Re: [tesseract-ocr] image_to_data recognize 'conf' as string

you can change int() to float() Vào lúc 14:32:58 UTC+7 ngày Thứ Sáu, 17 tháng 9, 2021, zdenop đã viết: > It is not the tesseract that produces conf as string but pytesseract. > > You can not convert float string to int directly in python. Check your > python tutorial how to do it correctly. > >

[tesseract-ocr] Question about training data and psm

Hey I've got a simple question and then I'll provide more context. I want to know whether I can fine-tune train tesseract using image/text pairs where each pair is only a single word. My understanding is that training happens on "line-level" data (which is how tesstrain describes it). The pro

Re: [tesseract-ocr] Failed to find library "leptonica-1.80.0.dll" for platform x86.

Your request is not related to tesseract specifically but Visual studio and Dot.Net. I am not familiar with Dot.Net and publishing/deploying if it's the final product. Anyway, the error message indicates that your application is not able to find its dependency (leptonica-1.80.0.dll). So, first of

Re: [tesseract-ocr] image_to_data recognize 'conf' as string

Can someone guide me how to enable Regix inside tesseract output to capture certain keywords ? What is best approach to catch certain keywords and its corresponding values, Any advise or help really appreciated. Regards, > On 1 Dec 2021, at 3:58 PM, Quang Linh wrote: > > you can change int(