Left Hands or Right Hands? An Artificial Intelligence Method-Based Evidence for Finding Remote Ancient People’s Habits When They Wrote Oracle Words that Were Deracinated 3000 Years Ago
Human beings like to ask where we came from and are always curious about how our habits evolved. One of our habits is handedness. It is found that cats and dogs do not differentiate between right- or left-handed forelimbs. But most humans are dextromanual. Did humans originate as dextromanual, or did most people converge to right-handedness as human society developed? To discover the answer, some archaeologists speculated that the ancients were right-handed because they found an ancient tooth fossil from 500,000 years ago in Spain skewed to the right. Is there more evidence? The extinct oracle bone scripts, written by ancient Chinese 3000 years ago, may expose some clues. We use the real images of the genuine rubbings provided by The Oracle Museum of China in our experiments. As it is well known, the power of deep learning networks has surpassed human beings in identifying subtle differences in images. Using the artificial intelligence tool, this paper studies the recognition of real oracle rubbings. Since it is impossible to recognize directly with the naked eye whether these rubbings were written by the left or right hand of ancient Chinese humans, this study has to employ the unsupervised method. We found through exhaustive experiments that the ancient oracle word authors were more likely to be dextromanual.
References
[1]
Wang, B. (2019) Oracle Bone Inscriptions Copybook. Beijing Arts and Crafts Publishing House. (In Chinese)
[2]
Chen, T. (2010) Restudy on the Glyph System of Shang Oracle Bone Inscriptions. Shanghai People’s Publishing House. (In Chinese)
[3]
Warren, J.M. (1953) Handedness in the Rhesus Monkey. Science, 118, 622-623. https://doi.org/10.1126/science.118.3073.622
[4]
Finch, G. (1941) Chimpanzee Handedness. Science, 94, 117-118. https://doi.org/10.1126/science.94.2431.117
[5]
Tsai, L.S. and Maurer, S. (1930) “Right-Handedness” in White Rats. Science, 72, 436-438. https://doi.org/10.1126/science.72.1869.436
[6]
Zhou, X., Li, F. and Hua, X. (1996) Study on Computer Identification Method of Oracle. Journal of Fudan University, 5, 481-486. (In Chinese)
[7]
Li, F. and Zhou, X. (1996) The Graph Theory Method of Oracle Bone Inscriptions Automatic Recognition. Journal of Electronics & Information Technology, S1, 41-47. (In Chinese)
[8]
Gu, S. (2018) A Method of Oracle Character Recognition Based on Fractal Geometry. Journal of Chinese Information Processing, 32, 138-142. (In Chinese)
[9]
Liu, G. (2018) Oracle-Bone Inscription Recognition Based on Deep Convolutional Neural Network. Journal of Computers, 13, 1442-1450. https://doi.org/10.17706/jcp.13.12.1442-1450
[10]
Gao, J. and Liang, X. (2020) Distinguishing Oracle Variants Based on the Isomorphism and Symmetry Invariances of Oracle-Bone Inscriptions. IEEE Access, 8, 152258-152275. https://doi.org/10.1109/access.2020.3017533
[11]
Liang, X. (2020) Social Computing with Artificial Intelligence. Springer.
[12]
Trinh, T., Luong, M. and Le, Q. (2019) Selfie: Self-Supervised Pretraining for Image Embedding. https://arxiv.org/abs/1906.02940
[13]
Faghri, F., Fleet, D., Kiros, J.R. and Fidler, S. (2018) VSE++: Improving Visual-Semantic Embeddings with Hard Negatives. British Machine Vision Conference 2018, BMVC 2018, Newcastle, 3-6 September 2018, 12.
