白丝美女被狂躁免费视频网站,500av导航大全精品,yw.193.cnc爆乳尤物未满,97se亚洲综合色区,аⅴ天堂中文在线网官网

Handwriting detector, extractor, and language classifier

專利號
US11176361B2
公開日期
2021-11-16
申請人
Raytheon Company(US MA Waltham)
發(fā)明人
Darrell L. Young; Kevin C. Holley
IPC分類
G06F40/171; G06F40/263; G06K9/00; G06K9/34; G06K9/38; G06K9/62; G06K9/68; G06K9/72
技術(shù)領(lǐng)域
language,may,or,in,bounding,be,hardware,features,geometric,image
地域: MA MA Waltham

摘要

Disclosed are methods for handwriting recognition. In some aspects, an image representing a page of a sample document is analyzed to identify a region having indications of handwriting. The region is analyzed to determine frequencies of a plurality of geometric features within the region. The frequencies may be compared to profiles or histograms of known language types, to determine if there are similarities between the frequencies in the sample document relative to those of the known language types. In some aspects, machine learning may be used to characterize the document as a particular language type based on the frequencies of the geometric features.

說明書

Option 1810 may then detect geometric features formed by features within the bounding box. Operation 1810 may detect one or more of loops, line segments, line crossings, line curves, orthogonal intersections, rectangles, squares, polygons, or other geometric features within the bounding box, as described above for example with respect to FIGS. 12-16. Operation 1810 may also detect a frequency of adjoining features within the bounding box. For example, operation 1810 may count a number of times two particular features are positioned next to or adjoining each other in the bounding box.

The counts of each type of geometric feature may then be normalized based on a ratio between the height and width of the bounding box. For example, in some aspects, each count of a particular type of geometric feature may be normalized to identify a frequency of the particular type of geometric feature. One or more of the frequencies may be generated according to:
frequency=count*height/length??(2)

The frequencies for the geometric features may then, in some aspects, be used to generate a histogram, the histogram indicating the frequencies for each of the geometric features. The histogram may be compared to other histograms for documents of known types, to determine which of the other histograms the histogram is most similar to. This may indicate the language of the handwriting.

權(quán)利要求

1
微信群二維碼
意見反饋