In this project, we primarily introduced an algorithm that recognizes Baybayin scripts at word level. This work relies to the method proposed in (1) where some MATLAB codes/functions in (2) have been modified to achieve the purpose of the project. That is, classification and recognition of the Baybayin word applies at the character level where we concatenate each character's recognition result to form the corresponding Latin word. We tested the system with the dataset provided in (3) and obtained an impressive recognition accuracy. We also discuss the strengths and limitations of the system, and recommendations for further research.
The complete system files can be downloaded below with filename A.Baybayin.Word.Recognition.System.zip.
Links cited:
(1) https://peerj.com/articles/cs-360/
(2) https://github.com/rbp0803/An-OCR-System-for-Baybayin-Scripts-using-SVM
(3) https://www.kaggle.com/rodneypino/baybayin-word-images?select=Baybayin+Word+Images