-
公开(公告)号：US4982292A
公开(公告)日：1991-01-01
申请号：US252193
申请日：1988-09-30
摘要： A system for processing image data of a text document in compressed form wherein pel signals of the original image are stored in pel positions in an input image buffer and the pel signals stored in every other pel (EOP) positions in the input buffer are sequentially fetched, along with respective pluralities of neighboring pel signals stored in EOP positions and compressed by adaptive arithmetic compression to generate a first set of compressed data which is stored in a memory. The pel signals stored in remaining pel (RP) positions in the input image buffer are also sequentially fetched, along with respective pluralities of neighboring pel signals, including at least one signal stored in an RP position and a plurality of signals stored in EOP positions, and compressed by adaptive arithmetic compression to generate a second set of compressed data which is stored in a memory. The first and second sets of compressed data may be decompressed to reproduce the pel signals stored at EOP positions, and the pel signals stored in RP positions along with their respective pluralities of neighboring pel signals stored in EOP positions, and stored in an output image buffer. The fetching operation includes selecting one of a plurality of sampling windows, each having a different sampling pattern, for sampling the pel signals making up the first and second sets of data during compression and decompression to achieve the improved data volumes.
-
公开(公告)号：US5555362A
公开(公告)日：1996-09-10
申请号：US507061
申请日：1995-07-26
申请人： Akio Yamashita , Kazuharu Toyokawa
发明人： Akio Yamashita , Kazuharu Toyokawa
CPC分类号： G06K9/00463
摘要： The present invention provide a method for extracting a tree structure by using image analysis results of an actual document and generating a flexible layout model. A tree structure and layout model are newly generated by automatically extracting the tree structure in accordance with document image analysis before a user executes graphical correction. That is, an inputted document image is physically analyzed to extract a separator with a high possibility to separate the objects of the document and segment the above document image into a plurality of areas in accordance with the information for the separator. Then, the area segmentation is displayed on a display unit together with a document image and interactively corrected by the user to define a desired tree structure and complete a flexible layout model by setting a parameter to each node of the tree structure.
摘要翻译： 本发明提供一种通过使用实际文档的图像分析结果并生成柔性布局模型来提取树结构的方法。 在用户执行图形校正之前，根据文档图像分析自动提取树结构，新生成树结构和布局模型。 也就是说，物理地分析输入的文档图像以提取分离器的可能性高的分离器，以分离文档的对象并且根据分离器的信息将上述文档图像分割成多个区域。 然后，区域分割与文档图像一起显示在显示单元上，并由用户交互地校正以定义所需的树结构，并通过将参数设置到树结构的每个节点来完成灵活的布局模型。
-
公开(公告)号：US4539506A
公开(公告)日：1985-09-03
申请号：US533481
申请日：1983-09-19
申请人： Hiroko Ohtani , Kazuharu Toyokawa
发明人： Hiroko Ohtani , Kazuharu Toyokawa
CPC分类号： C09K11/883 , H01J29/187
摘要： In a red-emitting phosphor which includes ZnSe as a host material, copper (Cu) as an activator and aluminum (Al) as a coactivator, the improvement comprising the inclusion of a small amount of cobalt (Co) to provide superlinear characteristics to said phosphor in combination with said Cu and Al. A preferred range of concentration of said Co is 10.sup.-6 -2.times.10.sup.-5 g atom/mol. A specific application of said red-emitting superlinear phosphor is as a phosphor screen for a current density sensitive, single gun color CRT, when mixed with a green-emitting sublinear phosphor.
摘要翻译： 在包含作为主体材料的ZnSe，作为活化剂的铜（Cu）和作为共活化剂的铝（Al））的红色发光荧光体中，改进包括含有少量的钴（Co）以提供所述 荧光粉与所述Cu和Al组合。 所述Co的优选浓度范围为10-6-2×10-5g原子/ mol。 当与绿色发射的亚线性荧光体混合时，所述红色发射超级线性荧光体的具体应用是用于电流密度敏感的单枪彩色CRT的荧光屏。
-
公开(公告)号：US5832108A
公开(公告)日：1998-11-03
申请号：US707888
申请日：1996-09-09
申请人： Masayuki Fukita , Kazuharu Toyokawa , Shin Katoh
发明人： Masayuki Fukita , Kazuharu Toyokawa , Shin Katoh
CPC分类号： G06K9/66
摘要： An interval �0, 1! of the output of neural network is equally divided into M (M being an integer of two or more), and the numbers or frequencies of data for the correct/incorrect patterns contained in the i-th interval �(i-1)/M, i/M! are .mu.1i and .mu.0i, respectively (where, i=1 . . . M). In this case, if this network provides an output contained in the i-th interval to unknown pattern data, this pattern is stored as a likelihood conversion table so that the pattern outputs likelihood P1i, which is a category, in an equation P1i=(.mu.1i+1)/(.mu.1i+.mu.0i+2). Then, when a value contained in the i-th interval �(i-1)/M, i/M! is output from a neural network, the likelihood convertor receives it as an input and outputs P1i which is so to speak normalized likelihood.
