Im exploring to use pretrained models like OpenCV EAST or CTPN or other to detect text on an image. I want to develop a tool in C# for this purpose. The aim is to develop a tool in which I can pass any pretrained model with test image, and the model should be able to identify the text blocks on the image. This tool needs to be a generic one in which any model can be used without making much or no code changes in the code.
In my efforts to explore different models and libraries (Tensorflow.NET, OpenCVSharp etc) I got impression that for each model I need to write model specific code to detect text on the images.
As Im quite novice in this field, my basic question is that if it is possible to use a generic code with all different models (EAST, CTPN , CRAFT etc) ? Or I need to write model specific code for all different models?
Thanks in advance
