专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明授权

US5748807A Method and means for enhancing optical character recognition of printed documents 失效
公开(公告)号：US5748807A
公开(公告)日：1998-05-05
申请号：US138467
申请日：1993-10-15
申请人： Daniel P. Lopresti , Jonathan S. Sandberg
发明人： Daniel P. Lopresti , Jonathan S. Sandberg
IPC分类号： G06F11/10 , G06F17/21 , G06F17/22 , G06K9/03 , G06K9/20 , G06T1/00
CPC分类号： G06K9/2054 , G06K9/03 , G06K2209/01
摘要： A document marker, including first values dependent upon the layout and the contents of the document and assigned by generating or preprocessing software, is provided in machine-readable symbology on the face of a printed version of the document. The marker may include encoded document layout information and values assigned on sequences of the original text, including text-dependent decimation sequences, error correction codes or check-sums. Upon optical character recognition scanning, or other digitizing reproduction, the marker is also scanned. The scanning computer, having corresponding software, assigns second values dependent upon the layout and contents of the reproduced document. Upon comparison of the first and second decimation sequences, line and character errors can be detected and some errors corrected, thereby generating re-aligned candidate sequences. Optional error correction codes can provide further correcting capabilities, as applied to the re-aligned reproduced document sequences; and, an optional check-sum comparison can be utilized to verify the accuracy of the reproduced sequences are correct.

2. 发明授权

US5734882A Pictographic bitmap naming of files in pen-based computer systems 失效
标题翻译：基于笔的计算机系统中的图形位图命名
公开(公告)号：US5734882A
公开(公告)日：1998-03-31
申请号：US462800
申请日：1995-06-05
申请人： Daniel P. Lopresti , Andrew Tomkins
发明人： Daniel P. Lopresti , Andrew Tomkins
IPC分类号： G06F12/00 , G06F17/30
CPC分类号： G06F17/30259 , Y10S707/915 , Y10S707/921 , Y10S707/99936
摘要： A system and method for storage and retrieval of pictographic images as computer file names. Upon generation of an input image, the computer saves the image and extracted spatial and temporal information about the generation of the image. The extracted information can be accessed for comparison, ordering and retrieving of stored pictographic file names and subsequent display to the user. Final selection of the desired name is performed visually by the user while viewing a display of the ordered file names via a document browser.
摘要翻译：用于将图像图像存储和检索为计算机文件名的系统和方法。在生成输入图像时，计算机保存图像并提取关于图像生成的空间和时间信息。所提取的信息可以被访问以用于比较，排序和检索存储的图像文件名和随后的显示给用户。当通过文档浏览器查看有序文件名的显示时，用户可视觉地执行期望名称的最终选择。

3. 发明授权

US5703972A Certifiable optical character recognition 失效
标题翻译：认证光学字符识别
公开(公告)号：US5703972A
公开(公告)日：1997-12-30
申请号：US560299
申请日：1995-11-17
申请人： Daniel P. Lopresti , Henry F. Korth , Jonathan S. Sandberg , Richard J. Lipton
发明人： Daniel P. Lopresti , Henry F. Korth , Jonathan S. Sandberg , Richard J. Lipton
IPC分类号： G06K9/03 , G06K9/20 , G06T1/00
CPC分类号： G06K9/2054 , G06K9/03 , G06K2209/01
摘要： A certificate, calculated on the text of a document to be reproduced, is included in the document in a form which is machine-readable. Upon optical character recognition scanning, or other digitizing reproduction, the certificate is also scanned and stored for comparison. A new certificate is calculated on the contents of the reproduced document and compared to the scanned certificate. If the two certificates are different, it is known that at least one error exists in the reproduced document. More than one certificate can be provided for a document in order to facilitate error location on the document and error correction therein.
摘要翻译：根据要复制的文档的文本计算的证书以机器可读的形式包含在文档中。在进行光学字符识别扫描或其他数字化再现时，也扫描和存储证书以进行比较。根据复制的文件的内容计算新的证书，并与扫描的证书进行比较。如果两个证书不同，则已知在再现的文档中存在至少一个错误。可以为文档提供多个证书，以便于文档上的错误位置和错误更正。

