Oracle Bone Research Articles

An open dataset for oracle bone character recognition and decipherment

Oracle bone script, one of the earliest known forms of ancient Chinese writing, presents invaluable research materials for scholars studying the humanities and geography of the Shang Dynasty, dating back 3,000 years. The immense historical and cultural significance of these writings cannot be overstated. However, the passage of time has obscured much of their meaning, presenting a significant challenge in deciphering these ancient texts. With the advent of Artificial Intelligence (AI), employing AI to assist in deciphering Oracle Bone Characters (OBCs) has become a feasible option. Yet, progress in this area has been hindered by a lack of high-quality datasets. To address this issue, this paper details the creation of the HUST-OBC dataset. This dataset encompasses 77,064 images of 1,588 individual deciphered characters and 62,989 images of 9,411 undeciphered characters, with a total of 140,053 images, compiled from diverse sources. The hope is that this dataset could inspire and assist future research in deciphering those unknown OBCs. All the codes and datasets are available at https://github.com/Pengjie-W/HUST-OBC.

The birth of the Chinese character ‘奈’: Reflections on semantic differentiation

In this study, ‘奈’, is the earliest character in Ancient Chinese to derive its meaning from a single character. It was derived and developed from the sounds and characters corresponding to ‘奈’, ‘柰’ and ‘祟’. Thus, the formation and elimination of sounds in Ancient Chinese can be viewed through the one-sided development of Chinese characters from the time of the oracle bone script period to the present, but it can be seen that sound components are not all components of lexical variation, and thatW the process of character differentiation is ultimately influenced by the similarity of characters, their meaning and their development. The article describes a study to examine the development of lexical meaning and the relationship between its semantic elements: first, the original meaning of the characters and the extended meaning; second, the development of sound and dialect from the Ancient Chinese period to the Middle Chinese period; and third, the grammatical implementation and function that can be checked through it, and the semantic analysis elements found in the Chinese characters, excavated texts and traditional texts.

Shang Dynasty's Foreign War in Oracle Bone Scripts

Shang Dynasty's Foreign War in Oracle Bone Scripts

Enhancing Oracle Bone Character Category Discovery via Character Component Distillation and Self-Merged Pseudo-Label

Enhancing Oracle Bone Character Category Discovery via Character Component Distillation and Self-Merged Pseudo-Label

OBCTeacher: Resisting labeled data scarcity in oracle bone character detection by semi-supervised learning

Oracle bone characters (OBCs) are ancient ideographs for divination and memorization, as well as first-hand evidence of ancient Chinese culture. The detection of OBC is the premise of advanced studies and was mainly done by authoritative experts in the past. Deep learning techniques have great potential to facilitate OBC detection, but the high annotation cost of OBC brings the scarcity of labeled data, hindering its application. This paper proposes a novel OBC detection framework called OBCTeacher based on semi-supervised learning (SSL) to resist labeled data scarcity. We first construct a large-scale OBC detection dataset. Through investigation, we find that spatial mismatching and class imbalance problems lead to decreased positive anchors and biased predictions, affecting the quality of pseudo labels and the performance of OBC detection. To mitigate the spatial mismatching problem, we introduce a geometric-priori-based anchor assignment strategy and a heatmap polishing procedure to increase positive anchors and improve the quality of pseudo labels. As for the class imbalance problem, we propose a re-weighting method based on estimated class information and a contrastive anchor loss to achieve prioritized learning on different OBC classes and better class boundaries. We evaluate our method by using only a small portion of labeled data while using the remaining data as unlabeled and all labeled data with extra unlabeled data. The results demonstrate the effectiveness of our method compared with other state-of-the-art methods by superior performance and significant improvements of an average of 11.97 in AP50:95 against the only supervised baseline. In addition, our method achieves comparable performance using only 20% of labeled data to the fully-supervised baseline using 100% of labeled data, demonstrating that our method significantly reduces the dependence on labeled data for OBC detection.

Gca-pvt-net: group convolutional attention and PVT dual-branch network for oracle bone drill chisel segmentation

Oracle bones (Obs) are a significant carrier of the shang dynasty civilization, primarily consisting of tortoise shells and animal bones, through the study of which we can gain a deeper understanding of the political, economic, religious, and cultural aspects of the shang dynasty. The oracle bone drill chisel (Obdc) is considered an essential non-textual material. The segmentation of Obdc assists archaeologists determine the approximate age of the Obs, which possesses considerable research value. However, the breakage of thousands of years of underground buried Obs, the blurring of the edges of the area burned by the Obdc, the different shapes, and the inconsistent number have brought challenges to the accurate segmentation of the Obdc. In this article, we propose a group convolutional attention and pvt dual-branch network (GCA-PVT-Net) for Obdc segmentation. To our knowledge, this paper is the first to research the automatic segmentation of Obdc. It is a hybrid Convolutional neural network (CNN) and Transformer framework. The work offers the following contributions: (1) The Obdc images are labeled based on the delineation criteria of different drill chisel (DC) shapes to create the Obdc dataset. (2) A convolutional attention module (CAM) is proposed as both an encoder and decoder. The feature extraction process, which effectively integrates global and local information, ensures better modeling of long-term correlations in images while preserving details. (3) A channel feature aggregation module (CFAM) is designed to enhance the effective integration of channel features, enabling feature fusion across various branches and at different levels. (4) The edge deep supervision strategy is applied to smooth the jagged edge of the predicted images at the decoder’s end. Extensive experiments on the Obdc dataset show that GCA-PVT-Net outperforms other state-of-the-art (SOTA) methods. The comparative experimental results show that the edge accuracy and segmentation accuracy of the model reach the top 1.

Digital Communication and Preservation of Cultural Heritage in the Context of New Media: A Case Study of Anyang

Anyang is rich in diverse cultural heritage, including the famous Yin Ruins, oracle bone script, Shang Dynasty culture, and divination beliefs. These heritages are core carriers of cultural transmission and important academic research areas. This study analyzes the adaptability of Anyang's cultural heritage amidst modern social changes, focusing on its integration with local economic development strategies. By activating the tourism market and image industry, it promotes economic growth and cultural transmission. The study also explores the digitization of literature and new media tools in modernizing educational content. Through visual media, Anyang's cultural heritage overcomes geographical barriers, connecting with a global audience. Visual narratives present Anyang's history and cultural stories, offering new paths for global recognition. Films, micro-dramas, online media, and other visual art forms transform Anyang's cultural narratives into symbols easily understood worldwide. The study encourages more film and television creators to explore Henan and Anyang, discovering the value of historical and cultural resources and landscapes through high-quality works.

Japanese Oracle Bone Divinations during the Yayoi to Heian Periods: A Review of Studies of the Last Seventy Years

Although often thought to be mostly relevant to Bronze Age China, oracle bone divination also has a rich history in Japan, primarily documented through literature and ethnographic records. In recent decades, the discovery of oracle bones spanning from the Early Yayoi (1000-400 B.C.) to Heian (A.D. 794-1185) periods has opened new avenues for research in pyro-osteomancy. These archaeological findings provide fresh perspectives on the social and cultural influences on oracle bone divination in Japan and East Asia more broadly. In this study, we review the historical, ethnographic, and archaeological studies of oracle bone divination in Japan, offering a comprehensive overview of divination practices and their broader significance.

COSMOLOGICAL CONCEPT OF TIME IN “THE CHANGE OF ZHOU” (“THE BOOL OF CHANGE”)

This paper represents one chapter from my PhD dissertation, written and successfully defended at Beijing Normal University in 2012. The whole content is translated from my doctoral dissertation that was originally written in Chinese language. According to the existing references, the earliest Chinese philosopher who mentioned in his essays the word “cosmos – yuzhou” was Shi Jiao (390-330 BC). He said: “four directions of Heaven and Earth are called ′yu′, time since ancient times till today is called ′zhou′”. In other words, yu represents space, while zhou symbolizes time, and that is why Chinese ancient cosmology may be even called “concept of space and time”. Inscriptions on the oracle bones and tortoiseshells with the symbols called “ganzhi”, originating from the Yin dynasty, were used to record hours, days, months and years i.e. time, but at the same time, Chinese people used these symbols to mark the directions of space, too. All of the cosmological diagrams used by “The Change of Zhou” and yijingologists, like Fuxi’s transcendental bagua diagram, king Wen’s empirical bagua diagram, river map and Luo book simultaneously depict time and space. In the eyes of the Chinese people, since ancient times, time and space are one whole and inseparable unity. However, being a foreigner, the writer of these lines will separately analyze the meaning of time in “The Book of Change”. As a foreigner, I find that the greatest charm of Chinese characters is that every character holds the whole history and etymology of one word or term in it. In other words, the most prominent feature of Chinese characters is symbolism. Therefore, if we want to explore “the time” concept, we must start from the character 时- shi meaning “time”. Character shi is formed of one radical meaning “sun”, and another meaning “measure”. This shows that the meaning of character shi is “measuring the sun”, i.e. measuring the length of sun shadow. The shorter the sun shadow is, the weather is being warmer and the Yang energy gets more abundant. It explains that character shi depicts increasing and decreasing of Yin and Yang energy in the cosmos and on the Earth. This paper analyzes time concept in “The Change of Zhou” from the Chinese and Western point of view. It explains meanings of Heavenly dao, Heavenly time, chance and synchronicity. The paper uses time theories (like simplicity of time, presentism, etc.) of German scientist Leibniz（1646 – 1716）, and famous Swiss psychologist Carl Jung’s（1875 - 1961） concepts (like cosmical archetypes and synchronicities), and compare them with ideas of “the cognition of subtle”, “progress through change” and “capability to grasp the chance” in “The Change of Zhou”. Finally, it combines and summarises the concept of time from “The Change of Zhou” and Western point of view.

金文“叀”字考

The ancient character “叀” is very common, and the shapes are also diverse. This article conducts a detailed analysis of the ancient “叀” character by analyzing the shape of the characters “叀” in oracle bone inscriptions and “叀” in bronze inscriptions. This article presents a table format for statistical analysis and classification comparison of the font forms of the ancient “叀” character. The focus is on a detailed analysis of the character “叀” from the two distinct forms, the interpretation of inscriptions on bronze inscriptions and modern translations, and the words “specialized” and “beneficial” related to “叀”. In addition, a brief analysis of the grammatical meaning of the character “叀” in Jinwen is also conducted. Jinwen is an important language material for studying ancient Chinese. In the development and evolution of characters, the phenomenon of mixed use of characters and borrowing characters is very common. However, during the use and evolution of the character “芔”, due to the occurrence of confusion in its use, it has intricate connections with the ancient “芔” character in terms of pronunciation and form, and also has the pronunciation of “zhuān” and “huì”. However, there are also obvious differences in semantics and pragmatics.

Exploration of the Phenomenon of Compound Characters and Separate Characters in River Names of Oracle Bone Inscriptions

Exploration of the Phenomenon of Compound Characters and Separate Characters in River Names of Oracle Bone Inscriptions

《說文解字》“从夲”諸字考及西周金文中“从𠦪”字考

Some people identify the character “夲” in clerical form as “𠦍”。 In Shuowen Jiezi (Explaining Graphs and Analyzing Characters), all characters belonging to “夲” are derived from the character “夲”, like “𠦪”、“曓”、“𡴞”、“奏”and“皋”。They are all components separated from the seal script forms of characters。But we believe that the character “夲” has nothing to do with the above。In Shuowen Jiezi, the pronunciation of the character “夲” is given as “滔”, which seems to inherit the “”, “” belonging to the character “𠦪”, borrowing the pronunciation of “禱”。We believe that the character “夲” may be related to the character “奔”, and its rhyme is also related to the characters “跑”, “挑”, or “走”, thus the pronunciation of the character “夲” is “滔”。 The initials of the characters “𠦪”, “曓”, “𡴞” and “奏” in Shuowen Jiezi are not very similar, the pronunciation of the character “夲” is “滔”, which also has a rhyming relationship with the characters “曓”, “奏” and “皋”, but their origins are different。The characters “𠦪”, “曓”, “𡴞” and “奏” can be classified under the “𠦪” radical, and the ancient form of the character “㚖” can be classified under the “㚔” radical。In Shuowen Jiezi, some characters in the “夲” section can be classified under the “𠦪” radical。This paper uses oracle bone inscriptions to explore the origin of the character “𠦪” , in the bronze inscriptions of the Western Zhou Dynasty, characters pronounced as “𠦪” include “𠦪”, “”, “”and “”, while the character “曓” has not yet been found。In the Yin and Zhou Bronze Inscriptions Collected, there are more than 50 examples of characters with the pronunciation of “𠦪”, such as “𩞑(饙)”, “賁”, “幩”, “帗”, “紱”, “韍”, “黻”, etc。In the bronze inscriptions of the Western Zhou Dynasty, the character “𠦪”is borrowed for characters such as “賁”, “幩”, “巿”, “祓”, “韍”, “饙” and “弼”, these borrowed characters have labial initials and a entering tone (-k) or a nasal ending (-en) in their rhyme。Their meanings, besides being used as personal names, also include “祓”, “賁”, “𩞑(饙)”, “弼”, “韍”, and “百”。 Among them, the character “” in “趩觶(chi zhi)” (06516) is interpreted as “百世”, which can be seen as a ligature, and it should be identify in clerical form as “”, but some people interpreted it as “𠦪”, we believe that should be interpreted as the variant character of “𠦪”。

