Optical character recognition system for Baybayin scripts using support vector machine

Abstract

In 2018, the Philippine Congress signed House Bill 1022 declaring the Baybayin script as the Philippines’ national writing system. In this regard, it is highly probable that the Baybayin and Latin scripts would appear in a single document. In this work, we propose a system that discriminates the characters of both scripts. The proposed system considers the normalization of an individual character to identify if it belongs to Baybayin or Latin script and further classify them as to what unit they represent. This gives us four classification problems, namely: (1) Baybayin and Latin script recognition, (2) Baybayin character classification, (3) Latin character classification, and (4) Baybayin diacritical marks classification. To the best of our knowledge, this is the first study that makes use of Support Vector Machine (SVM) for Baybayin script recognition. This work also provides a new dataset for Baybayin, its diacritics, and Latin characters. Classification problems (1) and (4) use binary SVM while (2) and (3) apply the multiclass SVM classification. On average, our numerical experiments yield satisfactory results: (1) has 98.5% accuracy, 98.5% precision, 98.49% recall, and 98.5% F1 Score; (2) has 96.51% accuracy, 95.62% precision, 95.61% recall, and 95.62% F1 Score; (3) has 95.8% accuracy, 95.85% precision, 95.8% recall, and 95.83% F1 Score; and (4) has 100% accuracy, 100% precision, 100% recall, and 100% F1 Score.

A Baybayin word recognition system

“…To the best of our knowledge, the proposed system is the first of its kind for recognizing Baybayin scripts at word level. The system relies heavily on previous work on Baybayin character recognition Pino, Mendoza & Sambayan (2021). The method is tested on a novel dataset found in Pino (2021a), where Full-size DOI: 10.7717/peerjcs.596/fig- 11 it contains 1000 Baybayin word images and yielded a competitive recognition accuracy of 97.9%.…”

“…The last assumption is to guarantee that the characters in the Baybayin word will be correctly extracted. Full-size DOI: 10.7717/peerjcs.596/fig- 3 The classification process in the proposed algorithm relies on the two SVM classifiers generated in Pino, Mendoza & Sambayan (2021), namely, Baybayin characters classifier and the Baybayin diacritic classifier. SVM is one of the well-known classification algorithms in supervised machine learning.…”

“…In Pino, Mendoza & Sambayan (2021), a Baybayin character recognition system has been proposed using SVM, which is a classification algorithm with extensive applications in data categorization (Bishop, 2006). SVM has attracted researchers because of its robustness and high recognition accuracy (Thomé, 2012).…”

“…Applications of SVM can be found in various fields of science and engineering ( Thomé, 2012 ; Sapankevych & Sankar, 2009 ; Nayak, Naik & Behera, 2015 ; Yang, 2004 ; Rivero, Lemence & Kato, 2017 ; Rivero & Kato, 2018 ; Do & Le, 2019 ; Le et al, 2019 ; Le, 2019 ; Byun & Lee, 2003 ). The OCR system proposed by Pino, Mendoza & Sambayan (2021) consists of four SVM classification models, all of which have recognition rates above 96% accuracy.…”

“…The Baybayin word recognition algorithm proposed in this study relies heavily on the OCR system proposed in Pino, Mendoza & Sambayan (2021) . For brevity, we will refer to this method as the SVM-OCR system.…”