[14]
Chen, X. and Li, Y. (2020) Deep Feature Learning with Manifold Embedding for Robust Image Retrieval. Algorithms, 13, Article No. 318. https://doi.org/10.3390/a13120318
[15]
Ren, J., Long, J. and Xu, Z. (2019) Financial News Recommendation Based on Graph Embeddings. Decision Support Systems, 125, Article ID: 113115. https://doi.org/10.1016/j.dss.2019.113115
[16]
Hinton, G.E., Osindero, S. and Teh, Y. (2006) A Fast Learning Algorithm for Deep Belief Nets. Neural Computation, 18, 1527-1554. https://doi.org/10.1162/neco.2006.18.7.1527
[17]
Cevikalp, H., Benligiray, B. and Gerek, O.N. (2020) Semi-Supervised Robust Deep Neural Networks for Multi-Label Image Classification. Pattern Recognition, 100, Article ID: 107164. https://doi.org/10.1016/j.patcog.2019.107164
[18]
Marin, J., Biswas, A., Ofli, F., Hynes, N., Salvador, A., Aytar, Y., et al. (2021) Recipe1m+: A Dataset for Learning Cross-Modal Embeddings for Cooking Recipes and Food Images. IEEE Transactions on Pattern Analysis and Machine Intelligence, 43, 187-203. https://doi.org/10.1109/tpami.2019.2927476
[19]
Lin, J. and Li, J. (1996) Feature Extraction and Preprocessing of Offline Chinese Signature Verification. Journal of Shanghai Jiaotong University, 30, 42-47. (In Chinese)
[20]
Wang, J. and Qin, F. (2004) Design and Application of Adaptive Binary Filtering Algorithm for Gray Text Image. Journal of Hefei University of Technology, No. 5, 509-512. (In Chinese)
[21]
Abdi, M.N. and Khemakhem, M. (2012) Arabic Writer Identification and Verification Using Template Matching Analysis of Texture. 2012 IEEE 12th International Conference on Computer and Information Technology, Chengdu, 27-29 October 2012, 592-597. https://doi.org/10.1109/cit.2012.126
[22]
Darwish, A.M. and Auda, G.A. (1994) A New Composite Feature Vector for Arabic Handwritten Signature Recognition. Proceedings of ICASSP ‘94. IEEE International Conference on Acoustics, Speech and Signal Processing, Adelaide, 19-22 April 1994, II/613-II/616. https://doi.org/10.1109/icassp.1994.389581
[23]
Said, H.E.S., Tan, T.N. and Baker, K.D. (2000) Personal Identification Based on Handwriting. Pattern Recognition, 33, 149-160. https://doi.org/10.1016/s0031-3203(99)00006-0
[24]
Singh, G. and Sundaram, S. (2015) A Subtractive Clustering Scheme for Text-Independent Online Writer Identification. 2015 13th International Conference on Document Analysis and Recognition (ICDAR), Tunis, 23-26 August 2015, 311-315. https://doi.org/10.1109/icdar.2015.7333774
[25]
Shivram, A., Ramaiah, C. and Govindaraju, V. (2013) A Hierarchical Bayesian Approach to Online Writer Identification. IET Biometrics, 2, 191-198. https://doi.org/10.1049/iet-bmt.2013.0017
[26]
Taghavi Sangdehi, S.A. and Faez, K. (2009) Writer Identification Using Super Paramagnetic Clustering and Spatio Temporal Neural Network. In: Bayro-Corrochano, E. and Eklundh, J.-O., Eds., Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications, Springer, 669-676. https://doi.org/10.1007/978-3-642-10268-4_79
[27]
Bloice, D.M., Stocker, C. and Holzinger, A. (2017) Augmentor: An Image Augmentation Library for Machine Learning. The Journal of Open Source Software, 2, Article No. 432. https://doi.org/10.21105/joss.00432
[28]
Bengio, Y., Ducharme, R., Vincent, P. and Janvin, C. (2003) A Neural Probabilistic Language Model. Journal of Machine Learning Research, 3, 1137-1155.
[29]
Le, Q. and Mikolov, T. (2014) Distributed Representations of Sentences and Documents. Proceedings of the 31st International Conference on Machine Learning, ICML 2014, Beijing, 21-26 June 2014, 1188-1196.
[30]
Hamilton, W.L., Leskovec, J. and Jurafsky, D. (2016) Diachronic Word Embeddings Reveal Statistical Laws of Semantic Change. Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, Volume 1, 1489-1501. https://doi.org/10.18653/v1/p16-1141
[31]
Yin, Z. and Shen, Y. (2018) On the Dimensionality of Word Embedding. Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, NeurIPS 2018, Montréal, 3-8 December 2018, 895-906.
[32]
van der Maaten, L. and Hinton, G. (2008) Visualizing Data Using t-SNE. Journal of Machine Learning Research, 9, 2579-2605.
