Closed naveen-marthala closed 4 years ago
Hi Naveen, it seems like your dataset does not fit the IAM dataset very well. You may have to finetune the network to your dataset. This includes labelling a few images and similar to the IAM specifications.
Thanks. So, you are telling me that I should train the network again with my images and labels. Yes?
You could use use the weights in the pretrained network provided then retrain it with your own images.
Please take a look at https://gluon.mxnet.io/chapter08_computer-vision/fine-tuning.html for more details.
Here is my input image in color:
1. The detection that happended from pre-trained models can be seen below, when the above image is converted from 0. RGB to grayscale and 1. BGR to grayscale (happended at
2. Because of this improper region detection, areas that actually has text are being cropped out.
And, when i try form size other than what is in the code(because my images have smaller aspect ratio), that is
and here's the line segmentation:
How do i fix these?
paragraph segmentation
from '0_handwriting_ocr.ipynb' notebook & I have made no changes in the code from that notebook):form_size = (1120, 800)
, computer crashes. What is causing this and how can i not have this happen? 3. Presumably, because of the above improper detection or may be becuaseline/word segmentaion
not happening properly, here's the word segmentation: