Ancient Scripts Research Articles

Ancient Yi Script Handwriting Sample Repository

The ancient Yi script has been used for over 8000 years, which can be ranked with Oracle,Sumerian,Egyptian,Mayan and Harappan,and is one of the six ancient scripts in the world. In this article, we collected 2922 handwritten single word samples of commonly used ancient Yi characters. Each character was written by 310 people respectively, with a total of 427,939 valid characters. We completed continuous handwritten text sampling, written by 250 people, with 5 texts per person, covering topics such as Yi astronomy, geography, rituals, and agriculture. In the process of data collection, we proposed an automatic sampling method for ancient Yi script, and completed the automatic cutting and labeling of handwritten samples. Furthermore, we tested the recognition performance of the sorted data set under different deep learning network models. The results show that ancient Yi script has diverse shape structures and rich writing styles, which can be used as a benchmark data set in related fields such as handwritten text recognition and handwritten text generation.

Retraction Note: A hybrid group search optimization: firefly algorithm-based big data framework for ancient script recognition

Retraction Note: A hybrid group search optimization: firefly algorithm-based big data framework for ancient script recognition

Deep learning for ancient scripts recognition: A CapsNet-LSTM based approach

Efficient character recognition in ancient handwritten Devanagari documents is crucial for societal advancements. Challenges such as overlapping characters, missing headlines, and over-inked stains further complicate the recognition process. In response, we propose a Capsule Network (CapsNet) with LSTM to address hierarchical temporal dependencies in Devanagari scripts, following initial implementation of a simple CNN. We also explored a combined CNN+LSTM architecture for character recognition, leveraging CNN’s feature extraction capabilities with LSTM’s sequential modeling to handle temporal dependencies in Devanagari scripts. Our experimentation involved a dataset of 10,825 characters from ancient Devanagari manuscripts, encompassing basic characters, modifiers, and conjuncts, classified into 399 classes. Testing various training–testing ratios (9:1, 8:2, and 7:3), we visually and statistically evaluated the experimental data, demonstrating the superiority of CapsNet and LSTM in handling these challenges. We calculated recognition accuracy, precision, and recall values, with CapsNet achieving a maximum accuracy of 95.98% after 30 epochs. This research underscores the effectiveness of CapsNet and LSTM in advancing character recognition for ancient Devanagari manuscripts.

Seventy years of study on ethnic paleography in China

This paper systematically presents the development process of studying ancient Chinese ethnic scripts over the past seven decades since the founding of the People’s Republic of China in 1949, including the establishment of related research institutions and academic disciplines. Firstly, it records the establishment of the Chinese Association for Ethnic Paleography, the emergence of ancient scripts of ethnic groups in China as an academic discipline, and the conduction of a comprehensive and in-depth study of ancient Chinese ethnic literature in history. Secondly, this paper outlines the establishment of the National Leading Group for Compilation and Publication Planning of Ancient Ethnic Books, the census of ancient books written in ethnic scripts, the specialized preservation and conservation of ancient ethnic books in Xizang and Xinjiang, the promotion of compiling and publishing ancient ethnic books, and how the promotion further drives the protection of and research on ancient books written in ethnic scripts. Thirdly, the paper lists many innovative outcomes in studying ancient ethnic books. Fourthly, the paper proposes to conduct further censuses and in-depth research in this area, establish a grading system for ancient ethnic books, and utilize the resource of ancient ethnic books written in ethnic scripts in a modern context to further promote the excellent cultural heritages of the Chinese nation and enhancing ethnic unity and national unity.

A Systematic Review of Computational Approaches to Deciphering Bronze Age Aegean and Cypriot Scripts

Abstract This article provides a detailed insight into computational approaches for deciphering Bronze Age Aegean and Cypriot scripts, namely, the Archanes script and the Archanes formula, Phaistos Disk, Cretan hieroglyphic (including the Malia Altar Stone and Arkalochori Axe), Linear A, Linear B, Cypro-Minoan, and Cypriot scripts. The unique contributions of this article are threefold: (1) a thorough review of major Bronze Age Aegean and Cypriot scripts and inscriptions, digital data and corpora associated with them, existing computational decipherment methods developed in order to decipher them, and possible links to other scripts and languages; (2) the definition of 15 major challenges that can be encountered in computational decipherments of ancient scripts; and (3) an outline of a computational model that could possibly be used to simulate traditional decipherment processes of ancient scripts based on palaeography and epigraphy. In the context of this article the term decipherment denotes the process of discovery of the language and/or the set of symbols behind an unknown script, and the meaning behind it.