4. 发明授权

US5696878A Speaker normalization using constrained spectra shifts in auditory filter domain 失效
标题翻译：在听觉滤波器域中使用约束光谱位移的扬声器归一化
公开(公告)号：US5696878A
公开(公告)日：1997-12-09
申请号：US123637
申请日：1993-09-17
申请人： Yoshio Ono , Yunxin Zhao , Hisashi Wakita
发明人： Yoshio Ono , Yunxin Zhao , Hisashi Wakita
IPC分类号： G10L11/00 , G10L15/00 , G10L5/06
CPC分类号： G10L25/48 , G10L15/00 , G10L25/18 , G10L25/24
摘要： A speaker normalization method is described based on spectral shifts in the auditory filter domain. The method is characterized by using an estimated vocal tract length as a criterion to determine the spectral shift value. Certain constraints are found to be necessary for the shift in the auditory filter domain, and two techniques based on these constraints, the One-Bark shift and the refined Bark-scale shift, are introduced. When tested in vowel classification experiments, significant performance improvement was obtained for both techniques. The method is useful for speaker normalization in speaker-independent speech recognition.
摘要翻译：基于听觉滤波器域中的频谱偏移来描述扬声器归一化方法。该方法的特征在于使用估计的声道长度作为确定光谱偏移值的标准。发现某些约束对于听觉滤波器域中的移位是必要的，并且基于这些约束的两种技术，即单树皮移位和精细的巴克尺度位移被引入。当在元音分类实验中进行测试时，两种技术都获得了显着的性能改进。该方法对于与说话者无关的语音识别中的扬声器归一化是有用的。

5. 发明授权

US5610604A Analog to digital converter providing varying digital resolution 失效
标题翻译：模数转换器提供不同的数字分辨率
公开(公告)号：US5610604A
公开(公告)日：1997-03-11
申请号：US350953
申请日：1994-12-07
申请人： Thomas J. Leacock , Robert J. Topper
发明人： Thomas J. Leacock , Robert J. Topper
IPC分类号： H03M1/36
CPC分类号： H03M1/367
摘要： An analog to digital converter which includes a resistive network for generating a number of first reference voltages related to each other by a first linear relationship and a number of second reference voltages related to each other by a second linear relationship, where the first linear relationship is different from the second linear relationship. Also included are first comparators which compare an analog signal to each one of the first reference voltages to produce specified first comparator signals where a respective comparator of the first comparators is provided for each of the first reference voltages. Second comparators are provided to compare the analog signal to each of the second reference voltages to produce second comparator signals where a respective comparator of the second comparators is provided for each one of the second reference voltages. Also included is an encoder to directly convert the first comparator signals and the second comparator signals to a linear digital encoded signal having respecting different quantization resolutions in different parts of its range.
摘要翻译：一种模数转换器，其包括用于通过第一线性关系产生彼此相关的多个第一参考电压的电阻网络和通过第二线性关系彼此相关的第二参考电压的数量，其中第一线性关系是与第二线性关系不同。还包括第一比较器，其将模拟信号与第一参考电压中的每一个进行比较，以产生指定的第一比较器信号，其中为每个第一参考电压提供第一比较器的相应比较器。提供第二比较器以将模拟信号与每个第二参考电压进行比较，以产生第二比较器信号，其中为每个第二参考电压提供第二比较器的相应比较器。还包括一个编码器，用于将第一比较器信号和第二比较器信号直接转换为在其范围的不同部分中具有不同量化分辨率的线性数字编码信号。

6. 发明授权

US5548332A Apparatus and method for black shading correction 失效
标题翻译：用于黑色阴影校正的装置和方法
公开(公告)号：US5548332A
公开(公告)日：1996-08-20
申请号：US427657
申请日：1995-04-21
申请人： Robert J. Topper , Lee R. Dischert
发明人： Robert J. Topper , Lee R. Dischert
IPC分类号： H04N5/365 , H04N9/64 , H04N5/217
CPC分类号： H04N5/3656
摘要： A technique is disclosed for correcting black shading errors in a video camera. The technique involves calculating a horizontal correction waveform as a function of the average pixel values for the columns of a field. Next, a vertical correction waveform is calculated as a function of the average pixel values for the rows of a field. Then, calculation of a diagonal correction waveform as a function of the average pixel values along predetermined diagonals is performed. Finally, an input video signal representing real images is combined with the correction waveforms to produce a video output signal having substantially reduced black shading errors. Correction waveforms can be determined in any order.
摘要翻译：公开了一种用于校正摄像机中的黑色阴影错误的技术。该技术包括计算作为场的列的平均像素值的函数的水平校正波形。接下来，根据场的行的平均像素值来计算垂直校正波形。然后，执行沿着预定对角线的平均像素值的对角线校正波形的计算。最后，将表示真实图像的输入视频信号与校正波形组合，以产生具有显着减小的黑色阴影误差的视频输出信号。校正波形可以任意顺序确定。

