-
51.发明授权Methods and apparatus for selecting semantically significant images in a document image without decoding image content 失效在文件图像中选择语义有意义的图像而不对图像内容进行解码的方法和装置
公开(公告)号：US5390259A
公开(公告)日：1995-02-14
申请号：US794191
申请日：1991-11-19
申请人： M. Margaret Withgott , Steven C. Bagley , Dan S. Bloomberg , Daniel P. Huttenlocher , Ronald M. Kaplan , Todd A. Cass , Per-Kristian Halvorsen , Ramana B. Rao , Douglass R. Cutting
发明人： M. Margaret Withgott , Steven C. Bagley , Dan S. Bloomberg , Daniel P. Huttenlocher , Ronald M. Kaplan , Todd A. Cass , Per-Kristian Halvorsen , Ramana B. Rao , Douglass R. Cutting
CPC分类号： G06K9/00442 , G06F17/211 , G06F17/27
摘要： A method and apparatus for processing a document image, using a programmed general or special purpose computer, includes forming the image into image units, and at least one image unit classifier of at least one of the image units is determined, without decoding the content of the at least one of the image units. The classifier of the at least one of the image units is then compared with a classifier of another image unit. The classifier may be image unit length, width, location in the document, font, typeface, cross-section, the number of ascenders, the number of descenders, the average pixel density, the length of the top line contour, the length of the base contour, the location of image units with respect to neighboring image units, vertical position, horizontal inter-image unit spacing, and so forth. The classifier comparison can be a comparison with classifiers of image units of words in a reference table, or with classifiers of other image units in the document. Equivalent classes of image units can be generated, from which word frequency and significance can be determined. The image units can be determined by creating bounding boxes about identifiable segments or extractable units of the image, and can contain a word, a phrase, a letter, a number, a character, a glyph or the like.
摘要翻译： 一种用于使用编程的通用或专用计算机处理文档图像的方法和装置，包括将图像形成为图像单元，并且确定至少一个图像单元的至少一个图像单元分类器，而不对 该至少一个图像单元。 然后将至少一个图像单元的分类器与另一图像单元的分类器进行比较。 分类器可以是图像单元长度，宽度，文档中的位置，字体，字体，横截面，上升数，下降数，平均像素密度，顶线轮廓的长度， 基本轮廓，图像单元相对于相邻图像单元的位置，垂直位置，水平图像间距等。 分类器比较可以是与参考表中的单词的图像单位的分类器或文档中的其他图像单元的分类器的比较。 可以生成等效的图像单位类别，从中可以确定字频率和重要性。 可以通过创建关于图像的可标识段或可提取单元的边界框来确定图像单元，并且可以包含单词，短语，字母，数字，字符，字形等。
-
公开(公告)号：US5355420A
公开(公告)日：1994-10-11
申请号：US963159
申请日：1992-10-19
申请人： Dan S. Bloomberg , Gary E. Kopec
发明人： Dan S. Bloomberg , Gary E. Kopec
CPC分类号： G06K9/3283 , G06T7/004 , H04N1/3878 , G06K2209/01
摘要： A method and apparatus for identifying and correcting for document skew. Lines of a bitmap are scanned and a variance in the number of ON pixels as a function of skew angle is calculated. Skew of the original document occurs when the variance is a maximum.
摘要翻译： 一种用于识别和校正文档偏斜的方法和装置。 扫描位图的行，并计算ON像素数作为偏斜角的函数的变化。 原始文档的偏差发生在方差为最大值时。
-
公开(公告)号：US5276742A
公开(公告)日：1994-01-04
申请号：US794551
申请日：1991-11-19
申请人： Lakshmi Dasari , Dan S. Bloomberg
发明人： Lakshmi Dasari , Dan S. Bloomberg
CPC分类号： G06K9/3208 , G06K2209/01
摘要： A method of apparatus for automatic page orientation of a scanned image which compares the number of character ascending pixels to the number of character descending pixels in the image to determine if the image is properly aligned or is 90.degree. or 180.degree. out of orientation. The method and apparatus includes morphologically processing the bitmap of the scanned image using structuring elements for isolating the character ascenders and descenders. When page orientation is improper, the bitmap image of the scanned image is rotated to correct the misalignment.
摘要翻译： 一种用于扫描图像的自动页面取向的装置的方法，其将角色上升像素的数量与图像中的字符下降像素的数量进行比较，以确定图像是否正确对齐，或者是取向为90度或180度。 所述方法和装置包括使用用于隔离角色上升器和下降器的构造元件形态地处理扫描图像的位图。 当页面方向不正确时，旋转扫描图像的位图图像以更正错位。
-
公开(公告)号：US5187753A
公开(公告)日：1993-02-16
申请号：US448774
申请日：1989-12-08
申请人： Dan S. Bloomberg , Gary E. Kopec
发明人： Dan S. Bloomberg , Gary E. Kopec
CPC分类号： G06K9/3283 , G06T7/004 , H04N1/3878 , G06K2209/01
摘要： A method and apparatus for identifying and correcting for document skew. Lines of a bitmap are scanned and a variance in the number of ON pixels as a function of skew angle is calculated. Skew of the original document occurs when the variance is a maximum. Once the skew has been identified, the document is deskewed accordingly.