Deep Aramaic: Towards a synthetic data paradigm enabling machine learning in epigraphy.

Epigraphy is witnessing a growing integration of artificial intelligence, notably through its subfield of machine learning (ML), especially in tasks like extracting insights from ancient inscriptions. However, scarce labeled data for training ML algorithms severely limits current techniques, especially for ancient scripts like Old Aramaic. Our research pioneers an innovative methodology for generating synthetic training data tailored to Old Aramaic letters. Our pipeline synthesizes photo-realistic Aramaic letter datasets, incorporating textural features, lighting, damage, and augmentations to mimic real-world inscription diversity. Despite minimal real examples, we engineer a dataset of 250 000 training and 25 000 validation images covering the 22 letter classes in the Aramaic alphabet. This comprehensive corpus provides a robust volume of data for training a residual neural network (ResNet) to classify highly degraded Aramaic letters. The ResNet model demonstrates 95% accuracy in classifying real images from the 8th century BCE Hadad statue inscription. Additional experiments validate performance on varying materials and styles, proving effective generalization. Our results validate the model's capabilities in handling diverse real-world scenarios, proving the viability of our synthetic data approach and avoiding the dependence on scarce training data that has constrained epigraphic analysis. Our innovative framework elevates interpretation accuracy on damaged inscriptions, thus enhancing knowledge extraction from these historical resources.

Leveraging AI for Historical Linguistics

This manuscript delves into the application of AI techniques, such as machine learning, natural language processing, and pattern recognition, to interpret ancient scripts and unveil linguistic phenomena. Through an examination of the strategies utilized by linguists and adept individuals in deciphering ancient languages, the manuscript underscores the potential of AI-driven methodologies in this realm.

‘손(手)’類 部首字 중심의 草書 字形 및 類似 字形에 관한 고찰

This paper studies the cursive script of characters such as 手(Hands), 攴(slaps), 攵(slaps), 支(supports), 又(hands), 爪(nails), 寸(short length), 厶(arms), 力(strength), 文(words), 戈(weapons) and compound characters.
 This paper compares these characters with similar shapes. The meaning and shape of ancient characters have influenced cursive writing. Just organize it briefly.
 Words(‘手’) express the shape of fingers and fists. The shape of cursive script is affected by this. The character(‘攴’, ‘攵’) represents the appearance of holding a stick in hand. ‘戈’ is a weapon used in war. So these words replaced each other in cursive script. The character(‘攴’) appears alternately with this character( ‘力’字, ‘又’字, ‘’字, ‘支’字, ‘弓’字, ‘攵’字, ‘文’字 ). One of these phenomena is that the characters are similar, which is why they appear in cursive script. This character(‘’字, ‘弓’字) is influenced by that character(‘乃’字, ‘’字, ‘’字) and appears in cursive script. The cursive script of this character(‘又’) has also been replaced by that character(‘寸’). Or multiple of these words(‘又’) have been weakened. The cursive strokes of this character(‘爪’) have weakened. Elaborate or express in two points.
 This word(‘寸’) has a curved tail and then narrates together with dots. Or change the position of the point to express it. This character(‘對’) divides the upper part of that character(‘丵’) into three dots according to the ancient script shape. This character(‘厶’) is an old version of this character(‘厷’). This character(‘厷’) appears with that character(‘九’). The reason is that(‘九’) in ancient Chinese characters, this character(‘九’) presents the shape of a human arm, and that character(‘肱’) also presents the shape of a bent arm, so it appears alternately. Because these characters have a common curved shape, which character(‘厷’) is used instead of this one(‘弓’) to express. You can see the appearance of ‘厶’, ‘厷’, ‘弓’, ‘’ from the cursive script. This word(‘力’) expresses human muscles and tendons. These words(攵, 攴, 力) related to hands or arms are mixed together for use. This character(‘文’) also has a similar shape to that character(‘攵’), so it will also appear in cursive script. According to these contents, the characters are influenced by similar characters, ancient characters, and variant characters, appearing in cursive script characters. Exploring similar or ancient character forms can provide a lot of information for distinguishing cursive script forms. By using it, it is possible to provide rich explanations for more glyphs. I hope this will be of great help in understanding the shapes of cursive script.

