search

matthewearl / deep-anpr

Using neural networks to build an automatic number plate recognition system
MIT License
1.85k stars 697 forks source link

Confirmation on bounding conditions to mark labels for plate presence #9

Open paramrajpura opened 8 years ago

paramrajpura commented 8 years ago

The gen.py decides on presence of plate on two conditions:

  1. Scale bounds
  2. Translation bounds

I found a few images where the presence(p) was not consistent from visual perspective. Can this lead to slower convergence of the model? Just wanted a confirmation whether including a tight bound on skew/rotation would help. 00000007_ao18bpq_1 Image 1: license plate is skewed but presence is true 00000038_bf28zck_0 Image 2: license plate is in the image but presence is false

00000034_he17gvs_0 Image 3: license plate is in the image but presence is false

paramrajpura commented 8 years ago

@matthewearl Please let me know what are your thoughts about the same....

mazcallu commented 5 years ago

The image is too small or too big in both cases, that is why it is p = 0 in all of them