Recognition of Oracle Bone Inscriptions by Extracting Line Features on Image Processing
Recognition of Oracle Bone Inscriptions by Extracting Line Features on Image Processing
复制标题
DOI：
10.5220/0006225706060611
复制
发表时间：
2017
期刊：
影响因子：
--
通讯作者：
Lin Meng
中科院分区：
文献类型：
--
作者：
Lin Meng
甲骨文是距今3000多年前，用锋利的器物刻在牛骨或龟甲上的文字。理解这些铭文可以让我们深入了解世界历史，人物评价，全球天气变化等，然而，由于一些政治原因，铭文一直埋在废墟中，直到大约120年前被发现。老化过程导致铭文变得不那么清晰。本文以甲骨文数据库中的甲骨文B为模板图像，利用甲骨文的线条特征，设计了一个系统，并提出了一种识别方法。首先利用高斯滤波和标号法去除噪声，利用仿射变换和细化提取骨架。然后利用Hough变换，提出了一种聚类的方法来提取直线特征点。最后计算原始图像与模板图像之间直线特征点的最小距离进行识别。实验结果表明，近80%的铭文被识别为最小距离和次小距离。即使在原始图像中存在噪声和倾斜的情况下，也能很好地识别。
Oracle bone inscriptions is a kind of characters, which are i nscr bed on cattle bone or turtle shells with sharp objects about 3000 years ago. Understanding these inscript ions can give us a lot of insight into world history, character evaluations, global weather shifts, etc. Howeve r, for some political reasons the inscriptions remained buried in ruins until their discovery about 120 years ago. Th e aging process has caused the inscriptions to become less legible. In this work, we design a system and pr oposal a recognition method for recognizing oracle bone inscriptions as a template image from an oracle b on inscription database, by using the line feature of the inscriptions. First we use Gaussian filtering and labe ling to reduce noise and use affine transformation and thinning to extract the skeleton. Then we use Hough trans form to extracting the line feature points by proposing a method of clustering. Finally, we calculate the minimum distance of the line feature points between the original image and the template images to perfor m the recognition. Experimental results shows that almost 80% of inscriptions are recognized as the most mi nimum distance and the second-most minimumdistance. And the proposal can recognized well, even if the n oise and tilt happened in original images.