‘손(手)’類 部首字 중심의 草書 字形 및 類似 字形에 관한 고찰

This paper studies the cursive script of characters such as 手(Hands), 攴(slaps), 攵(slaps), 支(supports), 又(hands), 爪(nails), 寸(short length), 厶(arms), 力(strength), 文(words), 戈(weapons) and compound characters.
 This paper compares these characters with similar shapes. The meaning and shape of ancient characters have influenced cursive writing. Just organize it briefly.
 Words(‘手’) express the shape of fingers and fists. The shape of cursive script is affected by this. The character(‘攴’, ‘攵’) represents the appearance of holding a stick in hand. ‘戈’ is a weapon used in war. So these words replaced each other in cursive script. The character(‘攴’) appears alternately with this character( ‘力’字, ‘又’字, ‘’字, ‘支’字, ‘弓’字, ‘攵’字, ‘文’字 ). One of these phenomena is that the characters are similar, which is why they appear in cursive script. This character(‘’字, ‘弓’字) is influenced by that character(‘乃’字, ‘’字, ‘’字) and appears in cursive script. The cursive script of this character(‘又’) has also been replaced by that character(‘寸’). Or multiple of these words(‘又’) have been weakened. The cursive strokes of this character(‘爪’) have weakened. Elaborate or express in two points.
 This word(‘寸’) has a curved tail and then narrates together with dots. Or change the position of the point to express it. This character(‘對’) divides the upper part of that character(‘丵’) into three dots according to the ancient script shape. This character(‘厶’) is an old version of this character(‘厷’). This character(‘厷’) appears with that character(‘九’). The reason is that(‘九’) in ancient Chinese characters, this character(‘九’) presents the shape of a human arm, and that character(‘肱’) also presents the shape of a bent arm, so it appears alternately. Because these characters have a common curved shape, which character(‘厷’) is used instead of this one(‘弓’) to express. You can see the appearance of ‘厶’, ‘厷’, ‘弓’, ‘’ from the cursive script. This word(‘力’) expresses human muscles and tendons. These words(攵, 攴, 力) related to hands or arms are mixed together for use. This character(‘文’) also has a similar shape to that character(‘攵’), so it will also appear in cursive script. According to these contents, the characters are influenced by similar characters, ancient characters, and variant characters, appearing in cursive script characters. Exploring similar or ancient character forms can provide a lot of information for distinguishing cursive script forms. By using it, it is possible to provide rich explanations for more glyphs. I hope this will be of great help in understanding the shapes of cursive script.

Some Issues Concerning the Phenomenon of Ancient Script Forms Being Preserved in Warring States Bamboo Manuscripts

Abstract The phenomenon of preserving ancient character forms (wenzi cungu xianxiang 文字存古現象) can be observed in certain recently unearthed bamboo slip manuscripts from the Warring States. These characters have preserved early character structures or word usage habits, thus reflecting an interactive relationship between the copyist and the source text. Based on the number of early characters observed in a copied manuscript, Warring States bamboo manuscripts can largely be divided into three categories. One category containing relatively more words with early word forms can be dubbed as “transcripts containing characteristics of ancient text preservation,” with the Tsinghua manuscripts *Xinian 繫年, *Hou fu 厚父, *Sheming 攝命, and *Si gao 四告 being the most emblematic of this category. The value of research into ancient character forms preserved in Warring States bamboo-slip manuscripts is important in many ways, such as providing evidence for character identification; helping to determine the origins of ancient manuscript source texts and their time of transcription; and demonstrating how documents may have been transmitted. All these aspects are evident in the relevant Tsinghua manuscripts. However, in assessing whether ancient character forms were indeed preserved in Warring States manuscripts, two problems must be accounted for: first, some characters that have previously been identified as having characteristics of different scripts may have earlier origins or lack any obvious script-specific features; second, some ancient-looking characters cannot necessarily be used as a standard to determine the occurrence of ancient script forms.

