Process and device for the automatic segmentation of a scanned image in
an image pattern recognition system
    1.
    发明授权
    Process and device for the automatic segmentation of a scanned image in an image pattern recognition system 失效
    用于在图像模式识别系统中自动分割扫描图像的过程和装置

    公开(公告)号:US4504971A

    公开(公告)日:1985-03-12

    申请号:US370360

    申请日:1982-04-21

    申请人: Morton Nadler

    发明人: Morton Nadler

    IPC分类号: G06T7/00 G06K9/34 G06K9/46

    CPC分类号: G06K9/342 G06K2209/01

    摘要: A pattern recognition system comprising scanning means (1) for producing a binary signal indicative of the state of the elementary areas in successively scanned columns of elementary areas and segmentation means to separate from said signal data relating to individual discrete graphic objects in the scanned pattern and to store the separated data in individual storage zones of a memory array, characterized in that said segmentation means comprise a QTC generator (2) for producing quasitopological codes indicative of predetermined states of successive elementary areas using the data in the signal of each successive scanned column and the data in the signal of the last previously scanned column, and for producing therefrom a start and a stop signals at the beginning and end of any series of data corresponding to a fragment of a graphic object, the succession of codes being different depending on whether a fragment detected in the signal is or is not continued from last previously scanned column, and assignment control means (3) for assigning a selected memory zone of a memory array (4) to any said series of data depending on the codes allotted at the beginning and end of the fragment, and controlling the delivery of said series of data to said selected memory zone.

    摘要翻译: 一种模式识别系统,包括用于产生指示基本区域的连续扫描列中的基本区域的状态的二进制信号的扫描装置和用于与扫描图案中的各个离散图形对象相关的信号数据分离的分割装置,以及 将分离的数据存储在存储器阵列的各个存储区域中,其特征在于,所述分段装置包括QTC发生器(2),用于使用每个连续扫描列的信号中的数据产生指示连续基本区域的预定状态的准子代码 以及最后先前扫描的列的信号中的数据,并且由此产生与图形对象的片段相对应的任何一系列数据的开始和结束处的起始和停止信号,依赖于 信号中检测到的片段是否是从上一次扫描过的或不继续的 列和分配控制装置(3),用于根据在片段的开头和结尾分配的代码将存储器阵列(4)的选定存储区分配给任何所述一系列数据,并且控制所述一系列 数据到所选择的存储区。

    Method and device for image analysis
    2.
    发明授权
    Method and device for image analysis 失效
    图像分析方法和装置

    公开(公告)号:US4418362A

    公开(公告)日:1983-11-29

    申请号:US335087

    申请日:1981-12-28

    申请人: Morton Nadler

    发明人: Morton Nadler

    摘要: A device for image analysis comprising scanner (1) for producing a video signal indicative of the light intensity received at successive regular time intervals from an image scanned along a first direction at an automatically controlled known motion velocity and along a second direction at an unknown motion velocity, characterized in that it further comprises circuits (2,5) for determining a reference contrast value from the difference between light intensities received from points of the image scanned along the first direction, circuits (3,6) for determining a variable contrast value from the difference between light intensities received from points of the image scanned along the second direction, circuit (7) for comparing the variable contrast value with the reference contrast value, and circuits (8,10) for using the comparison for compensating for the unknown motion velocity in the production of the video signal.

    摘要翻译: 一种用于图像分析的装置,包括扫描器(1),用于产生指示以连续的规则时间间隔从以第一方向以自动控制的已知运动速度扫描的图像以及以未知运动的第二方向接收的指示光强度的视频信号 速度,其特征在于,其还包括用于根据从沿着第一方向扫描的图像的点接收的光强度之间的差来确定参考对比度值的电路(2,5),用于确定可变对比度值的电路(3,6) 从根据沿着第二方向扫描的图像的点接收的光强度之间的差异,用于将可变对比度值与参考对比度值进行比较的电路(7)以及用于补偿未知的比较的电路(8,10) 运动速度在视频信号的制作中。

    Method and apparatus for visual telecommunications, in particular for
use by the deaf
    3.
    发明授权
    Method and apparatus for visual telecommunications, in particular for use by the deaf 失效
    用于视觉通信的方法和装置,特别是由聋人使用

    公开(公告)号:US4546383A

    公开(公告)日:1985-10-08

    申请号:US505309

    申请日:1983-06-17

    IPC分类号: G09B21/00 G09B21/06 H04N7/14

    CPC分类号: G09B21/009 G09B21/06

    摘要: In a system for visual telecommunications, e.g. for use by deaf people, an electronic camera (20) makes an image of a moving subject for transmission. The TV type image is passed through a contour extractor (25) to be converted to an animated cartoon line-drawing type image. The contour image is then compressed by means including a sampler (28) for image reduction, a difference detector (30) for selecting only points which change from one image to the next, a filter (34) for rejecting isolated points in the contour image, and an encoder (36) for converting sequences of on/off bits into data words for transmission, via a modem (14) over a telephone line (15). At the other end of the line a similar transmitter/receiver system decodes the received words and reconstitutes the successive images for display on a screen (46). The resulting animated cartoon type of display is adequate for communication by sign language or by lip reading, and is capable of being sufficiently compressed to be transmitted over a normal telephone line.

