Recognizing Cuneiform Signs Using Graph Based Methods

نویسندگان

  • Nils M. Kriege
  • Matthias Fey
  • Denis Fisseler
  • Petra Mutzel
  • Frank Weichert
چکیده

The cuneiform script constitutes one of the earliest systems of writing and is realized by wedge-shaped marks on clay tablets. A tremendous number of cuneiform tablets have already been discovered and are incrementally digitalized and made available to automated processing. As reading cuneiform script is still a manual task, we address the real-world application of recognizing cuneiform signs by two graph based methods with complementary runtime characteristics. We present a graph model for cuneiform signs together with a tailored distance measure based on the concept of the graph edit distance. We propose efficient heuristics for its computation and demonstrate its effectiveness in classification tasks experimentally. To this end, the distance measure is used to implement a nearest neighbor classifier leading to a high computational cost for the prediction phase with increasing training set size. In order to overcome this issue, we propose to use CNNs adapted to graphs as an alternative approach shifting the computational cost to the training phase. We demonstrate the practicability of both approaches in an experimental comparison regarding runtime and prediction accuracy. Although currently available annotated real-world data is still limited, we obtain a high accuracy using CNNs, in particular, when the training set is enriched by augmented examples.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

An additional middle cuneiform?

Additional cuneiform bones of the foot have been described in reference to the medial bipartite cuneiform or as small accessory ossicles. An additional middle cuneiform has not been previously documented. We present the case of a patient with an additional ossicle that has the appearance and location of an additional middle cuneiform. Recognizing such an anatomical anomaly is essential for ruli...

متن کامل

Cuneiform Detection in Vectorized Raster Images

Documents written in cuneiform script are one of the largest sources about ancient history. The script is written by imprinting wedges (Latin: cunei) into clay tablets and was used for almost four millennia. This three-dimensional script is typically transcribed by hand with ink on paper. These transcriptions are available in large quantities as raster graphics by online sources like the Cuneif...

متن کامل

Real Scene Sign Recognition

A common problem encountered in recognizing signs in realscene images is the perspective deformation. In this paper, we employ a descriptor named Cross Ratio Spectrum for recognizing real scene signs. Particularly, this method will be applied in two different ways: recognizing a multi-component sign as an whole entity or recognizing individual components separately. For the second strategy, a g...

متن کامل

A Remarkable Collection of Babylonian Mathematical Texts

A bout 120 new Mesopotamian mathematical cuneiform texts, all from the Norwegian Schøyen Collection, are published in the author’s book A Remarkable Collection of Babylonian Mathematical Texts, Springer (2007). Most of the texts are Old Babylonian (1900–1600 BC), but some are older (Sumerian), or younger (Kassite). In addition to the presentation and discussion of these new texts, the book cont...

متن کامل

Toward Automatically Assembling Hittite-Language Cuneiform Tablet Fragments into Larger Texts

This paper presents the problem within Hittite and Ancient Near Eastern studies of fragmented and damaged cuneiform texts, and proposes to use well-known text classification metrics, in combination with some facts about the structure of Hittite-language cuneiform texts, to help classify a number of fragments of clay cuneiform-script tablets into more complete texts. In particular, I propose usi...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:
  • CoRR

دوره abs/1802.05908  شماره 

صفحات  -

تاریخ انتشار 2018