I am developing a college project to perform the recognition of the notes through the TensorFlow, but the big problem is that the notes of the real have a lot of similarity between them, especially in the back of the note, another problem is the lack of a dataset with good quality of new notes of the real, so it is necessary to create a dataset with good quality images and it may be that at this point I am being flawed.
I made the whole TensorFlow configuration on windows and followed the tutorial ( link ) and there it uses the Faster-RCNN-Inception-V2-COCO model and with the images I have using this model the values of the loss is very high (Very High Same) I would like to know if you guys know some other model that would be very good for my scenario and if there would be some tips to work around these similarity problems.
