Erick Paulus

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

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.

Southeast Asian palm leaf manuscript images: a review of handwritten text line segmentation methods and new challenges

Abstract. 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.

Combining Fuzzy Clustering and Hidden Markov Models for Sundanese Speech Recognition

Sundanese tribe is one of the largest population tribe in Indonesia. However, over time, users of the Sundanese language are declining because of the living languages outside of Sundanese. One way to preserve Sundanese is Sundanese Speech Recognition. In this research, several processes of recognition were done include pre-processing, feature extraction, Fuzzy Clustering, and Hidden Markov Models. Pre-processing aims to separate the recording from the noise and normalize the speech signal, while the feature extraction to obtain the characteristics of the speech signal to distinguish each phoneme from the speech. In particular, the contribution of this research is to combine Fuzzy Clustering and Hidden Markov Models for Sundanese Speech Recognition. Fuzzy Clustering plays a role in finding unique symbols in the speech signal. These symbols are represented as centroid in fuzzy clustering. The next process, each segment of the speech signal calculated the probability of the membership for all centroids. The output of this calculation becomes input to Hidden Markov Models. The test uses a speech corpus derived from 30 people. The results obtained that the combination of Fuzzy Clustering and Hidden Markov Models have a better performance than Hidden Markov Models. Also, the research also analyses the optimal number of clusters of Fuzzy Clustering and states of Hidden Markov Models for the datasets used.

Improved Line Segmentation Framework for Sundanese Old Manuscripts

Line segmentation can be a useful process for further text segmentation. There are some certain line segmentation framework that use binarization method as an initial step. But binarization process is still facing a major challenge, especially on old document palm-leaf manuscripts. As the quality of the image has varying degrees of noises in the non-text region. Seam Carving method, one of line segmentation methods that uses binarization-free approach, can be an alternative solution. However, this method can separate the incorrect text line on small element text located at the bottom or at the top of a main character contour. Therefore, an improvement on line segmentation framework is proposed by using hybrid binarization and its implemented on the smallest energy function to separate out the text-lines. The proposed framework have been evaluated on 44 Sundanese old manuscript images that consist of true color and binary images. The evaluation matrix shows that this framework can improve Niblack binarization process up to 50%. In addition, our framework does not only generate the number of text-lines to come near to the number of target lines, but it also can separate the text-lines well on small element text. Overall, the expected result can in the end be produced from the proposed line segmentation framework.

EVALUASI APLIKASI SEMI-IMMERSIVE VIRTUAL REALITY PADA BIDANG PENDIDIKAN MENURUT ASPEK HEURISTIK DAN PEMBELAJARAN

Makalah ini memaparkan percobaan evaluasi komprehensif terhadap aplikasi virtual reality (VR) bertipe semi-immersive dari sisi heuristik disain antarmuka aplikasi, peningkatan kemampuan kognitif, dan peningkatan motivasi belajar ketika aplikasi digunakan dalam proses pembelajaran. Evaluasi terhadap disain antarmuka VR ini menggunakan metode heuristik yang diusulkan oleh Sutcliffe, yaitu sebanyak dua belas prinsip. Selain faktor usabilitas, evaluasi heuristik ini mampu memberikan panduan evaluasi dengan memperhitungkan faktor keberadaan pengguna ketika berada dalam lingkungan maya. Hasil proses inspeksi evaluasi heuristik ini adalah penggabungan nilai evaluasi dari tiga orang penilai. Hasil evaluasi menunjukan bahwa secara heuristik aplikasi BIOTALAUT VR sudah merepresentasikan kondisi lingkungan bawah laut dengan baik. Namun ada beberapa fitur disain yang perlu diperbaiki, yaitu interaksi antar objek, grafik objek 3D biota dan fungsi kontrol. Sedangkan, proses evaluasi dari segi peningkatan kemampuan kognitif diimplementasikan pada 30 siswa tingkat sekolah menengah pertama melalui kegiatan pretes dan postes kemudian dianalisa secara statistik. Selain pretes dan postes, siswa juga mengisi kuisioner untuk mengetahui tingkat motivasi belajar setelah menggunakan aplikasi. Kemudian, setelah aplikasi digunakan pada proses pembelajaran, terdapat perbedaan kemampuan kognitif yang signifikan ke arah positif dengan nilai sig-value sebesar 0.448 dan peningkatan motivasi dilihat dari nilai rata-rata central tendency sebesar 4.49. Adapun hasil evaluasi ini dapat digunakan sebagai bahan pertimbangan dalam pengembangan aplikasi selanjutnya khususnya dari sudut pandang disain antarmuka aplikasi maupun dari konteks pembelajarannya. Selain itu, kejadian munculnya gejala cybersickness pada pengguna juga ditelaah dan dilaporkan dalam penelitian ini. Adapun posisi gerakan pengguna saat menjalankan aplikasi VR dan perangkat keras yang dipakai menjadi aspek utama yang menyebabkan cybersickness tersebut. Kata Kunci: cybersickness, evaluasi usabilitas heuristik, , kemampuan kognitif, motivasi belajar, virtual reality