"ᚁ is Beith and means birch” - an exploration of Ogham in online fanfiction featuring King Alfred the Great

Through an analysis of three selected case studies, this study unveils how Ogham's integration into contemporary narratives generates fresh layers of meaning and revitalises this ancient alphabet. The chosen focus on Alfredian fanfiction offers a contextualised exploration of the role of this ancient Irish script in shaping novel interpretations, bridging historical languages with the digital age, and shedding light on how fan communities reconfigure cultural heritage across temporal and geographical boundaries within the dynamic landscape of internet culture. By employing a comprehensive approach, this research elucidates the intricate interplay between Ogham, historical narratives, and contemporary fan creativity, providing valuable insights into how this ancient script sparks innovative meanings and propels narratives within the digital realms of fan culture.

A Study of Bear Totem Characters in Ancient Scripts: The Spread of Writings in the Hongshan Culture

A Study of Bear Totem Characters in Ancient Scripts: The Spread of Writings in the Hongshan Culture

The Impact of Data Augmentation Techniques on the Recognition of Script Images in Deep Learning Models

Deep learning technology is widely used for recognizing character images, including various regional characters and diverse ancient scripts. Deep learning models require large data sets to recognize images accurately. However, creating a dataset has limitations in terms of quantity, including the Komering script dataset used in this study. Data augmentation techniques can be applied to expand the dataset by modifying existing images to increase data diversity. This study aims to investigate the impact of augmentation techniques on the performance of deep learning models in the case of Komering script recognition. The dataset consists of 500 images for five classes of Komering script characters. Three augmentation techniques, namely random rotation, height shift, and width shift, were applied to the five characters, which were then used to test the model trained to recognize characters in the Komering dataset. This research contributes to providing insights into the effect of augmentation techniques on robust confidence prediction of deep learning models for recognizing newly augmented data. The results demonstrate that the deep learning model can recognize modified data using augmentation techniques with an average accuracy of 80.05%.

A deep learning based approach for extracting Arabic handwriting: applied calligraphy and old cursive.

Based on the results of this research, a new method for separating Arabic offline text is presented. This method finds the core splitter between the "Middle" and "Lower" zones by looking for sharp character degeneration in those zones. With the exception of script localization and the essential feature of determining which direction a starting point is pointing, the baseline also functions as a delimiter for horizontal projections. Despite the fact that the bottom half of the characteristics is utilized to differentiate the modifiers in zones, the top half of the characteristics is not. This method works best when the baseline is able to divide features into the bottom zone and the middle zone in a complex pattern where it is hard to find the alphabet, like in ancient scripts. Furthermore, this technique performed well when it came to distinguishing Arabic text, including calligraphy. With the zoning system, the aim is to decrease the number of different element classes that are associated with the total number of alphabets used in Arabic cursive writing. The components are identified using the pixel value origin and center reign (CR) technique, which is combined with letter morphology to achieve complete word-level identification. Using the upper baseline and lower baseline together, this proposed technique produces a consistent Arabic pattern, which is intended to improve identification rates by increasing the number of matches. For Mediterranean keywords (cities in Algeria and Tunisia), the suggested approach makes use of indicators that the correctness of the Othmani and Arabic scripts is greater than 98.14 percent and 90.16 percent, respectively, based on 84 and 117 verses. As a consequence of the auditing method and the assessment section's structure and software, the major problems were identified, with a few of them being specifically highlighted.