摘要翻译： 神经网络的输出的间隔[0,1]被等分为M（M为2以上的整数），并且第i个区间中包含的正确/不正确模式的数据的数量或频率[ （i-1）/ M，i / M]分别为mu 1i和mu 0i（其中，i = 1 ... M）。 在这种情况下，如果该网络将包含在第i个间隔中的输出提供给未知模式数据，则该模式被存储为似然转换表，使得模式输出作为类别的可能性P1i，在等式P1i =（ mu 1i + 1）/（mu 1i + mu 0i + 2）。 然后，当从神经网络输出第i个区间[（i-1）/ M，i / M]中包含的值时，似然转换器将其作为输入接收，并输出P1i，这样可以说归一化的可能性 。
-
公开(公告)号：US5394484A
公开(公告)日：1995-02-28
申请号：US813239
申请日：1991-12-23
CPC分类号： G06K9/6282 , G06K9/6807
摘要： Character recognition apparatus capable of automatically modifying its recognition tree is disclosed. When a character is erroneously recognized, its image is used to select a leaf node of the character recognition tree which has a high probability of recognizing the character correctly. The tree is split at that node, creating one new leaf node which is assigned to the character formerly assigned to the split node, and a second new leaf node assigned to the erroneously recognized character. The split node is then assigned to test a pel address in a character image which has a high probability of discriminating between the two characters of its new leaf nodes.
摘要翻译： 公开了能够自动修改其识别树的字符识别装置。 当字符被错误识别时，其图像用于选择字符识别树的叶节点，其具有正确识别字符的高概率。 该树在该节点处被分割，创建一个新的叶节点，其被分配给先前分配给分割节点的角色，以及分配给错误识别的角色的第二个新叶节点。 然后，分配节点被分配以测试字符图像中的像素地址，其具有区分新叶节点的两个字符的高概率。
-
公开(公告)号：US4901363A
公开(公告)日：1990-02-13
申请号：US250596
申请日：1988-09-28
申请人： Kazuharu Toyokawa
发明人： Kazuharu Toyokawa
CPC分类号： H04N1/40062 , H04N1/4105
摘要： A system is disclosed for arithmetically compressing bi-level data of an image by sampling history pels, which are adjacent pels to a current pel to be processed, and pels so separated from the adjacent pels as to adapt to a period of a dither matrix for a dither image. From the sampled pels it is determined whether the sampled image has a dither dominant image pattern or a text-graphic dominant image pattern and an appropriate signal is generated, a first signal representing that the image has the dither dominant image pattern, a second signal representing that the image has the text-graphic dominant image pattern, and a third signal representing that the image is not classified as either of these image patterns. The first, second and third signals are applied to an up-down counter which accumulates the occurrences of the signals to produce, when the accumulated value exceeds an upper threshold or a lower threshold, a control signal for selectively switching access to first and second statistical tables, which store, at each entry, the more probable symbol and the probability of the less probable symbol for the image of the text-graphic image and the dither image, respectively.
摘要翻译： 公开了一种用于通过对与要处理的当前像素相邻的像素的历史像素进行算术压缩来对图像进行算术压缩的系统，以及与相邻像素分离的像素，以适应抖动矩阵的周期， 一个抖动的图像。 从采样像素中，确定采样图像是否具有抖动主要图像图案或文本图形主导图像图案，并且生成适当的信号，表示图像具有抖动主要图像图案的第一信号，表示 图像具有文本图形主导图像图案，以及表示图像不被分类为这些图像图案中的任一个的第三信号。 第一，第二和第三信号被施加到升降计数器，其累积信号的出现以在累积值超过上阈值或下阈值时产生用于选择性地切换到第一和第二统计 在每个条目上分别存储更可能的符号和图形图像和抖动图像的图像的可能性较小的符号的概率的表。
-
-
-
-
-
搜索结果
6 条记录 (耗时 0.02 秒)
