Ancient Scripts Research Articles

Ancient Epic Manuscript Binarization and Classification Using False Color Spectralization and VGG-16 Model

Ancient Malayalam manuscripts include a vast quantity of materials, much of which pertains to ancient custom and culture. These manuscripts are the foundation of the rich and diverse culture that we possess today. The information extraction from such scripts written in “Thaliyola” or palm leaves would be an extensive and tedious task due to various challenges such as understanding the ancient script, damages generated due to miss-handling, stains and fungus and other environmental factors caused to the palm leaves. Preserving and segregating these documents through binarization and classification is an important task. Classification of these documents will lead to understanding unique ancient documents and preserving them for our current and future generations. In proposed work primarily an RGB image of the palm leaf document is given as input to the Spectral Angle Mapper(SAM) algorithm which takes the input and converts into RGB-A image with an additional Alpha channel, after FCC and TCC is calculated and a spectral image is generated which possess good text readability which is then followed by classification. The spectral model is passed to using VGG-16 model along with other binarized images, after training and testing achieved an accuracy of 90% on Jadakam and an accuracy of 85% with Bhagavatham.

Efficient Scalable Template-Matching Technique for Ancient Brahmi Script營mage

Analysis and recognition of ancient scripts is a challenging task as these scripts are inscribed on pillars, stones, or leaves. Optical recognition systems can help in preserving, sharing, and accelerate the study of the ancient scripts, but lack of standard dataset for such scripts is a major constraint. Although many scholars and researchers have captured and uploaded inscription images on various websites, manual searching, downloading and extraction of these images is tedious and error prone. Web search queries return a vast number of irrelevant results, and manually extracting images for a specific script is not scalable. This paper proposes a novel multistage system to identify the specific set of script images from a large set of images downloaded from web sources. The proposed system combines the two most important pattern matching techniques-Scale Invariant Feature Transform (SIFT) and Template matching, in a sequential pipeline, and by using the key strengths of each technique, the system can discard irrelevant images while retaining a specific type of images.

“Rosetta Stone”: One or More? Examples of Multilingualism Texts and the Deciphering of Ancient Scripts

The decipherment of ancient languages and scripts was a challenging mission for linguists and philologists. There are successful and unsuccessful attempts to decipher ancient and famous languages, of which is the Egyptian hieroglyphs. In 1822, Champollion announced in the Académie des Inscriptions et Belles-Lettres his innovative methodology to read ancient Egyptian hieroglyphs when he could read the three scripts of the Rosetta Stone: Hieroglyphic, Demotic, and Greek. Champollion’s theory is based on finding a multi-script or multi-script text that is used as an aiding tool to read and decipher the required scripts. Thus, this paper sheds fresh light on the role of multilingualism in decoding ancient scripts. It is worth mentioning that the “Rosetta Stone” became an equivalent term of an assistance tool to crack ancient languages and scripts, giving examples of famous texts such as the Behistun Inscription and the manuscript copy of Landa alphabet.

Implementing a Hybrid Deep Learning Approach to Achieve Classic Handwritten Alphanumeric MODI Recognition

MODI, synonymous with the Devanagari script, is an ancient script from the 17th century used by the Maratha empire as a symbol of culture and power to propagate Marathi. Due to a decline in its usage, absence of quality script database and an unavailability of good literature, identification and translation of MODI script is demanding. The present work deals with a novel study on the recognition of MODI characters and numerals by using Convolutional Neural Network (CNN) architecture. By using a traditional machine learning classifier, classification is performed, and then through a comparative analysis of Random Forest and XGBoost, the study achieves recognition accuracy of 92% for characters and 93.3% for numerals.

Unsupervised deep learning supports reclassification of Bronze age cypriot writing system.

Ancient undeciphered scripts present problems of different nature, not just tied to linguistic identification. The undeciphered Cypro-Minoan script from second millennium BCE Cyprus, for instance, currently does not have a standardized, definitive inventory of signs, and, in addition, stands divided into three separate subgroups (CM1, CM2, CM3), which have also been alleged to record different languages. However, this state of the art is not consensually accepted by the experts. In this article, we aim to apply a method that can aid to shed light on the tripartite division, to assess if it holds up against a multi-pronged, multi-disciplinary approach. This involves considerations linked to paleography (shapes of individual signs) and epigraphy (writing style tied to the support used), and crucially, deep learning-based strategies. These automatic methods, which are widely adopted in many fields such as computer vision and computational linguistics, allow us to look from an innovative perspective at the specific issues presented by ancient, poorly understood scripts in general, and Cypro-Minoan in particular. The usage of a state-of-the-art convolutional neural model that is unsupervised, and therefore does not use any prior knowledge of the script, is still underrepresented in the study of undeciphered writing systems, and helps to investigate the tripartite division from a fresh standpoint. The conclusions we reached show that: 1. the use of different media skews to a large extent the uniformity of the sign shapes; 2. the application of several neural techniques confirm this, since they highlight graphic proximity among signs inscribed on similar supports; 3. multi-stranded approaches prove to be a successful tool to investigate ancient scripts whose language is still unidentified. More crucially, these aspects, together, point in the same direction, namely the validation of a unitary, single Cypro-Minoan script, rather than the current division into three subgroups.