AI Based Tamil Palm Leaf Character Recognition

A brand-new character recognition method has been created especially for Tamil manuscripts written on palm leaves. A variety of preprocessing techniques are used to obtain reliable recognition because these manuscripts are complicated and have age-related deterioration. Using cutting-edge image processing techniques, manuscript photos are enhanced and preprocessed in the earliest stage to improve clarity. Then, in accordance with the distinctive arrangement of these historical artifacts, these photos are divided into three separate portions. After segmentation, these parts are converted to grayscale to create the ideal contrast needed for character detection. Noise canceling algorithms have been incorporated to prevent any distortions or degradations that may occur as a result of the age of the manuscripts or other environmental influences. After this mitigation, the photos are binarized to emphasize the isolation of the figures from their surroundings. This makes sure that each character stands out clearly, laying the groundwork for the crucial next step: segmenting individual characters. The foundation of the training phase is this segmentation. Convolutional neural networks (CNNs), which excel at handling image-based tasks, were incorporated into the deep learning architecture used for model building. Utilizing a sizable dataset compiled from numerous articles, the model underwent intensive training. As a result, the model was able to recognise characters from these texts with an astounding accuracy rate of 89%. With the help of Flask, the complete system has been easily integrated into a user-friendly web interface. This platform's goal is quite clear: fusing the elegance and profundity of ancient scripts with the effectiveness of contemporary technology. It is positioned as a crucial tool for both academic research and teaching purposes. By doing this, it guarantees that the priceless history and knowledge found in these manuscripts remain accessible and lays the groundwork for their preservation for future generations. Keywords— Character recognition, Tamil palm manuscripts, Preprocessing, Visual clarity, Grayscale conversion, Noise cancellation, Binarization, Segmentation, Training, Flask-based web interface, Research, Education.

The history of archives in Central Asia: ancient times

The article devoted studies of the documents on the history of the archives in Central Asia on the basis of archeological researches having been conducted in Central Asia over the last decades. Until now there have not been conducted practical complex studies of Central Asian archives of ancient times. On the basis of certain facts this following article has described the life experiences of ancient people who lived in the territory of current Uzbekistan and indicated the process of preserving documents and transferring data from generation to generation in the form of rock paintings and archival documents-libraries. These references indicate to the existence of ancient scripts in Khorezm. On the basis of scientific studies of the scientists it can be concluded that the elements of scripts discovered on the ancient ceramic handcrafts may be considered as the samples of early economic archieves found in the territory of present Uzbekistan. In the period of Akhamanids in Iran and in Central Asia cuneiform was widespread and in the whole territory of the empire Aramaic script wasn’t the only language of paperwork. As it has been indicated in the article, according to its geographic scope, the Bactrian language took the second place after the Sogd language which was widely used in the territory extending from India to Eastern Turkestan. The fact that two biggest empires as Kushanids and Ephtalits and then also the state of Takhirids utilised this script demonstrates the significance of the ancient Bactrian language in the lives of ancient nations. This paper also shows the similar attributes of the Bactrian language used in making negotiations of Surkh-Kutal, Rabotak with the scripts used in the samples of the letters in the documents from the library of Ashurbanipal and with the Het script in which the texts of the anthems, national communal decisions and religious messages were inscribed on the rocks. There are also some evidences proving the existence of particular archives in the residences of ancient rulers of Central Asia in such places as Toprak Kala (Khorezm), and in the mount of Mug’ (Devashtich archives). Particularly in royal archives there was a systematic archival work and such materials as leather and wood were widely used to fix the data. Such documents as personal letters, diplomatic correspondence, contracts and economical records were kept in this period. It also should be noted that paperwork was far more enhanced in this epoch.

The Threat of Discontinuity Ancient Scripts in the Islamic-Malay Manuscript

The purpose of this writing is to prove that there is a threat of discontinuity of ancient scripts in Malay Islamic manuscripts. Preservation of cultural heritage in the form of ancient script tends to be ignored. Abandonment of ancient scripts in the form of discontinuity the inheritance of ancient scripts; discontinuity of ancient script writing and discontinuity due to myths. In fact, these three aspects have the effect of threatening the discontinuity of ancient script. Through direct and indirect observation of digital collections of ancient manuscripts and free interviews with informants consisting of government agencies, traditional leaders and communities of ancient script lovers. Three ancient scripts that are threatened with discontinuity were found: (1) Jawi script, (2) Ulu script and (3) Lontaraq script. To then do data analysis by means of descriptive, interpretive and reflective of the existing data. This research shows that the government's policy regarding the preservation of cultural heritage must be handed down by the local government in an effort to preserve ancient scripts with outreach, workshops/training as a condition for the sustainability of cultural heritage. In addition, recruitment of ancient script experts is needed to increase qualified human resources and ancient script experts so that local content subjects can be realized. This is important to increase the preservation of ancient scripts.

