Benchmarking of Document Image Analysis Tasks for Palm Leaf Manuscripts from Southeast Asia

TLDR

The dataset comprises palm leaf manuscripts in three scripts—Khmer, Balinese, and Sundanese—representing diverse Southeast Asian writing systems. The study aims to benchmark the principal document image analysis tasks—binarization, text line segmentation, character/glyph recognition, word recognition, and transliteration—on this challenging manuscript collection. Using a complete dataset of Southeast Asian palm leaf manuscripts, the authors evaluated state‑of‑the‑art binarization techniques, seam‑carving and new segmentation methods, handcrafted, unsupervised neural, and CNN‑based character recognition, and RNN‑LSTM models for word recognition and transliteration. The experiments yield quantitative benchmarks that establish the current performance limits for palm leaf manuscript analysis in the DIA community.

Abstract

This paper presents a comprehensive test of the principal tasks in document image analysis (DIA), starting with binarization, text line segmentation, and isolated character/glyph recognition, and continuing on to word recognition and transliteration for a new and challenging collection of palm leaf manuscripts from Southeast Asia. This research presents and is performed on a complete dataset collection of Southeast Asian palm leaf manuscripts. It contains three different scripts: Khmer script from Cambodia, and Balinese script and Sundanese script from Indonesia. The binarization task is evaluated on many methods up to the latest in some binarization competitions. The seam carving method is evaluated for the text line segmentation task, compared to a recently new text line segmentation method for palm leaf manuscripts. For the isolated character/glyph recognition task, the evaluation is reported from the handcrafted feature extraction method, the neural network with unsupervised learning feature, and the Convolutional Neural Network (CNN) based method. Finally, the Recurrent Neural Network-Long Short-Term Memory (RNN-LSTM) based method is used to analyze the word recognition and transliteration task for the palm leaf manuscripts. The results from all experiments provide the latest findings and a quantitative benchmark for palm leaf manuscripts analysis for researchers in the DIA community.