首页>
外国专利>
METHODS AND SYSTEMS OF AUTOMATIC RECOGNITION OF SYMBOLS USING A TREE OF DECISIONS
METHODS AND SYSTEMS OF AUTOMATIC RECOGNITION OF SYMBOLS USING A TREE OF DECISIONS
展开▼
机译:基于决策树的符号自动识别方法和系统
展开▼
页面导航
摘要
著录项
相似文献
摘要
1. An optical character recognition system comprising: one or more processors; one or more memory modules; one or more storage devices; machine code instructions stored in one or more of one or more memory devices when one or more of one or more processors are executed control an optical character recognition system for processing a text-scanned image of a document by: identifying symbol images in a scanned image of a document; for each identified symbol image, starting from the root node of the decision tree stored in the optical character recognition system, recursively bypassing the roar of decisions until the classifier in the decision tree node recognizes the image of the symbol; and presenting a symbol image using a symbol code associated with the classifier, and preparing a processed document containing symbol codes that are symbol images in the image of the scanned document and storing the processed document in one or more of one or more data storage devices and memory devices. 2. The optical character recognition system according to claim 1, characterized in that the decision tree contains: a root node that contains a classifier; several nodes of an intermediate level, each of which contains a classifier; several final nodes, each of which contains several classifiers. 3. The optical character recognition system according to claim 2, characterized in that the decision tree under construction is in each root node and an intermediate level node, each of which
展开▼