USING HIDDEN MARKOV MODELS
USING HIDDEN MARKOV MODELS
复制标题
使用隐马尔可夫模型
DOI：
--
复制
发表时间：
2007
期刊：
影响因子：
--
通讯作者：
Ichiro Fujinaga
中科院分区：
文献类型：
--
作者：
L. Pugin;J. Burgoyne;Ichiro Fujinaga
尽管光学识别（OMR）稳步改善，但由于其内容的可变性很高，早期文档仍然具有挑战性。在本文中，我们提出了一种使用最大后验（MAP）改编的原始方法，以改善基于隐藏的Markov模型动态的早期命中打印的OMR工具。利用这一事实是，在任何OMR工具的正常使用过程中，将纠正错误，从而实现地面真相，可以实时调整该系统。我们使用250页的音乐和两个程序应用地图适应进行了五个16世纪的音乐打印。只有少数页面，即使基线超过95％，召回率也提高了。
Despite steady improvement in optical music recognition (OMR), early documents remain challenging because of the high variability in their contents. In this paper, we present an original approach using maximum a posteriori (MAP) adaptation to improve an OMR tool for early typographic prints dynamically based on hidden Markov models. Taking advantage of the fact that during the normal usage of any OMR tool, errors will be corrected, and thus ground-truth produced, the system can be adapted in real-time. We experimented with five 16th-century music prints using 250 pages of music and two procedures in applying MAP adaptation. With only a handful of pages, both recall and precision rates improved even when the baseline was above 95 percent.