首页> 外国专利> METHOD AND APPARATUS FOR ESTABLISHING EXPRESSION RECOGNITION MODEL, AND COMPUTER DEVICE AND STORAGE MEDIUM

METHOD AND APPARATUS FOR ESTABLISHING EXPRESSION RECOGNITION MODEL, AND COMPUTER DEVICE AND STORAGE MEDIUM

机译:建立表达式识别模型的方法和装置,以及计算机设备和存储介质

摘要

Disclosed are a method and apparatus for establishing an expression recognition model, and a computer device and a storage medium, belonging to the field of artificial intelligence. The method comprises: acquiring data of a plurality of first training images and data of a plurality of second training images (201); according to a feature value, acquiring clustering centers corresponding to data of a plurality of target images, and reference maps corresponding to the data of the plurality of target images (203); randomly extracting data of two target images of different reference maps as first input image data to obtain data of a plurality of first input images corresponding to the clustering centers; randomly extracting second input images corresponding to different clustering centers to obtain data of a plurality of second input images; and inputting the first input images, the second input images and the clustering centers corresponding to the first input images into an EmtionNet. In addition, the method also relates to blockchain technology. The data of the first training images and the data of the second training images can be stored in a blockchain, thereby improving the expression recognition accuracy.
机译:公开了一种用于建立表达识别模型的方法和装置,以及属于人工智能领域的计算机设备和存储介质。该方法包括:获取多个第一训练图像的数据和多个第二训练图像的数据(201);根据特征值,获取对应于多个目标图像的数据的聚类中心,以及与多个目标图像的数据相对应的参考映射(203);随机提取不同参考映射的两个目标图像的数据作为第一输入图像数据,以获得与聚类中心对应的多个第一输入图像的数据;随机提取对应于不同聚类中心的第二输入图像,以获得多个第二输入图像的数据;并将与第一输入图像相对应的第一输入图像,第二输入图像和群集中心输入到EMTIONNET中。此外,该方法还涉及区块链技术。第一训练图像的数据和第二训练图像的数据可以存储在区块链中,从而提高表达式识别精度。

著录项

相似文献

  • 专利
  • 外文文献
  • 中文文献
获取专利

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