首页> 外文期刊>WSEAS Transactions on Information Science and Applications >Performance Analysis of Feature Extraction and Selection of Region of Interest by Segmentation in Mammogram Images between the Existing Meta-heuristic Algorithms and Monkey Search Optimization (MSO)
【24h】

Performance Analysis of Feature Extraction and Selection of Region of Interest by Segmentation in Mammogram Images between the Existing Meta-heuristic Algorithms and Monkey Search Optimization (MSO)

机译:现有元启发式算法与猴子搜索优化(MSO)之间的乳房X线照片图像分割中特征区域提取和区域选择的性能分析

获取原文
获取原文并翻译 | 示例
           

摘要

In medical image processing, feature selection and extraction is an important task for performing image classification and recognition which is performed through the image segmentation process. This paper proposes a different approach; Monkey Search Optimization (MSO) which is based on Metaheuristic Algorithm is presented for selecting region of interest in mammogram image. Monkey Search Optimization (MSO) algorithm is considered as a new algorithm searching for optimum solution based on the foraging behavior of monkeys. Pectoral region removed image is given as input for feature extraction. The proposed algorithm can be implemented for various applications as the time consumption for the process is reduced greatly. In this paper the proposed algorithm is compared with few other meta-heuristics algorithms such as Ant Colony Optimization (ACO), Artificial Bee Colony Optimization (ABC) and Particle Swarm Optimization (PSO); from the results that the proposed approach can be considered to be an appropriate algorithm for image segmentation. Results are presented based on simulation made with the implementation in MATLAB which is tested on the images of MIAS database.
机译:在医学图像处理中,特征选择和提取是执行通过图像分割过程执行的图像分类和识别的重要任务。本文提出了一种不同的方法。提出了基于元启发式算法的猴子搜索优化算法(MSO),用于在乳房X线照片中选择感兴趣区域。猴子搜索优化(MSO)算法被认为是一种基于猴子的觅食行为来寻找最优解的新算法。去除了胸膜区域的图像作为特征提取的输入。由于大大减少了该过程的时间消耗,因此可以将所提出的算法用于各种应用。本文将该算法与其他几种元启发式算法进行了比较,如蚁群算法(ACO),人工蜂群算法(ABC)和粒子群算法(PSO)。从结果来看,所提出的方法可以被认为是用于图像分割的合适算法。基于在MATLAB中实现的仿真结果给出了结果,并在MIAS数据库的图像上进行了测试。

著录项

相似文献

  • 外文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号