Word Transcription of MODI Script to Devanagari Using Deep Neural Network

-Many historical documents and letters are written in MODI script. Study of “Shivakalin” and “Peshvekalin” era documents is almost impossible without the knowledge of MODI script. This work aims to bridge the gap between Devanagari and MODI Script by developing a system to map the recognized MODI characters to its Devanagari equivalent. Our dataset would comprise 57 different classes of MODI Script characters. We has solved the problem of loss of information in CNN as the model goes deeper using Dense Net-121. The various approaches for feature extraction usually used include moment invariant, affine moment invariant, chain code histogram, intersection junction and for character classification. Deep Neural Networks on the other hand do not require any feature to be explicitly defined, instead they work on the raw pixel data to generate the best features and use them to classify the inputs into different classes. Hence, we propose a deep learning architecture for character recognition. Dense Net-121 uses little pre-processing compared to other image classification algorithms. This means that the network learns the filters which in traditional algorithms were hand-engineered. The system aims to provide a good recognition rate by implementing DCNN. Key Words:Siamese Neural Network, CNN, Devanagari, HOCR 1.INTRODUCTION ( Size 11, Times New roman) Modi is an ancient script. Crores of Modi documents. Origin: 12th century and used uptil the 20th century. Modi lipi converter is a low resource solution Many historical documents and letters are written in MODI script. Study of “Shivakalin” and “Peshvekalin” era documents is almost impossible without the knowledge of MODI script. This work aims to bridge the gap between Devanagari and MODI Script by developing a system to map the recognized MODI characters to its Devanagari equivalent, provides authors with most of the formatting specifications needed for preparing electronic versions of their papers. All standard paper components have been specified for three reasons: (1) ease of use when formatting individual papers, (2) automatic compliance to electronic requirements that facilitate the concurrent or later production of electronic products, and (3) conformity of style throughout a conference proceedings. Margins, column widths, line spacing, and type styles are built-in; examples of the type styles are provided throughout this document and are identified in italic type, within parentheses, following the example. Some components, suchas multi-leveled equations, graphics, and tables are notprescribed, although the various table text styles are provided. The formatter will need to create these components, incorporating the applicable criteria that follow.

Implementation of Incung Script Learning as a Form of Local Wisdom-Based Curriculum Development at SD Negeri 046/XI Koto Tengah

The incung script is an ancient script used by the indigenous Kerinci tribe as a medium of communication written on logs/bark, buffalo horns and palm leaves. The implementation of the incung script as a curriculum development based on local wisdom is an image of the community to continue to preserve culture in the form of education. The purpose of this study is to see how the process of implementing the incung script is a form of local wisdom-based curriculum development at SD Negeri 046/XI Koto Tengah. This study uses a qualitative research method with a descriptive approach to show how the implementation of the incung script in education. The result of the study shows that the implementation of the incung script as a form of local wisdom-based curriculum development goes through seven stages including: feasibility and needs study stage

PUNet: Novel and efficient deep neural network architecture for handwritten documents word spotting

Ancient scripts, documents and photos are valuable supports that opened a window to humanity’s past, its social and cultural treasure. However, due to the inevitable deterioration, seeking information in these documents remains a key challenge. Word Spotting remains an attractive alternative to Optical Character Recognition systems for information retrieval, especially in the case of old documents. The quantity of research work on this particular topic continues growing by extracting relevant words as an alternative method of recognizing text content. Here, we propose a new robust Deep Learning based framework for data exploration of ancient documents by applying Transfer Learning from the U-Net Network and using recent Pyramidal Histogram of Character Encryption: no special preprocessing or Data augmentation optimizers are required. Experimental results reveal its accuracy and high capacity to well classify words of various handwritten datasets.

