• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Engineering journal >Iris-based Image Processing for Cholesterol Level Detection using Gray Level Co-Occurrence Matrix and Support Vector Machine
【24h】

Iris-based Image Processing for Cholesterol Level Detection using Gray Level Co-Occurrence Matrix and Support Vector Machine

机译：基于IRIS的胆固醇水平检测图像处理使用灰度共发生矩阵和支持向量机

获取原文
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Serious illnesses such as strokes and heart attacks can be triggered by high levels ofcholesterol in human blood that exceeds ideal conditions, where the ideal cholesterol level isbelow 200 mg/dL. To find out cholesterol levels need a long process because the patient mustgo through a blood sugar test that requires the patient to undergo fasting for 10–12 hours firstbefore the test. Iridology is a branch of science that studies human iris and its relation to thewellness of human internal organs. The method can be used as an alternative for medicalanalysis. Iridology thus can be used to assess the conditions of organs, body construction, andother psychological conditions. This paper proposes a cholesterol detection system based onthe iris image processing using Gray Level Co-Occurrence Matrix (GLCM) and Support VectorMachine (SVM). GLCM is used as the feature extraction method of the image, while SVM actsas the classifier of the features. In addition to GLCM and SVM, this paper also construct apreprocessing method which consist of image resizing, segmentation, and color image to graylevel conversion of the iris image. These steps are necessary before the GLCM feature extractionstep can be applied. In principle, the GLCM method is a construction of a matrix containingthe information about the proximity position of gray level images pixels. The output of GLCMis fed to the SVM that relies on the best hyperplane. Thus, SVM performs as a separator of twodata classes of the input space. From the simulation results, the system built was able to detectexcess cholesterol levels through iris image and classify into three classes, namely: non–cholesterol (< 200 ????/????), risk of cholesterol (200–239 ????/????) and high cholesterol (> 240????/????). The accuracy rate obtained was 94.67% with an average computation time of 0.0696s.It was using each of the 75 training and test data, with the second-order parameters used arecontrast–correlation–energy–homogeneity, pixel distance = 1, quantization level = 8,Polynomial kernel types and One Against One Multiclass.
机译：诸如中风和心脏病发作的严重疾病可以通过高水平的人血液中超过理想条件的高水平触发，其中理想的胆固醇水平是200mg / dl。为了发现胆固醇水平需要一个长的过程，因为患者患有血糖试验，要求患者在前面测试患者10-12小时进行禁食。虹膜是研究人类虹膜的科学分支及其与人类内部器官韦尔韦尔的关系。该方法可用作医学分析的替代品。因此，虹膜可以用于评估器官，身体构建，以及其他心理条件的条件。本文提出了一种基于使用灰度共发生矩阵（GLCM）和支持Vectormachine（SVM）的虹膜图像处理的胆固醇检测系统。 GLCM用作图像的特征提取方法，而SVM ACTSAS的特征分类器。除了GLCM和SVM之外，本文还构造了一种APRePorcessing方法，该方法包括图像调整大小，分段和彩色图像到虹膜图像的GrayleVel转换。可以在可以应用GLCM功能提取前进行这些步骤。原则上，GLCM方法是矩阵的结构，其包含关于灰度级图像像素的接近位置的信息。 GLCMI的输出馈送到依赖最佳超平面的SVM。因此，SVM执行为输入空间的Twodata类的分隔符。从仿真结果来看，系统内置的系统能够通过虹膜图像检测胆固醇水平并分为三类，即：非胆固醇（<200 ???? / ????），胆固醇的风险（200-239？ ??? / ????）和高胆固醇（> 240 ???? / ????）。获得的精度率为94.67％，平均计算时间为0.0696S。使用75个训练和测试数据中的每一个，使用二阶参数使用的areContrbt - 相关 - 能量 - 均匀性，像素距离= 1，量化级别= 8，多项式内核类型和一个对阵一个多字符。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 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