Summary of Towards Accessible Learning: Deep Learning-based Potential Dysgraphia Detection and Ocr For Potentially Dysgraphic Handwriting, by Vydeki D et al.
Towards Accessible Learning: Deep Learning-Based Potential Dysgraphia Detection and OCR for Potentially Dysgraphic Handwriting
by Vydeki D, Divyansh Bhandari, Pranav Pratap Patil, Aarush Anand Kulkarni
First submitted to arxiv on: 18 Nov 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Machine Learning (cs.LG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This study leverages deep learning techniques to develop a custom Convolutional Neural Network (CNN) model that accurately detects dysgraphia in children’s handwriting samples. The researchers utilized a dataset of handwritten samples from Malaysian schoolchildren to train their custom CNN model, which outperformed pre-trained models VGG16 and ResNet50 with a test accuracy of 91.8%. The study also implemented an optical character recognition (OCR) pipeline to segment and recognize individual characters in dysgraphic handwriting, achieving an accuracy of approximately 43.5%. This research contributes to the development of assistive technologies for learning disabilities, offering potential diagnostic tools for educators and clinicians. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This study uses computer science to help detect a condition called dysgraphia that makes it hard for kids to write neatly. The researchers created a special kind of computer program that can look at handwriting samples and figure out if they belong to a kid with dysgraphia. They tested this program on a bunch of handwriting samples from Malaysian schoolkids and found that it worked really well! They also made another tool that can read the individual letters in the kids’ handwriting, which is important for understanding how these kids are doing over time. This research could lead to better tools for teachers and doctors to help kids with dysgraphia. |
Keywords
» Artificial intelligence » Cnn » Deep learning » Neural network