The Development and Role of Symmetry in Ancient Scripts

This paper investigates various scripts regarding the occurrences of signs that have mir- ror symmetry along a central vertical line. The scripts belong to one of the following three script families: the Phoenician script family, the Minoan-Mycenaean script family, and the Indus Valley script family. It is shown that many scripts in these script families contain a high percentage of signs that have mirror symmetry. Moreover, the scripts within the Phoenician and the Minoan- Mycenaean script families show a tendency of increased percentage of mirror-symmetric signs over time. For example, while the Phoenician Alphabet contains 40.9 percent mirror-symmetric signs, one of its descendants, the Euclidean Greek Alphabet, contains 59.3 percent mirror-symmetric signs. The paper also identifies the boustrophedonic way of writing and religious writings with a deliberate mirroring as an afterlife symbolism as possible causes of the increased use of mirror- symmetric signs.

『說文』省聲⋅省形字의 재구조— 戰國 出土文獻의 몇 가지 예를 근거로

This study checks the classification contents of the generated organisms in “shuowen” through an advisor by referring to the classification of existing studies on the generated organisms, and analyzes the spherical cause. Abbreviated significand abbreviated phonetic is an additional analysis method other than the “six principles theory of Chinese script” system used as “從某, 從某省” of syssemantograph or “從某省, 某聲” of phonogram in the “shuowen” system. Existing researchers analyzed the attribution and assistant process of the creator or of “shuowen” according to their respective criteria. They also summarized examples of analysis based on ancient script form but as literature from the National Era was excavated, a new basis for estimating the process of shape change was prepared. Therefore, this study also believes that additional analysis of abbreviated significand abbreviated phoneticis necessary, and examines the graphic component relationship of abbreviated significand abbreviated phonetic through text analysis in the national era, and further examines the cause of formation of abbreviated significand abbreviated phoneticis. This study analyzed through national text using actual examples in Chapter 3. It can be seen that most of the letters that attempted to be analyzed as “abbreviated significand abbreviated phonetic” reflect phenomena such as “modified tone” and “apperception”, which are spherical features of the “Paleography stage”, and several meanings can be found below. First, when “abbreviated significand abbreviated phonetic” misrepresented the letter, it was found that the original meaning and interior of the letter were unknown mainly due to “corruption” and “consolidation” of the letter. Second, the letters interpreted as “abbreviated significand abbreviated phonetic” could be analyzed in different coined and spherical methods for each era. This was able to confirm the process of the at the ancent characters stage. Third, when the classification of unilateral among the abbreviated significand abbreviated phoneticis characters was incorrectly induced, the shape of the unilateral unit as well as the graphic unit mainly played a central role in form-meaning, reflecting the derivational method and the organization method.

A CROSS-SECTIONAL STUDY ON BODY CONSTITUTION (DHEGA ILAKKANAM) IN UTHIRAVATHA SURONITHAM (RHEUMATOID ARTHRITIS)

Background: Siddha medicine is an ancient script of medicine has been originated in South India. The concept of the Siddha system is based on fundamental principles of 96 thathuvangal which include five basic elements of the Universe, Udal thadhugal, and Uyir thadhugal etc. The physical health of the human body is maintained by three humors vathm, pitham, kabam which are the basic vital forces of humans. Udaliyal assessment is an essential tool, to diagnose any variation in the three vital forces. This study was to evaluate the body constitution in Uthiravatha Suronitham (Rheumatoid arthritis). This study was conducted in the outpatient department maruthuvam, Ayothidoss pandithar hospital, National Institute of Siddha, Chennai. 50 Uthiravatha Suronitham patients were selected to analyze the body constitution of Uthiravatha suronitham disease. The study details were collected by using the questionnaire in the data collection questionnaire. vathakaba thegi and vathapitha thegi body constitutions were more prone to Uthiravatha suronitham disease. The traits of thega illakanam, can be used for the line of treatment to the Uthiravatha suronitham patients along with dietary habits, behavioural modifications. etc.

Panini’s Astadhyayi in the Eyes of Plant Invasion on Indian Subcontinent

Indigenous plantlore is a manifestation in a given community, based on adaptation and wisdom of local people and environment. It develops over times and continues so also. This treasure of traditional knowledge is used to sustain the community and its bioculture. In long past, people of great understanding, christalized their wisdom in some treatises such as the Panini’s Astadhyayi. This treatise is understood and well known for the genesis and development of Sanskrit knowledge. Ancient Sanskrit scripts usually contain information concerning culture and sustenance based on plant world. The present author analysed it in view of plant invasion on Indian landmass in Panini’s time. Total 45 exotic plant species belonging to 44 genera and 29 angiospermic families are divulged from it. These belong to nearly all corners of the Old and New Worlds. Majority of them (28 species) are cultigens and still continue even in modern period in India. Of course, rest of them are wild, naturalised and presently constitute integral part of Indian biodiversity. The importance of such ancient treatises is dilated in this communication.

