-
公开(公告)号：US3384875A
公开(公告)日：1968-05-21
申请号：US49024465
申请日：1965-09-27
Applicant: IBM
Inventor： BENE JACK F , NELSON PAUL E
CPC classification number: G11C13/048 , G06F9/4425 , G06K9/6807
Abstract: 1,102,359. Character recognition. INTERNATIONAL BUSINESS MACHINES CORPORATION. 1 Sept., 1966 [27 Sept., 1965], No. 38990/66. Heading G4R. A first reference to be cross-correlated with an unknown data set to identify the latter is selected from a plurality of references in a store by addressing the store with one of a set of addresses selected from a control word by logic means. As described, the unknown data set is obtained from " measurements " on the clipped and digitized output of a flying-spot scanner which covers a character on a document in a raster of vertical scans. Correlation commences when the character has been completely scanned, e.g. after a predetermined number of vertical scans. Portions of the control word are accessed from the store. The first byte of the control word contains control data (see below) and is always accessed. In addition, one of the remaining bytes is selected in accordance with (a) whether the document field being scanned contains numeric or alphabetic characters, deduced by the circuitry from the identity of the field as indicated by detecting thick black lines bounding the fields, (b) whether upper or both upper and lower case characters are used, as indicated by a document type switch, (c) whether thin, medium or heavy characters are present, as indicated by the clipping and digitizing circuit. Dependence on font style is also mentioned. This second byte contains a correlation cut-off value (see below), end-of-field and end-of-area bits for controlling termination of correlation, and the address of the first reference word to be correlated with the measurements (unknown data set). This reference word is accessed from store and contains besides the data to be correlated with the measurements, also the address of the next reference word to be used, end-of-field and end-ofarea bits to be compared with those from the control word to control whether this reference word is the last to be used, a code indicating the identity of the character, an additive constant for normalizing the number of mis-matches with respect to this reference word, and a branch address (see below). The correlation cut-off value specifies the maximum number of mismatches which can occur during correlation with the given reference word without ruling-out the code of the word as being possibly the identity of the unknown character, or in another mode (" converging cut-off mode ") it represents the initial value of this maximum. In the second mode the maximum is continually updated. The mode is selected by a bit from the control word. If a given reference word used has less than the maximum number of mismatches, the code from the word is entered into a stored decision word at a byte position determined by the number of mismatches. After the first such code is discovered, the correlation cut-off value is increased by the value of a " minimum distance tolerance " field from the control word. When the series of reference words to be correlated has ended, the decision word is scanned from the least-number-ofmismatehes end to detect any of the identifying codes stored therein. The first code encountered is taken as identifying the character provided it is within the first so many byte positions, as specified by a field (" field recognition threshold ") from the control word, and it is at least so many byte positions from the second code encountered, as specified by another field (" minimum distance criteria ") from the control word. Otherwise, in general, further reference words will be used (the first being taken from the " next address " or " branch address " in the last used reference word, depending on, e.g., the raster height at which the unknown character was scanned) and if these fail to produce positive identification, one or more rescans of the character are performed using a clipping threshold specified by the control word. The maximum number of rescans is also specified by the control word.
-
公开(公告)号：US3588451A
公开(公告)日：1971-06-28
申请号：US3588451D
申请日：1968-07-08
Applicant: IBM
Inventor： NELSON PAUL E
IPC: G06K7/10
CPC classification number: G06K7/1092
Abstract: AN OPTICAL SYSTEM FOR READING MARKS ON A DOCUMENT. EACH MARK AREA IS SCANNED BY A BEAM IN A RASTER PATTERN. THE NUMBER OF TIMES WHICH A MARK IS ENCOUNTERED DURING THE RASTER PATERN SCAN OF A MARK AREA PROVIDES AN INDICATION OF THE EXISTENCE OF A MARK AND THE STRENGTH OF THE EXISTING MARK. ORIENTATION FOR THE RASER PATTERN SCANS IS PROVIDED BY A TIMING MARK ASSOCIATED WITH A LINE OF MARK AREAS.
-
Patent Agency Ranking
公开(公告)号：US3662375A
公开(公告)日：1972-05-09
申请号：US3662375D
申请日：1969-01-10
Applicant: IBM
Inventor： JOHNSTON DAVID L , NELSON PAUL E
CPC classification number: G09G1/18
Abstract: The contents of a matrix-type shift register used in an optical character reader is displayed on command on a cathode ray tube. Display is accomplished by generating a raster pattern scan for each storage position of the shift register, said raster pattern scans being at the same relative positions to one another as the storage positions in the shift register. Each raster pattern scan, referred to as a cell raster, is intensified if the corresponding shift register storage cell contains a video or ''''black bit.'''' If the storage cell does not contain a black bit, the corresponding cell raster is not intensified. A partial outline of all cell rasters may be intensified to provide a visual indication of all cell positions. The resulting pattern displayed by the cathode ray tube is a configuration which corresponds to the configuration of black bits held in the shift register.
