel Accuracy, and Mean Intersection over Union, respectively. The experimental outputs illustrate that VBPCM algorithm can achieve more satisfactory cluster effect with high-intensity noise, further perform better in image segmentation task.
In this study, an image representation method based on multi-scale microstructural binary pattern extraction is proposed, which uses zero-mean microstructural pattern binarisation. This method can express all kinds of...
详细信息
In this study, an image representation method based on multi-scale microstructural binary pattern extraction is proposed, which uses zero-mean microstructural pattern binarisation. This method can express all kinds of important pattern structures that may appear in the image. By using the dominant binary pattern learning model, the dominant feature pattern sets adapted to different datasets can be obtained, which have good performance in the aspects of feature robustness, recognition, and representation ability. This method can greatly reduce the dimension of feature coding and improve the speed of the algorithm. The experimental results show that this method has strong recognition ability and robustness, is superior to the traditional local binary pattern and grey image micorstructure maximum response pattern methods, and has a competitive performance compared with the results of many latest algorithms.
暂无评论