Pengenalan Pola Tulisan Tangan Aksara Bima menggunakan Ciri Tekstur dan KNN

As the fact, that is Bima script did not familiar to bimanese, Bima script as a cultural heritage needs to be preserved. Pattern recognition has been used to recognize several of ancient script. Gray Level Co-occurence Matrix (GLCM) as features exctraction and K Nearest Neighbour (KNN) as a classifier show the good performance to recognize of an ancient script. so, in this research we use GLCM and KNN to recognize Bima script. we use 2640 images of handwritting bima Script that is collected from 10 volunter. Each volunter write 22 of Bima script twelve times each script. The experimental result show that the performance of our model is good enough, with 60.86% of accuracy that is obtained by manhattan distances.

TAMIZHİ: Historical Tamil-Brahmi Script Recognition Using CNN and MobileNet

Computational epigraphy is the study of an ancient script where the computer science and mathematical model is relatively built for epigraphy. The Tamil-Brahmi inscriptions are the most ancient of the extant written of the Tamil. The inscriptions furnish valuable information on many aspects of life in the ancient Tamil country from a period anterior to the literary age of Sangam. The recognition of the script and systematic analysis of the script is required. The recognition of this script is complex, containing various curves for a single character and the style of writing overlap with curves and lines. Generating corpus of the script is necessary, since it is the initial step for computational epigraphy. The archaeological department has supported the raw data that helped to develop a corpus of Tamizhi. In this article, we have implemented a convolution neural network in various ways, i.e., (i) Training the CNN model from scratch a Softmax classifier in a sequential model (ii) using MobileNet: Transfer learning paradigm from a pre-trained model on a Tamizhi dataset (iii) Building Model with CNN and SVM (iv) SVM for evaluation of best accuracy to recognize handwritten Brahmi characters. To train the CNN Model an extensive TAMIZHİ handwritten Brahmi Dataset of 1lakh and 90,000 isolated samples for the character has been created and deployed. The designed dataset consists of 9 vowels and 18 consonants and 209 class so researchers can use machine learning. MobileNet outperformed among all the models implemented with the accuracy of 68.3%, whereas other algorithm ranges from 58% to 67% with respect to the Tamizhi dataset. MobileNet model is trained and tested for the dataset of vowels (8 class), consonants (18 class), and consonants vowels (26 class) with the accuracy of 98.1%, 97.7%, 97.5%, respectively.

Handwritten MODI Character Recognition Using Transfer Learning with Discriminant Feature Analysis

“MODI lipi” is one of the ancient scripts of Western India. Considerable work has been reported for various other ancient Indian languages except for MODI lipi. Its structural characteristics and non-availability of image database make MODI recognition challenging. The work reported in this paper comprises the creation of an image dataset for MODI handwritten characters and the development of a supervised Transfer Learning (TL)-based classification framework. It makes use of Deep Convolutional Neural Network (DCNN) Alexnet as a pre-trained network to transfer weights to retrain the network. This network is used as a feature extractor to extract features from different layers of the network. A Support Vector Machine (SVM) is trained on activation features to obtain classifier models. These models are investigated further for recognition accuracy and feature analysis. Subjective and objective measures are used to select discriminant deep features. We achieved recognition accuracies of 92.32% and 97.25% for Handwritten MODI character recognition and handwritten Devnagari character recognition, respectively.

A method of identifying allographs in undeciphered scripts and its application to the Indus Valley Script

This work describes a general method of testing for redundancies in the sign lists of ancient scripts by data mining the positions of the signs within the inscriptions. The redundant signs are allographs of the same grapheme. The method is applied to the undeciphered Indus Valley Script, which stands out from other ancient scripts by having a large proposed sign list that contains dozens of asymmetric signs that have mirrored pairs. By a statistical analysis of mirrored asymmetric signs, this paper shows that the Indus Valley Script was multi-directional and the mirroring of signs often denotes only the direction of writing without any difference in meaning. For this and five other specific reasons listed in the paper, 50 pairs of signs, 23 mirrored, and 27 non-mirrored, can be grouped together because each pair consists of only insignificant variations of the same original sign. The reduced sign list may make decipherment easier in the future.

