专利名称：Spatial recognition and grouping of text and
graphics
发明人：Michael Shilman,Paul A. Viola,Kumar H.
Chellapilla
申请号：US10927452申请日：20040826
公开号：US20060045337A1公开日：20060302
专利附图：
摘要：The present invention leverages spatial relationships to provide a systematicmeans to recognize text and/or graphics. This allows augmentation of a sketched shape
with its symbolic meaning, enabling numerous features including smart editing,beautification, and interactive simulation of visual languages. The spatial recognitionmethod obtains a search-based optimization over a large space of possible groupingsfrom simultaneously grouped and recognized sketched shapes. The optimization utilizesa classifier that assigns a class label to a collection of strokes. The overall groupingoptimization assumes the properties of the classifier so that if the classifier is scale androtation invariant the optimization will be as well. Instances of the present inventionemploy a variant of AdaBoost to facilitate in recognizing/classifying symbols. Instances ofthe present invention employ dynamic programming and/or A-star search to performoptimization. The present invention applies to both hand-sketched shapes and printedhandwritten text, and even heterogeneous mixtures of the two.
申请人：Michael Shilman,Paul A. Viola,Kumar H. Chellapilla
地址：Seattle WA US,Kirkland WA US,Sammamish WA US
国籍：US,US,US
更多信息请下载全文后查看
因篇幅问题不能全部显示，请点此查看更多更全内容