我可以配置 Google Vision 来识别粗俗的分数符号(例如 ½、¼ 等)吗?

Can I configure Google Vision to recognize vulgar fraction symbols (e.g. ½, ¼, etc...)?

当我运行 this image containing various vulgar fraction symbols through the Google Vision demo时,它能正确识别除那些符号之外的所有字符。当我使用 API 时也是如此,无论是 TEXT_DETECTION 还是 DOCUMENT_TEXT_DETECTION。有什么方法可以配置 Google Vision 以准确识别这些符号?

Vision API 没有检测此类字符的特定配置。 OCR 功能已开发用于执行文本识别;然而,在某些情况下,分数符号未被识别为字符,导致服务获得错误的值,甚至它们无法识别符号本身。

基于此,我通过正确使用this image and I could confirm that the service was able to recognize several fraction symbols进行了运行一些测试。请记住,Vision API 使用 机器学习模型 ,这些模型正在不断训练以提高结果质量。

我建议您查看 Supported Images document where you can find some file format and image sizing recommendations that may help you to improve your results accuracy, as well use the Send Feedback button located at the lower left and upper right corners of the Vision API public 文档,以便您对产品发表意见。