Hello, Personal
I'm developing a solution where I use Google Cloud Vision to analyze texts in the image, this is already ready in my solution. Managing the image and Google Vision returns the found words and their coordinates.
What I need is to extract the face (the back of the RG document) from the scanned image, did several tests with OpenCV, EmguCV (C #) and tried using TensorFlow (Google) using neural network to try to create something that recognizes the face of the RG document, but all a bit confusing in this part because there is little content regarding OpenCV, EmguCV and TensorFlow and the little content that exists are all in English or other languages.
TensorFlow uses it to train Python (I do not know if it's worth it either) because there are a lot of factors to use the TensorFlow installation, configuration taking into account the time of my learning without knowing if this will work for my project.
OpenCV I wanted to use it but it is still unclear how the models are trained as well and in python or C ++ my knowledge in these languages are scarce but I am modestly speaking senior in C # but I do not know which way to go for that .
Today I send the image the way I receive it for api from Google Vision and I retrieve the OCR analysis information summarizing I want to detect the RG inside the scanned image and cause it to rotate it to leave it horizontal and then yes sends it to the api Google Vision.
Does anyone have any ideas for doing this "pre-upload step" that is medium or some easy-to-understand model for how to train OpenCV image models. I've been reading a lot and what I theoretically need and the neural network model Convolutional Neural Network, for Detect Object.
I have done several examples of marking the image using OpenCV (EmguCV) but due perhaps the lack of knowledge of the framework I could not use and I have read several tutorials to leave the image and GrayScale and Threshold, I have already used the library AForge but I still could not reach a stage or legal level of the project I need this step before sending for OCR analysis.
I ask for tips and examples if anyone has.
Hugs.