Detection and recognition method of oracle bone inscription radicals based on deep learning

Abstract

The invention discloses a method for detecting and identifying radicals of oracle bone inscriptions based on deep learning, and mainly relates to the technical field of oracle bone inscription recognition. Follow the steps below: S1: scan or take pictures of the oracle bone inscription rubbings to obtain the oracle bone inscription image; S2: use the maximum extremum stable region algorithm to screen the oracle bone inscription single radical area in the oracle bone inscription image; S3: conduct the selected oracle bone inscription single radical area Ellipse fitting; S4: Use the non-maximum value suppression algorithm to remove redundant or erroneous detection results for the same oracle radical, complete the detection of oracle single radical, and obtain oracle single radical data; S5: use BN‑Lenet network model identification Oracle single radical data. The beneficial effects of the present invention are: higher recognition accuracy can be obtained, at the same time, oracle bone inscriptions are regarded as radical combinations rather than whole character recognition, and new characters in oracle bone inscriptions that have not been interpreted can be recognized, that is, zero-sample learning, which has important application significance for oracle bone inscriptions research .

Description

technical field [0001] The invention relates to the technical field of oracle bone inscriptions identification, in particular to a method for detecting and recognizing oracle bone inscriptions radicals based on deep learning. Background technique [0002] Oracle bone inscription is the earliest mature writing system discovered in China so far. It is the source of Chinese characters and the root of Chinese excellent traditional culture. However, there are still many difficulties in the interpretation of oracle bone inscriptions. Despite the continuous efforts of archaeologists and paleographers, from the perspective of computer vision There are few studies on oracle bone script analysis, and there is no relevant public data set. Although there are some traditional methods to try to recognize oracle bone script, such as the recognition method based on topological registration proposed by Gu Shaotong; Zhou Xinlun et al. The method of identifying oracle bone characters by stroke...

AI Technical Summary

Problems solved by technology

[0002] Oracle bone inscriptions are the earliest mature writing system discovered in China so far. They are the source of Chinese characters and the root of Chinese excellent traditional culture. However, the interpretation of oracle bone inscriptions is still difficult. There are few studies on the analysis of oracle bone inscriptions, and there are no relevant public data sets. Although there are some traditional methods to try to recognize oracle bone inscriptions, such as the recognition method based on topological registration proposed by Gu Shaotong; Zhou Xinlun et al. proposed using graph theory and The method of identifying oracle bone glyphs based on stroke characteristics; Li Feng et al. proposed a method of using graph features to identify oracle bone glyphs; Li Qingsheng et al. proposed a method of using graph isomorphism to identify oracle bone glyphs, but they often only use oracle bone glyphs as a whole It does not consider the similarity and internal structure between different characters, nor does it consider the problem of variant characters in oracle bone inscriptions that are different but still have the same glyph. However, there are a large number of variant characters in oracle bone inscriptions, so the practicability is limited

Images