Summary of Leveraging Deep Learning with Multi-head Attention For Accurate Extraction Of Medicine From Handwritten Prescriptions, by Usman Ali et al.
Leveraging Deep Learning with Multi-Head Attention for Accurate Extraction of Medicine from Handwritten Prescriptions
by Usman Ali, Sahil Ranmbail, Muhammad Nadeem, Hamid Ishfaq, Muhammad Umer Ramzan, Waqas Ali
First submitted to arxiv on: 24 Dec 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Machine Learning (cs.LG); Image and Video Processing (eess.IV)
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 A novel method is presented for extracting medication names from handwritten doctor prescriptions. This method combines Mask R-CNN with Transformer-based Optical Character Recognition (TrOCR) to overcome the challenges of variability in handwriting styles and prescription formats. A dataset of diverse handwritten prescriptions from Pakistan is used to fine-tune the model, allowing it to accurately identify medicinal sections and transcribe text using Multi-Head Attention and Positional Embeddings. The proposed approach achieves a character error rate (CER) of 1.4% on standard benchmarks, making it a reliable and efficient tool for automating medicine name extraction. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about creating a way to extract medication names from handwritten doctor prescriptions. This can be hard because different people write in different ways, and prescriptions are written in different styles too. The method uses two techniques: Mask R-CNN and Transformer-based Optical Character Recognition (TrOCR). The dataset used was made up of many different handwriting styles from Pakistan. This helps the model to learn how to identify medicine names correctly. The new approach can help doctors and hospitals quickly and accurately identify medication names, which is important for giving patients the right treatment. |
Keywords
» Artificial intelligence » Cer » Cnn » Mask » Multi head attention » Transformer
