.png){kind=icon}
返回
Image Segmentation Using Linked Mean-Shift Vectors and Its Implementation on GPU
.png){kind=icon}
PRE
AI
DOI：10.1109/TCE.2014.7027348.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
This paper proposes a new approach to mean-shift-based image segmentation that uses a non-iterative process to determine the maxima of the underlying density, which are called modes. To identify the mode, the proposed approach performs a mean-shift process on each pixel only once, and uses the resulting mean-shift vectors to construct links for the pairs of pixels, instead of iteratively performing the mean-shift process. Then, it groups the pixels of the same mode, connected through the links, into the same cluster. Although the proposed approach performs the mean-shift process only once, it provides comparable segmentation quality to the conventional approaches. In experiments using benchmark images, the processing time was reduced to a quarter, while probabilistic rand index and segmentation covering were well maintained; they were degraded by only 0.38% and 1.87%, respectively. Furthermore, the proposed algorithm improves the locality of the required data and compute-intensity of the algorithm, which are important factors for utilizing the GPU effectively. The proposed algorithm, when implemented on a GPU, improved the processing speed by over 75 times compared to implementation on a CPU, while the conventional approach was accelerated by about 15 times(1).
Keyword:
Mean-shift algorithm
parallel processing
image segmentation
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
10.9
论文数:
5.1K
被引数:
6.8K
机构
引用论文
An efficient method for segmentation of images based on fractional calculus and natural selection
PREAI
分享收藏Tinnitus Retraining Therapy (TRT) as a Method for Treatment of Tinnitus and Hyperacusis Patients耳鸣再训练疗法 (TRT) 作为治疗耳鸣和高亢患者的方法
PREAI
分享收藏EEG Feature Extraction Using Genetic Programming for the Classification of Mental States.png)
Algorithms
OAAI
AlgorithmsIF0
OAAI分享收藏
查看更多内容