Azure认知服务 [英] Azure Cognative Services

问题描述

我们正试图从机械设备品牌/型号/序列号以及其他机械数据的照片中获取OCR. PowerApps中的ComputerVision API运气不佳.我们需要更好的准确性.

We are trying to get OCR from photographs of mechanical Equipment Make/Model/Serial Number and additional mechanical data. Not having much luck with ComputerVision API in PowerApps. We need better accuracy. 

是否有其他选择或其他方法可以改进?

Are there other options or other methodologies in place to improve?

我们正在使用PowerApps和移动相机为OCR拍照.

We are using PowerApps and mobile camera to take the photo for the OCR.

谢谢

推荐答案

我建议您仔细阅读以下文档，以提高Computer Vision API的准确性:

I would recommend you to go through the following doc to improve accuracy in Computer Vision API :

https://docs.microsoft.com/zh-cn/azure/machine-learning/desktop-workbench/how-to-improve-accuracy-for-computer-vision-models

https://docs.microsoft.com/en-us/azure/machine-learning/desktop-workbench/how-to-improve-accuracy-for-computer-vision-models

希望这会有所帮助.

这篇关于Azure认知服务的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！