An Oracle Bone Inscriptions Detection Algorithm Based on Improved YOLOv8

Ancient Chinese characters known as oracle bone inscriptions (OBIs) were inscribed on turtle shells and animal bones, and they boast a rich history dating back over 3600 years. The detection of OBIs is one of the most basic tasks in OBI research. The current research aimed to determine the precise location of OBIs with rubbing images. Given the low clarity, severe noise, and cracks in oracle bone inscriptions, the mainstream networks within the realm of deep learning possess low detection accuracy on the OBI detection dataset. To address this issue, this study analyzed the significant research progress in oracle bone script detection both domestically and internationally. Then, based on the YOLOv8 algorithm, according to the characteristics of OBI rubbing images, the algorithm was improved accordingly. The proposed algorithm added a small target detection head, modified the loss function, and embedded a CBAM. The results show that the improved model achieves an F-measure of 84.3%, surpassing the baseline model by approximately 1.8%.

Detecting oracle bone inscriptions via pseudo-category labels

Oracle bone inscriptions (OBIs) are the earliest Chinese characters and reserve abundant historical information. OBIs are detected by locating their positions in digital images. This has been a foundational task in modern archeological studies. Due to the development of deep neural networks(DNNs) in computer vision, detecting OBIs can be implemented by a more concise method instead of designing complicated hand-crafted features. However, existing models cannot perform well when noise areas are similar to some inscriptions. In this work, we present a simple but effective pseudo-label-based architecture for OBIs detection. Different from previous approaches, our method performs OBIs detection with the employment of information from multilabel annotations rather than single location information. We append a plug-and-play module that predicts the pseudo-label of an inscription after the backbone network for learning the particular structure prior to each inscription and brings this information to the backbone network by means of feature fusion. We make remarkable improvements on different backbone networks when using the proposed method on an OBIs detection dataset. The quantitative and qualitative results show that the proposed model can detect OBIs well and is an effective tool for assisting in the discovery and recognition of ancient writing.

"View Wisps of Smoke Rising from The Stove Again"

Chinese calligraphy is the carrier of cultural heritage and has profound cultural connotations. The origin of Chinese calligraphy can be traced back to the ancient oracle bone inscriptions and Chinese bronze inscriptions period, which has a history of several thousand years. It is a key element of Chinese culture and an important means to inherit China's excellent traditional culture in the new era. Under the impact of information technology and “fast food ” culture, various computer fonts and personalized fonts have emerged, and people tend to use some "odd" fonts, and their cultural awareness is gradually weakened. In the new era, Chinese calligraphy culture is full of vigor, which requires us to deeply understand the essence of calligraphy culture, respect history and culture better, enhance cultural identity, and firmly believe in culture. We should adapt to the development of science and technology, using artificial intelligence technology to add new energy to traditional culture, inherit the historical context better, create an atmosphere where everyone strives to be a cultural inheritor, and carry forward the spirit of writing.

Ancient Chinese Character Recognition with Improved Swin-Transformer and Flexible Data Enhancement Strategies.

The decipherment of ancient Chinese scripts, such as oracle bone and bronze inscriptions, holds immense significance for understanding ancient Chinese history, culture, and civilization. Despite substantial progress in recognizing oracle bone script, research on the overall recognition of ancient Chinese characters remains somewhat lacking. To tackle this issue, we pioneered the construction of a large-scale image dataset comprising 9233 distinct ancient Chinese characters sourced from images obtained through archaeological excavations. We propose the first model for recognizing the common ancient Chinese characters. This model consists of four stages with Linear Embedding and Swin-Transformer blocks, each supplemented by a CoT Block to enhance local feature extraction. We also advocate for an enhancement strategy, which involves two steps: firstly, conducting adaptive data enhancement on the original data, and secondly, randomly resampling the data. The experimental results, with a top-one accuracy of 87.25% and a top-five accuracy of 95.81%, demonstrate that our proposed method achieves remarkable performance. Furthermore, through the visualizing of model attention, it can be observed that the proposed model, trained on a large number of images, is able to capture the morphological characteristics of ancient Chinese characters to a certain extent.

