首页> 外文会议>International Conference on Electronics, Information, and Communication >Microorganism Image Recognition based on Deep Learning Application
【24h】

Microorganism Image Recognition based on Deep Learning Application

机译:基于深度学习应用的微生物图像识别

获取原文

摘要

The application of Machine Learning for microorganism, especially bacteria and yeast, recognition becomes attractive because it can reduce the analyzing time of microorganism classification and eliminates human error compare to the classic biological techniques. Therefore, the recognition of microorganism based on Deep Learning increases the efficiency and accuracy of diagnostic process of infected patient. This research studies the possibility to use image classification and deep learning method to recognize bacteria and yeast with the comparison of cell image data-quality between our standard-resolution dataset and high-resolution dataset. We purpose this implementation method of microorganism recognition system using Python programming and the Keras API with Tensorflow Machine Learning framework. The experimental results have shown that bacteria and yeast cell images from microscope are able to be recognized. From the experimental results compare the deep learning methodology of different quality image dataset, our standard resolution dataset could be applied for obtaining more than 80% accuracy of prediction bacteria and yeast.
机译:与经典的生物学技术相比,机器学习在微生物(尤其是细菌和酵母菌)识别方面的应用具有吸引力,因为它可以减少微生物分类的分析时间并消除人为错误。因此,基于深度学习的微生物识别可提高感染患者诊断过程的效率和准确性。这项研究通过比较我们的标准分辨率数据集和高分辨率数据集的细胞图像数据质量,研究了使用图像分类和深度学习方法识别细菌和酵母的可能性。我们旨在使用Python编程和带有Tensorflow Machine Learning框架的Keras API来实现这种微生物识别系统的实现方法。实验结果表明,可以识别出显微镜下的细菌和酵母细胞图像。从实验结果比较不同质量图像数据集的深度学习方法,我们的标准分辨率数据集可用于获得超过80%的预测细菌和酵母准确度。

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