7. 发明授权

US5536171A Synthesis-based speech training system and method 失效
标题翻译：综合语音训练系统及方法
公开(公告)号：US5536171A
公开(公告)日：1996-07-16
申请号：US226648
申请日：1994-04-12
申请人： Hector R. Javkin , Elizabeth G. Keate , Norma Antonanzas-Barroso , Brian A. Hanson
发明人： Hector R. Javkin , Elizabeth G. Keate , Norma Antonanzas-Barroso , Brian A. Hanson
IPC分类号： G09B5/06 , G09B19/04 , G09B19/06 , G09B21/00 , G10L13/00 , G10L15/00 , G10L15/02 , G10L21/06 , H04R1/42 , G09B9/00
CPC分类号： G09B5/065 , G09B19/04
摘要： This invention includes a speech training system that allows a student to enter any utterance to be learned and have the articulatory model movements required to produce the utterance displayed on a CRT screen. The system accepts a typed utterance, breaking it down into a set of speech units which could be phonemes or syllables and the onset and offset of the speech units. The set of speech units is sent to a synthesizer, which produces a set of parameters indicating the acoustic characteristics of the utterance. The acoustic parameters are converted into articulatory parameters emphasizing the frequency and nasality required to produce the typed utterance. The speech units and onset and offset of each are used to generate tongue-palate contact patterns required to produce the typed utterance. The articulatory parameters are displayed on the CRT screen. The acoustic parameters are also sent to a formant synthesizer which converts the parameters into speech output. The system measures a student's production and then evaluates the student's production against the parameters of the typed utterance for its similarity. Feedback on the similarity is displayed on the CRT screen.
摘要翻译：本发明包括语音训练系统，其允许学生输入要学习的任何话语，并且具有产生在CRT屏幕上显示的话语所需的发音模型移动。系统接受类型的话语，将其分解成一组可能是音素或音节的语音单元以及语音单元的开始和偏移。该组语音单元被发送到合成器，该合成器产生一组指示话音的声学特性的参数。声学参数被转换为强调产生类型语音所需的频率和鼻音的发音参数。语音单元和每个的开始和偏移用于产生产生类型语音所需的舌头接触模式。发音参数显示在CRT屏幕上。声学参数也被发送到共振峰合成器，其将参数转换成语音输出。该系统测量学生的生产，然后根据类型语音的相似性参数评估学生的生产。相似性的反馈显示在CRT屏幕上。

8. 发明授权

US5510743A Apparatus and a method for restoring an A-level clipped signal 失效
标题翻译：用于恢复A电平限幅信号的装置和方法
公开(公告)号：US5510743A
公开(公告)日：1996-04-23
申请号：US274821
申请日：1994-07-14
申请人： Qun Shi
发明人： Qun Shi
IPC分类号： H04B10/04 , H03F1/32 , H03G3/00 , H03G3/34 , H04B10/06 , H04B10/14 , H04B10/18 , H04B10/26 , H04B10/28
CPC分类号： H04B10/2507 , H03F1/3252 , H03G3/005 , H03G3/345
摘要： A circuit which restores portions of an input signal lost due to clipping distortion includes a comparator which locates the portions of the input signal which have been subject to clipping distortion and generates a pulse signal where each pulse corresponds to a clipped portion of the input signal. This pulse signal is used to generate parabolic pulses which are combined with the input signal to generate a modified signal that approximates the input signal without the clipping distortion. One circuit generates the pulse signals by controlling an oscillator to produce a parabolic pulse train which changes in frequency and amplitude to match each pulse of the pulse signal and then selecting one of the parabolic pulses for each pulse of the pulse signal. Another circuit generates the parabolic pulses by doubly integrating the pulses of the pulse signal.
摘要翻译：恢复由于削波失真而丢失的输入信号的部分的电路包括：比较器，其定位已经受到削波失真的输入信号的部分，并产生脉冲信号，其中每个脉冲对应于输入信号的限幅部分。该脉冲信号用于产生与输入信号组合的抛物线脉冲，以产生近似输入信号而没有限幅失真的修正信号。一个电路通过控制振荡器产生脉冲信号来产生抛物线脉冲串，其频率和幅度发生变化以匹配脉冲信号的每个脉冲，然后为脉冲信号的每个脉冲选择一个抛物线脉冲。另一电路通过对脉冲信号的脉冲进行双积分来产生抛物线脉冲。

