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.

This paper presents the results of the Competition on the Analysis of Handwritten Text in Images of Balinese Palm Leaf Manuscripts that was organized in the context of the 15th International Conference on Frontiers in Handwriting Recognition (ICFHR-2016). This competition provides a suitable challenge for testing and evaluation of robustness for some methods, image features and descriptors which were already proposed for handwritten text analysis of document image. In this competition, three different challenges in document analysis of palm leaf manuscript images are proposed: Challenge 1: Binarization of Palm Leaf Manuscript Images, Challenge 2: Query-by-Example Word Spotting on Palm Leaf Manuscript Images, and Challenge 3: Isolated Character Recognition of Balinese Script in Palm Leaf Manuscript Images. The first handwritten Balinese palm leaf manuscript dataset, the AMADI_LontarSet, is used for performance evaluation. This paper describes the competition details including the dataset creation and the ground truth construction, the evaluation measures used, a short description of each participant as well as the performance of the all submitted methods.

We present the AMADI_LontarSet, the first handwritten Balinese palm leaf manuscript dataset. It includes three components of dataset as follows: binarized images ground truth dataset, word annotated images dataset, and isolated character annotated images dataset. The dataset was constructed from a hundred pages of randomly selected collections of palm leaf manuscripts from Bali, Indonesia. The dataset is publicly available for scientific use.

Most of text line and character segmentation methods for handwritten document image basically still depend on the binary image of the document. Unfortunately, for palm leaf manuscript images, the binarization process is a real challenge. We proposed a new binarization free scheme for text line and character segmentation for palm leaf manuscript images. Our scheme consists of 4 sub-tasks: brushing character area of gray level images with minimum filtering, average block projection profile of gray level images, selection of candidate area for segmentation path, and construction of nonlinear segmentation path. For evaluation, we compared our method with the shredding method which is applied in three different schemes of experiment. The experimental results showed that the proposed method performed optimal on the palm leaf manuscript images which contain discolored parts, with low intensity variations or poor contrast, random noises, and fading.

Ancient palm leaf manuscripts are one of the very valuable cultural heritages that store various forms of knowledge and historical records of social life in Southeast Asia. The automatic analysis of these documents, in order to extract relevant information, is a real challenge. However, to evaluate the developed extraction algorithms, a ground truth is absolutely necessary. In this paper, we present some of the challenges of the state of the art binarization methods as an initial study for the construction of ground truth binarized images of palm leaf manuscripts. We propose and analyze the need for a specific scheme for the construction of the ground truth of binarized images. The aim of this scheme is to achieve a better ground truth for low quality palm leaf manuscripts. We experimentally tested and evaluated our proposed specific scheme and got promising results. This scheme adapts and performs better in constructing the ground truth of binarized images for palm leaf manuscripts.

Due to their specific characteristics, palm leaf manuscripts provide new challenges for text line segmentation tasks in document analysis. We investigated the performance of six text line segmentation methods by conducting comparative experimental studies for the collection of palm leaf manuscript images. The image corpus used in this study comes from the sample images of palm leaf manuscripts of three different Southeast Asian scripts: Balinese script from Bali and Sundanese script from West Java, both from Indonesia, and Khmer script from Cambodia. For the experiments, four text line segmentation methods that work on binary images are tested: the adaptive partial projection line segmentation approach, the A* path planning approach, the shredding method, and our proposed energy function for shredding method. Two other methods that can be directly applied on grayscale images are also investigated: the adaptive local connectivity map method and the seam carving-based method. The evaluation criteria and tool provided by ICDAR2013 Handwriting Segmentation Contest were used in this experiment.