Abstract translation: 在光学字符读取器中使用的矩阵型移位寄存器的内容以阴极射线管的命令显示。 通过对移位寄存器的每个存储位置生成光栅图案扫描来实现显示，所述光栅图案扫描与移位寄存器中的存储位置彼此处于相同的相对位置。 如果相应的移位寄存器存储单元包含视频或“黑位”，则每个光栅图案扫描（称为单元格栅格）都会增强。 如果存储单元不包含黑色位，则相应的单元格栅格不会增强。 可以加强所有细胞光栅的部分轮廓，以提供所有细胞位置的视觉指示。 由阴极射线管显示的结果图案是对应于保持在移位寄存器中的黑位的配置的配置。
-
4.发明授权System and method for determining the position, height and width of a character marking 失效用于确定字符标记位置，高度和宽度的系统和方法
公开(公告)号：US3629827A
公开(公告)日：1971-12-21
申请号：US3629827D
申请日：1969-01-13
Applicant: IBM
Inventor： JOHNSTON DAVID L , NELSON PAUL E
CPC classification number: G06K9/32 , G06K2209/01
Abstract: A beam is linearly swept across a character marking and stepped in directions perpendicular to the sweep. The extremes of the marking in four orthogonal directions, as determined during the sweep, are stored for use in controlling the positioning of a recognition scanning beam.
-
公开(公告)号：US3618018A
公开(公告)日：1971-11-02
申请号：US3618018D
申请日：1969-06-02
Applicant: IBM
Inventor： JOHNSTON DAVID L , NELSON PAUL E
CPC classification number: G06K9/32 , G06K2209/01
Abstract: Scan-control apparatus responsive to a format word specifying boundaries of a document field to be scanned generates a series of search patterns for characters within the field. A ''''read'''' command causes a scanning beam to seek the intersection of horizontal and vertical boundaries contained in the format word. A line-search scan travels downward therefrom until black video is detected. A character-search scan then moves horizontally to establish the beginning of a character line. The first character is normalized, a recognition scan is initiated, and the vertical position of the line is digitally recorded. Reaching the format end-of-line boundary, or detection of a number of blank spaces, terminates the ''''read'''' command. Further ''''load-format'''' and ''''read'''' commands cause the beam to seek the format word horizontal boundary and the recorded vertical position. The field is terminated when the vertical format word boundary is attained. Tests for document and read-window ends are provided. Several types of format words enhance the flexibility of the system.
-
公开(公告)号：US3536950A
公开(公告)日：1970-10-27
申请号：US3536950D
申请日：1968-07-15
Applicant: IBM
Inventor： JOHNSTON DAVID L , NELSON PAUL E , HOFFMANN GORDON F
Abstract: 1,252,584. Character recognition. INTERNATIONAL BUSINESS MACHINES CORP. 10 July, 1969 [15 July, 1968], No. 34806/69. Heading G4R. Document scanning apparatus comprises means for scanning a region of a document expected to include a calibration mark in accordance with a scan pattern, the position of the scan pattern being varied by a predetermined amount on detection of an error in the way in which a calibration mark is intercepted during a scanning operation. The document, which is to be read under computer control for character recognition purposes, bears an L-shaped calibration mark, the vertical and horizontal bars of the mark being 400 mils long each and the bar widths being at least 20 mils. The nominal position of the junction of the bars is specified, and the scan starts 200 mils to the left and 200 mils up from this point to perform 12 coincident 420 mil downward sweeps followed by 12 coincident 420 mil leftward sweeps (also starting from the same point). If the condition is satisfied that a 12 mil (or more) length of black is sensed in the same position in every sweep of each set of 12 but not at the beginning, the positions of these blacks on the downward and leftward sweeps are used to derive error voltages subsequently used to correct deflection voltages used in the subsequent scanning of fields for recognition. If the condition is not satisfied the scanning is repeated but with the starting point displaced 20 mils to the right and 20 mils down, if it is still not satisfied, the scanning is repeated again but with the starting point displaced 20 mils to the left and 20 mils up (from the first scanning start point). If it is not satisfied now, the document is rejected. If it is satisfied on the second or third scanning, the error voltages are derived and used as with a successful first scan. The position of the junction of the bars on a first (or master) document is set by the operator on potentiometers and whether this setting is accurate to within 40 mils (both vertically and horizontally) is automatically checked using scanning, a lamp being lit if it is. This provides the nominal position of the bar junction for subsequent use as above. The invention may be used as a modification of the systems of Specifications 1,077,094 and 1,252,583 which are referred to.
-
公开(公告)号：US3440546A
公开(公告)日：1969-04-22
申请号：US3440546D
申请日：1965-11-15
Applicant: IBM
Inventor： NELSON PAUL E
CPC classification number: H03K3/78 , H03K5/15013 , H03K5/159
-
-
-
-
-
-
Search Results
7
records
(took 0.029 seconds)
