How to classify a document by image? [closed]

Question

I need an opens source solution to classify a document. I do not want to use NLP i need only to check the look and feel.

I tried OpenCV. I have a template and i need to match it.

import cv2

template = cv2.imread(template_file,0)
template = cv2.normalize(template, None, alpha=0, beta=1, norm_type=cv2.NORM_MINMAX, dtype=cv2.CV_32F)

 method = ['cv2.TM_CCOEFF_NORMED'] 

 img = img2.copy()
 method = eval(meth)
 # Apply template Matching
 res = cv2.matchTemplate(img,template,method)

 min_val, max_val, min_loc, max_loc = cv2.minMaxLoc(res)
 if (max_val > threshold):
    print('match OK')

this method doesn't seems so robust and I get a lot of false positive.

Answer 1

You might want to look at Siamese CNNs depending on the size of your dataset. A good introduction can be found here.