[go: up one dir, main page]
More Web Proxy on the site http://driver.im/

GB1237534A - Improvements in or relating to pattern recognition systems - Google Patents

Improvements in or relating to pattern recognition systems

Info

Publication number
GB1237534A
GB1237534A GB31941/67A GB3194167A GB1237534A GB 1237534 A GB1237534 A GB 1237534A GB 31941/67 A GB31941/67 A GB 31941/67A GB 3194167 A GB3194167 A GB 3194167A GB 1237534 A GB1237534 A GB 1237534A
Authority
GB
United Kingdom
Prior art keywords
autocorrelation
log
pattern
optical
logging
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Expired
Application number
GB31941/67A
Inventor
Raymond Louis Beurle
Robert Bruce Guy
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
National Research Development Corp UK
Original Assignee
National Research Development Corp UK
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by National Research Development Corp UK filed Critical National Research Development Corp UK
Priority to GB31941/67A priority Critical patent/GB1237534A/en
Publication of GB1237534A publication Critical patent/GB1237534A/en
Expired legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00Arrangements for image or video recognition or understanding
    • G06V10/20Image preprocessing
    • G06V10/24Aligning, centring, orientation detection or correction of the image
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00Arrangements for image or video recognition or understanding
    • G06V10/20Image preprocessing
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00Arrangements for image or video recognition or understanding
    • G06V10/20Image preprocessing
    • G06V10/32Normalisation of the pattern dimensions
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00Arrangements for image or video recognition or understanding
    • G06V10/40Extraction of image or video features
    • G06V10/42Global feature extraction by analysis of the whole pattern, e.g. using frequency domain transformations or autocorrelation
    • G06V10/431Frequency domain transformation; Autocorrelation
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00Arrangements for image or video recognition or understanding
    • G06V10/88Image or video recognition using optical means, e.g. reference filters, holographic masks, frequency domain filters or spatial domain filters

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Image Analysis (AREA)
  • Character Discrimination (AREA)

Abstract

1,237,534. Pattern recognition. NATIONAL RESEARCH DEVELOPMENT CORP. 12 July, 1968 [11 July, 1967], No. 31941/67. Heading G4R. Pattern recognition apparatus transforms a position co-ordinate of the input pattern, or of an autocorrelation function of it, to a logarithmic scale and forms the autocorrelation function of the result to feed recognition means. Autocorrelation can be done: (a) using one or two transparencies of the pattern, by obtaining an optical image through both, or of the one through itself using a mirror (Specification 981,431 is referred to for variations), (b) the pattern can be stored on two charge storage meshes of an image storage tube and a flood of electrons passed through both to an output phosphor, (c) by an electrical network fed by a matrix of photo-cells, (d) by inserting the binarized outputs of a matrix of photo-cells in parallel into each of two shift registers, the second of which is then progressively shifted, each stage of one register being ANDed with the corresponding stage of the other to feed a respective counter, (e) by serializing the binarized outputs of a photo-cell matrix and shifting them into a shift register, each stage except the first of which feeds a respective counter via an AND gate controlled by the first stage, (f) as (e) except that the shift register input comes from a television-type scanner, (g) using tapped delay lines in place of a shift register, but using digital or analogue signals, (h) using a computer. The first autocorrelation, if used, may be partial, permitting detection of particular character features, e.g. vertical, horizontal and oblique straight lines and curves. These features could be cross-correlated before the logging. Logging can be done in the optical case by optical fibres, each going from a position in an input plane to the log of this position in an output plane. The log of the position with polar co-ordinates (r, #) is taken to be the position with rectangular cartesian co-ordinates (log r, #). Alternatively, distorting optical systems or the electron optical equivalent can be used for the logging, or a computer, or in the case of a television type scanner, scan conversion tubes can be used. The logged function may be exponentially weighted using an optical filter, or transformed to its second differential with respect to log r. Intensities are normalized before or after the logging. Recognition can be by use of an optical mask or masks, or an analogous electrical network. The autocorrelations, normalization and logging compensate for non-standard size, mispositioning and rotation of the pattern. If the output is required to be independent of size or rotation only, the second autocorrelation is performed in the log r or # direction only, respectively. Alternatively, the second autocorrelation may be complete in the log r direction and only partial in the # direction, giving independence of size and small rotations. The first autocorrelation is omitted if there can be no mispositioning of the input pattern.
GB31941/67A 1968-07-12 1968-07-12 Improvements in or relating to pattern recognition systems Expired GB1237534A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
GB31941/67A GB1237534A (en) 1968-07-12 1968-07-12 Improvements in or relating to pattern recognition systems

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
GB31941/67A GB1237534A (en) 1968-07-12 1968-07-12 Improvements in or relating to pattern recognition systems

Publications (1)

Publication Number Publication Date
GB1237534A true GB1237534A (en) 1971-06-30

Family

ID=10330674

Family Applications (1)

Application Number Title Priority Date Filing Date
GB31941/67A Expired GB1237534A (en) 1968-07-12 1968-07-12 Improvements in or relating to pattern recognition systems

Country Status (1)

Country Link
GB (1) GB1237534A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4745633A (en) * 1986-08-18 1988-05-17 Peter Waksman Optical image encoding and comparing using scan autocorrelation

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4745633A (en) * 1986-08-18 1988-05-17 Peter Waksman Optical image encoding and comparing using scan autocorrelation

Similar Documents

Publication Publication Date Title
Rosenfeld et al. Edge and curve detection: Further experiments
US3429990A (en) Scanning raster generator
US2415191A (en) Electronic computer
GB607397A (en) Improvements in and relating to electrical computing circuits
GB1400471A (en) Apparatus for automatic computation of cardiothoracic ratio
GB1237534A (en) Improvements in or relating to pattern recognition systems
GB908783A (en) Improvements in or relating to devices for converting radiation images into colour component signals
GB1526556A (en) Measuring radiation absorption or radiation emission
US4016413A (en) Optoelectronic means for one-dimensional integral transforms of two dimensional information
US3197735A (en) Reading machine
US3115545A (en) Grain spacing to light intensity translator for photographic enlargements
US2877457A (en) Method and apparatus for presenting three-dimensional representation of voltages
GB1381573A (en) Device for the detection of moving objects
GB982990A (en) Optical specimen identification filtering techniques
GB1393532A (en) Viewing systems
SU131106A1 (en) Multiparameter scalar field analyzer
GB1221071A (en) Pattern detection apparatus
JPS5676153A (en) Image signal processor for scanning electron microscope
GB1448596A (en) Exposure apparatus for the direct photographic production of a phosphor screen on the face-plate of a colour picture tube
US3031774A (en) Radar simulation
GB742983A (en) Apparatus for reproducing the image of an instrument dial at a remote point
GB1131539A (en) Television apparatus for synthesizing a combined display of a plurality of targets
GB679237A (en) Improvements in or relating to the examination of photographic materials
GB529985A (en) Apparatus for the production of temporary positives from photographic negatives
Kuprevich et al. Some Statistical Determinations of the Instability of Television Images of Stars