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

Journal of Imaging

Setiawan Hadi¹  Mira Suryani¹  Erick Paulus¹  Sophea Chhun²  Dona Valy³  Made Windu Antara Kesiman⁴  Jean-Marc Ogier⁴  Jean-Christophe Burie⁴  Michel Verleysen⁵ 

[1] Department of Computer Science, Universitas Padjadjaran, Bandung 45363, Indonesia;Department of Information and Communication Engineering, Institute of Technology of Cambodia, Phnom Penh, Cambodia;Institute of Information and Communication Technologies, Electronic, and Applied Mathematics (ICTEAM), Université Catholique de Louvain, 1348 Louvain-la-Neuve, Belgium;Laboratoire Informatique Image Interaction (L3i), Université de La Rochelle, 17042 La Rochelle, France;Laboratory of Cultural Informatics (LCI), Universitas Pendidikan Ganesha, Singaraja, Bali 81116, Indonesia;

关键词: document image analysis;    binarization;    character recognition;    text line segmentation;    word recognition;    transliteration;    palm leaf manuscript;    dataset;    benchmark;    experimental test;   

DOI  :  10.3390/jimaging4020043

来源: DOAJ

【 摘 要 】

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.

【 授权许可】

Unknown