    摘要翻译: 在用于视觉通信的系统中,例如, 为了聋人使用,电子照相机(20)使得移动的被摄体的图像被传送。 电视类型图像通过轮廓提取器(25),以转换为动画卡通图形类型图像。 然后通过包括用于图像缩小的采样器(28),用于仅选择从一个图像变化到下一个图像的点的差分检测器(30),用于拒绝轮廓图像中的孤立点的滤波器(34) ,以及用于经由调制解调器(14)经由电话线(15)将开/关位序​​列转换为数据字以进行传输的编码器(36)。 在线路的另一端,类似的发射机/接收机系统对所接收的话音进行解码,并重新构成连续的图像以在屏幕(46)上显示。 所得到的动画卡通类型的显示器对于通过手语或唇读取的通信是足够的,并且能够被充分压缩以通过普通电话线传输。

    Process and device for the binarization of a pattern
    4.
    发明授权
    Process and device for the binarization of a pattern 失效
    模式二值化的过程和设备

    公开(公告)号:US4509195A

    公开(公告)日:1985-04-02

    申请号:US334468

    申请日:1981-12-28

    申请人: Morton Nadler

    发明人: Morton Nadler

    IPC分类号: G06K9/38 G06T5/00 G06K9/36

    CPC分类号: G06K9/38

    摘要: The device of the invention allows the binarized evaluation of a pattern from a signal indicative of intensity values of spatially distributed discrete points of the pattern. It comprises circuits for registering the intensity values of points distributed in at least two concentric rings within an elementary area, at least in one sector centered on the elementary area, determining contrast values each equal to the difference of the registered intensity values between a point of an inner ring and a point of an outer ring, and assigning a positive and negative difference sign to respectively the positive and negative contrast values thus determined having an absolute value higher than a predetermined contrast threshold. A counter is provided for counting distinctively the positive and negative difference signs in the vicinity of the elementary area. An evaluation circuit assigns a light or dark quality to the area respectively when the counted difference signals contain a predominant number of positive or negative difference signs by more than a predetermined minimum.

    摘要翻译: 本发明的装置允许从指示图案的空间分布的离散点的强度值的信号对图案进行二值化评估。 它包括用于记录分布在基本区域内的至少两个同心环中的点的强度值的电路,至少在基本区域上的一个扇区中,确定每个等于在一个点之间的注册强度值的差异的对比度值 内圈和外圈的点,并且分别将正和负差分符号分配给具有高于预定对比阈值的绝对值所确定的正和负对比度值。 提供一个计数器用于区分基本区域附近的正和负差异迹象。 当计数的差分信号包含主要数量的正或负差异符号超过预定的最小值时,评估电路分别将光或暗质量分配给该区域。

    Image scanning method and device
    5.
    发明授权
    Image scanning method and device 失效
    图像扫描方法和装置

    公开(公告)号:US4471387A

    公开(公告)日:1984-09-11

    申请号:US339169

    申请日:1982-01-13

    申请人: Morton Nadler

    发明人: Morton Nadler

    摘要: An image scanning method, comprising providing an array of intercalated odd and even detectors, said odd detectors and said even detectors being aligned parallely to a common direction, displacing said array over said image transversely to said direction, repeatedly serially sampling element signals from said detectors, each indicative of the intensity detected by a corresponding detector over an element part of the image, and serially transferring into an image signal a sequence of said element signals sampled from said odd detectors and a sequence said element signal sampled from said even detectors alternately.

    摘要翻译: 一种图像扫描方法,包括提供插入的奇数和偶数检测器的阵列,所述奇数检测器和所述偶数检测器与公共方向平行排列,使所述阵列在所述图像上横向于所述方向移位,从所述检测器重复地串行采样元件信号 每个指示由图像的元件部分上的相应检测器检测到的强度,并且将从所述奇数检测器采样的所述元件信号的序列和从所述偶数检测器交替采样的序列所述元件信号串行传送到图像信号中。

    Method and apparatus for sharpening a grayscale image
    7.
    发明授权
    Method and apparatus for sharpening a grayscale image 失效
    用于锐化灰度图像的方法和装置

    公开(公告)号:US06195467B1

    公开(公告)日:2001-02-27

    申请号:US09276472

    申请日:1999-03-25

    IPC分类号: G06T500

    摘要: A digitized image is treated by an electronic system where pairs of pixels within a convolution window are compared, and for those differences which are greater than a preselected, or automatically calculated, threshold, a black or white vector is counted, respectively, depending on whether the more centrally located pixel is darker or lighter than the outer pixel. The central pixel is replaced with an enhanced value, if it is surrounded by a majority of significantly lighter or darker pixels, as indicated by the black and white vector counts. Weighting factors allows for custom tailoring the enhancement algorithm to suit the need of the particular image.