摘要翻译： 一种用于识别和校正文档偏斜的方法和装置。 扫描位图的行，并计算作为旋转角度的函数的ON（或OFF）像素数的变化（4,6,8）。 原始文档的偏差发生在方差为最大值时（10）。
-
公开(公告)号：US5168147A
公开(公告)日：1992-12-01
申请号：US560659
申请日：1990-07-31
申请人： Dan S. Bloomberg
发明人： Dan S. Bloomberg
CPC分类号： G06K7/143 , G06K19/06037 , G06K7/0166 , G06K9/18
摘要： Binary image processing techniques are provided for decoding bitmap image space representations of self-clocking glyph shape codes of various types (e.g., codes presented as original or degraded images, with one or a plurality of bits encoded in each glyph, while preserving the discriminability of glyphs that encode different bit values) and for tracking the number and locations of the ambiquities (sometimes referred to herein as "errors") that are encountered during the decoding of such codes. A substantial portion of the image processing that is performed in the illustrated embodiment of this invention is carried out through the use of morphological filtering operations because of the parallelism that is offered by such operations. Moreover, the error detection that is performed in accordance with this invention may be linked to or compared against the error statistics from one or more alternative decoding process, such as the convolution filtering process that is disclosed herein, to increase the reliability of the decoding that is obtained.
-
56.发明授权Identification, characterization, and segmentation of Halftone or stippled regions of binary images by growing a seed to a clipping mask 失效通过将种子生长到剪影面具来识别，表征和分割二进制图像的黑皮书或刺激区域
公开(公告)号：US5131049A
公开(公告)日：1992-07-14
申请号：US448193
申请日：1989-12-08
CPC分类号： H04N1/40062 , G06K9/346 , G06K2209/01
摘要： A method for creating a mask for separating halftone regions in a binary image from other regions comprises: constructing a seed image that includes pixels only in halftone regions and at least one pixel in every halftone region (67); constructing a clipping mask that covers in a connected manner all ON pixels in halftone regions (70); and filling the seed while clipping to the mask (72). Thresholded reductions and morphological operations are preferred.
-
57.发明授权Adaptive scaling for decoding spatially periodic self-clocking glyph shape codes 失效用于解码空间周期性自我时钟字形形状码的自适应缩放
公开(公告)号：US5091966A
公开(公告)日：1992-02-25
申请号：US560658
申请日：1990-07-31
申请人： Dan S. Bloomberg , Robert F. Tow
发明人： Dan S. Bloomberg , Robert F. Tow
CPC分类号： G06K7/143 , G06K19/06037 , G06K9/18
摘要： Weighted and unweighted convolution filtering processes are provided for decoding bitmap image space representations of self-clocking glyph shape codes and for tracking the number and locations of the ambiquities or "errors" that are encountered during the decoding. This error detection may be linked to or compared against the error statistics from an alternative decoding process, such as the binary image processing techniques that are described herein to increase the reliability of the decoding that is obtained.
摘要翻译： 提供加权和未加权卷积滤波处理，用于解码自定时字形形状码的位图图像空间表示，并用于跟踪在解码期间遇到的环境或“错误”的数量和位置。 该错误检测可以链接到来自替代解码过程的错误统计信号，或者与本文所述的二进制图像处理技术相比较以提高所获得的解码的可靠性。
-
公开(公告)号：US5048109A
公开(公告)日：1991-09-10
申请号：US447985
申请日：1989-12-08
CPC分类号： H04N1/38 , G06K9/20 , G06K9/2054 , G06K2209/01
摘要： A method and apparatus for detection of highlighted regions of a document. A document containing highlighted regions is scanned using a gray scale scanner. Morphology and threshold reduction techniques are used to separate highlighted and non-highlighted portions of the docment. Having separated the highlighted and non-highlighted portions, optical character recognition (OCR) techniques can then be used to extract text from the highlighted regions.
摘要翻译： 用于检测文档的突出显示区域的方法和装置。 使用灰度扫描仪扫描包含突出显示区域的文档。 形态和阈值削减技术用于分隔文档的突出显示部分和非突出显示部分。 在分离了突出显示和未突出显示的部分之后，可以使用光学字符识别（OCR）技术从突出显示的区域中提取文本。
-
-
-
-
-
-
-
搜索结果
58 条记录 (耗时 0.039 秒)