Defining the structure of the epic <em>Khan Kharangui</em>

The article analyzes the syntagmatic and paradigmatic structure of “Khan Kharangui” as the origin of Mongolian epics. In doing so, through syntagmatic and paradigmatic analysis each meaningful narrative in the epic is traced on the sentence level and consolidated in a chart grouping all these narratives. The theoretical and methodological significance of this study is to demonstrate how to apply the techniques of structural and syntagmatic analysis while studying epic poetry.
 The manuscripts of “Khan Kharangui” from Okin (Buryatia, Russia) and Kyzyl (Tuva, Russia) as well as “Rinchen” (published in Hungary) and “Tod Üseg” (St. Petersburg, Russia) are known to researchers. It was concluded that all the manuscripts of “Khan Kharangui” are originated from one source, namely from the source written in ancient script tod üseg. Since that source was substantially damaged, the other sources are used in this study. The Okin and the Rinchen manuscripts match almost word for word while the Kyzyl manuscript is more literary both in stylistic and orthographic aspects, but some episodes are rendered in a somewhat more shortened form compared to the former manuscripts. There are slight differences in their size, but they are same in terms of substantive functions and structures.
 When analyzing the syntagmatic structure of the epic by means of the functions described in Vladimir Propp’s “Morphology of the Folktale”, the following functions are not identified in the epic about Khan Kharangui: branding (J), unrecognized arrival (O), unfounded claims (L), difficult task (M), solution (N), recognition (Q) and exposure (Ex).
 As for the paradigmatic structure of the epic, it could be analyzed by the method proposed in “The Structural Study of Myth” by Claude Lévi-Strauss. A particular feature in the paradigmatic structure of the epic is that it legitimizes how one ripostes and what the ultimate results will be when the established relationships and attitudes are violated. That is why each column on the left constitutes a premise or condition for the column on the right, and each column on the right becomes a consequence or implication for the left one with respect to the two columns on the right and left in the illustrated chart.

A Novel Framework for Ancient Text Translation Using Artificial Intelligence

Ancient script has been a repository of knowledge, culture and civilization history. In order to have a greater access to the valuable information present in the ancient scripts, an appropriate translation system needs to be developed keeping complexity and very less knowledge of the script available in consideration. In this study, a translation and prediction system has been implemented using Artificial Intelligence. The training has been developed using Sunda-Dataset and self-generated dataset, whereas the translation from ancient script viz. Sundanese script to English text is done using two layers Recurrent Neural Network. The technique used is compared with an existing translator called IM Translator. The results shows that the BLEU score is increased by 8% in comparison to IM Translator further WER is decreased by 10% in contrast to IM Translator. Furthermore, the N-Gram analysis results indicate 3% to 4% increase in 100% contrast value.

Convolutional Neural Networks Analysis Reveals Three Possible Sources of Bronze Age Writings between Greece and India

This paper analyzes the relationships among eight ancient scripts from between Greece and India. We used convolutional neural networks combined with support vector machines to give a numerical rating of the similarity between pairs of signs (one sign from each of two different scripts). Two scripts that had a one-to-one matching of their signs were determined to be related. The result of the analysis is the finding of the following three groups, which are listed in chronological order: (1) Sumerian pictograms, the Indus Valley script, and the proto-Elamite script; (2) Cretan hieroglyphs and Linear B; and (3) the Phoenician, Greek, and Brahmi alphabets. Based on their geographic locations and times of appearance, Group (1) may originate from Mesopotamia in the early Bronze Age, Group (2) may originate from Europe in the middle Bronze Age, and Group (3) may originate from the Sinai Peninsula in the late Bronze Age.