shanky1947/Paper-Evaluation-using-AI
It is able to recognize handwritten text, uses IAM dataset for training. CNN and RCNN architectures are used for training and CTC are used to calculate the loss.
This project helps educators quickly grade handwritten exams with descriptive answers. You provide scanned images of student answer sheets and a set of sample keywords or phrases, and the system uses AI to recognize the handwriting, compare it to your samples, and assign a score. This tool is ideal for teachers, professors, or anyone who regularly evaluates handwritten tests.
No commits in the last 6 months.
Use this if you need to automate the grading of handwritten, descriptive answers on tests, saving significant time and ensuring consistent evaluation.
Not ideal if your assessments involve multiple-choice questions, require nuanced human interpretation beyond keyword matching, or only deal with typed submissions.
Stars
12
Forks
3
Language
Jupyter Notebook
License
—
Category
Last pushed
Aug 31, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/shanky1947/Paper-Evaluation-using-AI"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
ilivans/tf-rnn-attention
Tensorflow implementation of attention mechanism for text classification tasks.
carpedm20/lstm-char-cnn-tensorflow
in progress
ahmedbesbes/character-based-cnn
Implementation of character based convolutional neural network
AlexGidiotis/Document-Classifier-LSTM
A bidirectional LSTM with attention for multiclass/multilabel text classification.
NonvolatileMemory/AAAI_2019_EXAM
Official implementation of "Explicit Interaction Model towards Text Classification"