    摘要翻译: 通过比较卷积窗口内的像素对的电子系统对数字化图像进行处理,对于大于预选或自动计算的阈值的那些差异,分别计算黑色或白色矢量,这取决于是否 位于中心的像素比外部像素更暗或更亮。 如果被黑色和白色矢量计数所指示的大部分显着较亮或较暗的像素包围,则中心像素被替换为增强值。 加权因子允许定制改进算法以适应特定图像的需要。

    Process and device for analyzing and restoring image data in a digital
signal from a scanned document
    8.
    发明授权
    Process and device for analyzing and restoring image data in a digital signal from a scanned document 失效
    用于分析和恢复来自扫描文档的数字信号中的图像数据的处理和设备

    公开(公告)号:US5703971A

    公开(公告)日:1997-12-30

    申请号:US393257

    申请日:1995-02-23

    IPC分类号: G06K9/38 H04N1/403 G06K9/20

    摘要: A process and device for analyzing image data and performing automatic optimization of a black and white image created by a scanner. The process and device performs dynamic thresholding by approximating the information level and the background level at every pixel in the image, the threshold being calculated as a function of the background and information levels at that point, and a characterization process step comparing the pixel intensity at that point with the threshold, so that if the pixel is darker, it is considered to be black, or if it is lighter, it is considered to be white.

    摘要翻译: 用于分析图像数据并执行由扫描仪创建的黑白图像的自动优化的处理和装置。 该过程和设备通过近似图像中每个像素处的信息水平和背景水平来执行动态阈值,该阈值作为该点处背景和信息水平的函数被计算,并且表征处理步骤将 该点与阈值相同,因此如果像素较暗,则认为是黑色,或者如果它较浅,则认为是白色。

    Alphanumeric character identification
    9.
    发明授权
    Alphanumeric character identification 失效
    字母数字字符识别

    公开(公告)号:US4163213A

    公开(公告)日:1979-07-31

    申请号:US847894

    申请日:1977-11-02

    申请人: Morton Nadler

    发明人: Morton Nadler

    IPC分类号: G06K9/50 G06K9/46 G06K9/00

    CPC分类号: G06K9/4638 G06K2209/01

    摘要: The method and apparatus disclosed involve the scanning of a representation of a character by means of at least three frame scans based on respectively different directions, the frame scans developing quasitopological codes (QTC) indicative of character STARTS, OPENINGS, CLOSINGS and FINISHES. The QTC relating to convexity-shapes and concavity-shapes of different segments of the character are then automatically stored in respective groups of storage locations in a store, such that, at the end of the process, the groups storing QTC are functionally arranged approximately in the shape of the character so that the character is at least partially recognizable thereby. Also disclosed is method and apparatus in which at least partial recognition of the character takes place by comparing the distances between selected pairs of QTC. In addition, the recognition process may involve the actual comparison of the list of QTC for the character with a set of lists representing predetermined characters.

    摘要翻译: 所公开的方法和装置包括通过基于分别不同方向的至少三帧扫描来扫描字符的表示,帧扫描开发指示字符STARTS,OPENINGS,关闭和完成的准星体代码(QTC)。 然后,与字符的不同段的凸度形状和凹形形状相关的QTC被自动存储在存储器中的相应存储位置组中,使得在处理结束时,存储QTC的组在功能上大致布置在 字符的形状使得角色至少部分地被识别。 还公开了一种方法和装置,其中通过比较选择的QTC对之间的距离来进行字符的至少部分识别。 此外,识别处理可以涉及将字符的QTC列表与表示预定字符的一组列表的实际比较。

    Analog/digital converter
    10.
    发明授权
    Analog/digital converter 失效
    模/数转换器

    公开(公告)号:US4058806A

    公开(公告)日:1977-11-15

    申请号:US668192

    申请日:1976-03-18

    申请人: Morton Nadler

    发明人: Morton Nadler

    IPC分类号: H03M1/36 H03M1/00 H03K13/175

    CPC分类号: H03M1/64 H03M1/123

    摘要: A procedure for the parallel conversion of an analog signal to a cyclic binary code with one comparison to a threshold per channel, or bit, in which each channel is composed of an analog function generator, characterized by the fact that the transfer function of said generator is constructed in a piecewise-linear manner from a certain number of pairs of segments of straight lines, whose input/output slopes have equal absolute values and opposite signs, where in each pair the lower instantaneous value is selected by an operator MIN, of two arguments, and among all the lower instantaneous values thus selected, the greatest instantaneous value is selected by an operator MAX, of number of arguments equal to the number of pairs of segments that compose the said transfer function, in such manner that the value of the code is zero or one according to whether the instantaneous value at the output of the said function generator is below the value of the threshold of a comparator or above.

    摘要翻译: 一种用于将模拟信号并行转换为循环二进制码的过程,其中一个比较与每个信道或比特的阈值,其中每个信道由模拟函数发生器组成,其特征在于,所述发生器的传递函数 以一定数量的直线段对构成,其输入/输出斜率具有相等的绝对值和相反的符号,其中在每对中由操作者MIN选择较低的瞬时值,两个 参数,并且在如此选择的所有较低的瞬时值中,最大的瞬时值由操作符MAX选择,其数量等于组成所述传递函数的段的对数,以使得 代码是根据所述函数发生器的输出端的瞬时值是否低于比较器或更高的阈值的值而为零或一个。