You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: README.md
+5-3Lines changed: 5 additions & 3 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -37,7 +37,7 @@ Use Convolutional Recurrent Neural Network to recognize the Handwritten line tex
37
37
* Only needed the lines images and lines.txt (ASCII).
38
38
* Place the downloaded files inside data directory
39
39
40
-
###### The Trained model is not available right now. You can trained it by yourself.
40
+
###### The Trained model is available and download from this [link](https://drive.google.com/file/d/10HHNZPqPQZCQCLrKGQOq5E7zFW5wGcA4/view?usp=sharing). The trained model CER=8.32% and trained on IAM dataset with some additional created dataset.
41
41
42
42
43
43
To Train the model from scratch
@@ -71,8 +71,10 @@ With Correction clothed leaf by leaf with the dioappoistmest
71
71
![PredictionOutput](images/PredictionOutput.png?raw=true"Prediction Output on Self Data")
72
72
73
73
# Further Improvement
74
-
* Line segementation can be added for full paragraph text recognition.
74
+
* Line segementation can be added for full paragraph text recognition. For line segmentation you can use A* path planning algorithm or CNN model to seperate paragraph into lines.
75
75
* Better Image preprocessing such as: reduce backgoround noise to handle real time image more accurately.
76
76
* Better Decoding approach to improve accuracy. Some of the CTC Decoder found [here](https://github.com/githubharald/CTCDecoder)
77
77
78
-
*This is part of my last semester project of Computer Science Program From Tribhuvan University. July 2019*
78
+
Feel Free to improve this project with pull Request.
79
+
80
+
*This is part of my last semester project of Computer Engineering From Tribhuvan University. July 2019*
0 commit comments