利索-全球专利检索

  1. 登录
  2. 注册
发明公开
CN109614947A 电力部件识别模型训练方法、装置和计算机设备 无效 - 驳回

电力部件识别模型训练方法、装置和计算机设备
摘要：
本申请涉及一种电力部件识别模型训练方法、装置和计算机设备。所述方法包括：获取机巡图像；识别所述机巡图像中的电力部件；在所述机巡图像中，对所述电力部件进行外观特征变换，得到部件变换图像；采用所述部件变换图像对电力部件识别模型进行机器训练，得到优化识别模型；所述优化识别模型用于识别待识别图像中的电力部件。采用本方法能够解决现有的电力部件识别模型存在识别准确度不高的问题。
摘要（英）：

The invention relates to a power component recognition model training method and device and computer equipment. The method comprises the steps of obtaining a machine inspection image; I; identifying an electric power part in the machine patrol image; C; carrying out appearance feature transformation on the electric power part in the machine inspection image to obtain a part transformation image; C; carrying out machine training on a power component recognition model by adopting the component transformation image to obtain an optimized recognition model; W; wherein the optimization identification model is used for identifying the electric power part in the to-be-identified image. By adopting the method, t, the problem of low recognition accuracy of an existing power part recognition model can be solved.

0/0