9. 发明授权

US5500794A Distribution system and method for menu-driven user interface 失效
标题翻译：菜单驱动用户界面的分发系统和方法
公开(公告)号：US5500794A
公开(公告)日：1996-03-19
申请号：US221685
申请日：1994-03-31
申请人： Yosuke Fujita , Steve P. Lam
发明人： Yosuke Fujita , Steve P. Lam
IPC分类号： H02J13/00 , G05B15/02
CPC分类号： H02J13/001 , H02J13/0086 , Y04S10/40
摘要： An apparatus for distributing control menus over a multi-channel distribution network such as a CEBus throughout a home is disclosed. The apparatus includes a controller such as a personal computer for centrally generating control menus as video information on available channels of the multi-channel distribution network. The controller also executes commands received over the distribution network. The apparatus further includes a display device such as a TV for receiving and displaying the control menu on the channel selected by the control means and a receiver, located proximate to the display device, for receiving user commands related to the displayed menu and for delivering the user commands, via the distribution network, to the control processor. User commands can be given using, for example, infra-red transmission or voice recognition circuitry.
摘要翻译：公开了一种用于在整个家庭内的诸如CEBus之类的多渠道分配网络上分发控制菜单的装置。该装置包括诸如个人计算机的控制器，用于将多个频道分配网络的可用频道的视频信息集中生成控制菜单。控制器还执行通过分配网络接收的命令。该装置还包括诸如TV的显示装置，用于接收和显示由控制装置选择的频道上的控制菜单和位于显示装置附近的接收器，用于接收与所显示的菜单相关的用户命令，并用于传送用户通过分发网络命令到控制处理器。可以使用例如红外线传输或语音识别电路来给出用户命令。

10. 发明授权

US5376962A Neural network video image processor 失效
标题翻译：神经网络视频图像处理器
公开(公告)号：US5376962A
公开(公告)日：1994-12-27
申请号：US119873
申请日：1993-09-10
申请人： Anthony Zortea
发明人： Anthony Zortea
IPC分类号： H04N5/14 , G06N3/00 , G06N3/06 , G06N3/08 , G06T5/00 , H04N9/04 , H04N9/64
CPC分类号： H04N9/045 , G06T5/007 , G06T2207/20084
摘要： A signal processing system for a video camera uses a single neural network to implement multiple nonlinear signal processing functions. In one example, the neural network implements gamma correction, contrast compression, color correction, high pass filtering and aperture correction as a combined function which is emulated by the network. The network is trained off-line using back propagation to emulate the entire composite function for a set of parameters which results in multiple sets of weighting factors. Then, using the stored multiple sets of weighting factors as initial values, the neural network is "re-trained" on-line for each new parameter setting. The use of a single neural network in place of the multiple dedicated processing functions reduces engineering effort to develop the product and may reduce the cost of the total system.
摘要翻译：用于摄像机的信号处理系统使用单个神经网络来实现多个非线性信号处理功能。在一个示例中，神经网络实现了由网络模拟的组合功能的伽马校正，对比度压缩，颜色校正，高通滤波和孔径校正。使用反向传播离线训练网络，以对一组参数进行模拟整个复合函数，该参数导致多组加权因子。然后，使用存储的多组加权因子作为初始值，神经网络在线为每个新参数设置“重新训练”。使用单个神经网络代替多个专用处理功能减少了开发产品的工程努力，并可能降低整个系统的成本。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式