arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2304.09469cs.CV
收藏

Baybayin字符实例检测

Baybayin Character Instance Detection

De La Salle University(德拉萨大学)

Adriel Isaiah V. Amoguis, Gian Joseph B. Madrid, Benito Miguel D. Flores, Macario O. Cordel

AI总结:

针对Baybayin文字识别受限于受控输入和变音符号支持不足的问题,提出基于CNN的端到端字符实例检测、分割与分类模型,并取得优异检测性能。

摘要:

菲律宾政府最近通过了《国家书写系统法》,推动在菲律宾文本中使用Baybayin。为支持这项推广Baybayin使用的工作,我们提出了一种计算机视觉系统,可帮助难以阅读Baybayin文字的人。本文综述了利用计算机视觉和机器学习技术识别Baybayin文字的现有方法,并讨论了其能力与局限。此外,我们提出了一种Baybayin光学字符实例分割与分类模型,该模型采用最先进的卷积神经网络(CNN),先检测图像中的Baybayin字符实例,然后输出图像中每个字符实例对应的拉丁字母。大多数现有系统局限于字符级图像分类,并且经常误分类带变音符号的字符,或不能原生支持这些字符。此外,这些现有模型通常具有特定的输入要求,使其只能在受控环境中分类Baybayin文本,例如在清晰度和对比度等方面存在限制。据我们所知,我们提出的方法是首个面向Baybayin的端到端字符实例检测模型,取得了93.30%的mAP50分数、80.50%的mAP50-95分数以及84.84%的F1-Score。

英文摘要:

The Philippine Government recently passed the "National Writing System Act," which promotes using Baybayin in Philippine texts. In support of this effort to promote the use of Baybayin, we present a computer vision system which can aid individuals who cannot easily read Baybayin script. In this paper, we survey the existing methods of identifying Baybayin scripts using computer vision and machine learning techniques and discuss their capabilities and limitations. Further, we propose a Baybayin Optical Character Instance Segmentation and Classification model using state-of-the-art Convolutional Neural Networks (CNNs) that detect Baybayin character instances in an image then outputs the Latin alphabet counterparts of each character instance in the image. Most existing systems are limited to character-level image classification and often misclassify or not natively support characters with diacritics. In addition, these existing models often have specific input requirements that limit it to classifying Baybayin text in a controlled setting, such as limitations in clarity and contrast, among others. To our knowledge, our proposed method is the first end-to-end character instance detection model for Baybayin, achieving a mAP50 score of 93.30%, mAP50-95 score of 80.50%, and F1-Score of 84.84%.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