I'm trying to use VNRecognizeTextRequest and/or VNDetectTextRectanglesRequest to highlight Chinese text in an image.
The results are mediocre/bad compared to what's recognized in e.g. the Photos app.
The VN functions work okay for most left-to-right text that's in a "standard" font.
The VN functions completely fail to recognize any top-to-bottom text at all, and also completely fail to recognize any text that's a little bit stylized.
The ImageAnalysis functions have no problem recognizing and transcribing all the text in an image, they do a great job, but they don't return bounding boxes for the text, so as great as they are, they're kind of useless for my purposes.
I guess my question is, why are the VN functions different from (and worse than) the ImageAnalysis functions, and is there any way to get the VN functions to do better??
Thanks in advance!