A scribal device in oral clothing: functions of formulaic language in early Chinese divinatory texts

This paper aims at broadening the scope of what the term ‘formula’ encompasses by studying a written context of formulaic applications and their complex connections to ritual performance. More specifically, it examines the interplay between the oral and the written in the language of the late Shang 商 (ca. 1230–1046 BC) oracle bone inscriptions (OBI). Drawing on the study on ‘formulaicity’ by Wray and Perkins, I propose a definition of formulae based on the OBI evidence and identify the structure-based formulaic types as found in the divinatory records. I then discuss the functions that formulae perform in the divinatory record. I suggest that formulae should be considered a scribal device, a set of stock phrases and technical words used by the scribes to record divination results. They formed a toolkit which was meant to facilitate the composition of written records on hard media. The writing act occurred after (and separately from) the oral divinatory act. Therefore, the oral and written coexisted but were independent from each other within the context of divinatory performance.

An unsupervised automatic organization method for Professor Shirakawa’s hand-notated documents of oracle bone inscriptions

AbstractAs one of the most influential Chinese cultural researchers in the second half of the twentieth-century, Professor Shirakawa is active in the research field of ancient Chinese characters. He has left behind many valuable research documents, especially his hand-notated oracle bone inscriptions (OBIs) documents. OBIs are one of the world’s oldest characters and were used in the Shang Dynasty about 3600 years ago for divination and recording events. The organization of OBIs is not only helpful in better understanding Prof. Shirakawa’s research and further study of OBIs in general and their importance in ancient Chinese history. This paper proposes an unsupervised automatic organization method to organize Prof. Shirakawa’s OBIs and construct a handwritten OBIs data set for neural network learning. First, a suite of noise reduction is proposed to remove strangely shaped noise to reduce the data loss of OBIs. Secondly, a novel segmentation method based on the supervised classification of OBIs regions is proposed to reduce adverse effects between characters for more accurate OBIs segmentation. Thirdly, a unique unsupervised clustering method is proposed to classify the segmented characters. Finally, all the same characters in the hand-notated OBIs documents are organized together. The evaluation results show that noise reduction has been proposed to remove noises with an accuracy of 97.85%, which contains number information and closed-loop-like edges in the dataset. In addition, the accuracy of supervised classification of OBIs regions based on our model achieves 85.50%, which is higher than eight state-of-the-art deep learning models, and a particular preprocessing method we proposed improves the classification accuracy by nearly 11.50%. The accuracy of OBIs clustering based on supervised classification achieves 74.91%. These results demonstrate the effectiveness of our proposed unsupervised automatic organization of Prof. Shirakawa’s hand-notated OBIs documents. The code and datasets are available at http://www.ihpc.se.ritsumei.ac.jp/obidataset.html.

R-GNN: recurrent graph neural networks for font classification of oracle bone inscriptions

Font classification of oracle bone inscriptions serves as a crucial basis for determining the historical period to which they belong and holds significant importance in reconstructing significant historical events. However, conventional methods for font classification in oracle bone inscriptions heavily rely on expert knowledge, resulting in low efficiency and time-consuming procedures. In this paper, we proposed a novel recurrent graph neural network (R-GNN) for the automatic recognition of oracle bone inscription fonts. The proposed method used convolutional neural networks (CNNs) to perform local feature extraction and downsampling on oracle bone inscriptions. Furthermore, it employed graph neural networks (GNNs) to model the complex topologiure and global contextual information of oracle bone inscriptions. Finally, we used recurrent neural networks (RNNs) to effectively combine the extracted local features and global contextual information, thereby enhancing the discriminative power of the R-GNN. Extensive experiments on our benchmark dataset demonstrate that the proposed method achieves a Top-1 accuracy of 88.2%, significantly outperforming the competing approaches. The method presented in this paper further advances the integration of oracle bone inscriptions research and artificial intelligence. The code is publicly available at: https://github.com/yj3214/oracle-font-classification.

A dataset of oracle characters for benchmarking machine learning algorithms

Oracle bone script is an ancient Chinese writing system engraved on turtle shells and animal bones, serving as a valuable resource for interpreting ancient culture, history, and language. We introduce the Oracle-MNIST dataset, comprising of 28 × 28 grayscale images of 30,222 ancient characters from 10 categories, designed for benchmarking pattern classification, with particular challenges related to image noise and distortion. The training set totally consists of 27,222 images, and the test set contains 300 images per class. Oracle-MNIST follows the same data format with the original MNIST dataset, enabling direct compatibility with all existing classifiers and systems, but it constitutes a more challenging classification task than MNIST. The images of ancient characters suffer from (1) extremely serious and unique noises caused by three-thousand years of burial and aging and (2) dramatically variant writing styles by ancient Chinese, which all make them realistic for machine learning research.