Deciphering Undersegmented Ancient Scripts Using Phonetic Prior

Most undeciphered lost languages exhibit two characteristics that pose significant decipherment challenges: (1) the scripts are not fully segmented into words; (2) the closest known language is not determined. We propose a decipherment model that handles both of these challenges by building on rich linguistic constraints reflecting consistent patterns in historical sound change. We capture the natural phonological geometry by learning character embeddings based on the International Phonetic Alphabet (IPA). The resulting generative framework jointly models word segmentation and cognate alignment, informed by phonological constraints. We evaluate the model on both deciphered languages (Gothic, Ugaritic) and an undeciphered one (Iberian). The experiments show that incorporating phonetic geometry leads to clear and consistent gains. Additionally, we propose a measure for language closeness which correctly identifies related languages for Gothic and Ugaritic. For Iberian, the method does not show strong evidence supporting Basque as a related language, concurring with the favored position by the current scholarship. 1

Assessment of the Role of Environmental factors and Associated Plants for the Mass Cultivation of Santalum album L in Nepal and India

Sandalwood (White Sandal) is the fragrant heartwood of some species of genus Santalum. The widely distributed and economically important Santalum genus belongs to the family Santalaceae which includes 30 genera with about 400 species, many of which being completely or partially parasitic (John, 1947). The word Sandal has been derived from Chandana (Sanskrit), Chandan (Persian), Savtador (Greek) and Santal (French). There are references of Sandalwood in Indian mythology, folklore and ancient scripts. ‘Chandana’ the Sanskrit name ascribed to Santalum album L. was known and used in India from the earliest historic times and is frequently mentioned in the ancient Sanskrit writings, some of which dated before Christian era. Kautilya’s Arthashastra (320 B.C.) considered Sandal as one of the important forest products to increase royal revenue. Charaka Sanhitha, the major text book of internal medicine in Ayurveda (300 B.C.) quotes uses of Sandal over 160 time in the entire text. In treatment of major diseases like fever, piles, hemorrhagic conditions, diabetes, dropsy, mental disorders, management of poisons & skin disorders wide spread uses of sandal is seen. Susrutha Samhita (150 B.C.) a great text on Indian wisdom on surgical procedures, equally preferred sandal for the management of wounds. Sandal fumigation is indicated in warding off evils and organisms, which contaminate the wounds. Such fumigations hasten the wound healing & surgical wards remain aseptic. Dusting of wounds with sandal for early healing is common. In the Amarkosha (Lexicon 3rd or 4th Century A.D.) sandal is mentioned and it is said that ‘Vina-malayam anyathra chandanam vivarditha’

Transliterating Nôm Scripts into Vietnamese National Scripts using Statistical Machine Translation

Nôm scripts were used as the Vietnamese writing system from the 10th century to the early 20th century. During this period, Nôm scripts were the means to record a broad range of historical events, literary works, medical knowledge, as well as wisdom of many other domains. Unfortunately, since hardly any native Vietnamese speaker can read Nôm scripts nowadays, these valuable documents have not been fully harnessed. To address this gap, it is necessary to build an automatic transliteration system that can support us in decoding the ancient scripts and gaining knowledge of our Vietnamese ancestors. This study focuses on categorizing and reviewing the current progress on the Statistical Machine Translation (SMT) approaches to transliterate Nôm scripts into Vietnamese national scripts. In this paper, we discuss the differences between Nôm scripts and Vietnamese national scripts, systematically compare SMT models in transliterating Nôm scripts into Vietnamese national scripts, as well as having a thorough outlook on several promising research directions.

Experiential Realization in "Poda Ni Namonangon Ribut" on Mandailing Social Context

This study aims to analyze the function and realization of the meaning contained in the Poda ni Namonangon Ribut as an ancient script text contained in the Ulu Pungkut sub-district, Mandailing Natal district. This study uses a qualitative method with the documentation method in which the data is sourced from the Medan Archeology Agency. Data were analyzed using Systemic Functional Linguistics theory on Ideational Functions and to find metaphors of ideational meaning. The results of this study indicate the distribution of the relational process dominates from Participant, Cirmuntance. The realization of the meaning of the ideational function can be seen in the first, metaphor as a description of the community who want to have offspring, where the aim of Poda is ido napajadi boru "what makes a daughter". In the second, there is a metaphor that explains the word Na sundat realized with the words "Heavy Rain", "Divorce", "Birds perch", "ravine". In the third, shows that Poda has methafora like when the expectation is reached, it is the services of the writer "Shaman”. then when the writer has explained what the ingredients are. Social context of text that has a narrative and the author's conclusion about the solution to the problem of everyone who wants offspring in his family. The tradition of writing with the mandailing script (sumurat) became quite a tradition so that there are ancient texts in the traditional house became the animist beliefs and ideologies which can be seen in Bagas Godang.