KR930001094A - Document recognition method - Google Patents

Document recognition method Download PDF

Info

Publication number
KR930001094A
KR930001094A KR1019910010479A KR910010479A KR930001094A KR 930001094 A KR930001094 A KR 930001094A KR 1019910010479 A KR1019910010479 A KR 1019910010479A KR 910010479 A KR910010479 A KR 910010479A KR 930001094 A KR930001094 A KR 930001094A
Authority
KR
South Korea
Prior art keywords
group
input image
height
width
horizontal
Prior art date
Application number
KR1019910010479A
Other languages
Korean (ko)
Other versions
KR930008060B1 (en
Inventor
노희호
Original Assignee
이헌조
주식회사 금성사
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 이헌조, 주식회사 금성사 filed Critical 이헌조
Priority to KR1019910010479A priority Critical patent/KR930008060B1/en
Publication of KR930001094A publication Critical patent/KR930001094A/en
Application granted granted Critical
Publication of KR930008060B1 publication Critical patent/KR930008060B1/en

Links

Classifications

    • 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
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00Arrangements for image or video recognition or understanding
    • G06V10/10Image acquisition

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Character Input (AREA)
  • Character Discrimination (AREA)

Abstract

내용 없음No content

Description

문서 인식 방법Document recognition method

본 내용은 요부공개 건이므로 전문내용을 수록하지 않았음Since this is an open matter, no full text was included.

제1도는 본 발명에 따른 문서 인식 회로도,1 is a document recognition circuit diagram according to the present invention;

제2도는 본 발명에 따른 문서 인식 방법 알고리즘도,2 is a document recognition method algorithm according to the present invention;

제3도는 4 ×4메쉬(mesh)를 보인 도면.3 is a view showing a 4 × 4 mesh (mesh).

Claims (3)

문서인식에 있어, 입력영상의 특징에 따라 4개의 군으로 대별할 때 입력 영상의 높이가 그 폭의 1/2보다 작으면 제1군으로 분류하여 인식을 수행하고, 수직 클러스터의 수가 1이고 수평 클러스터의 수가 1이 아니면 제2군으로 분류하여 인식을 수행하며, 입력영상의 높이가 그 폭보다 3배 이상이거나 높이와 폭의 차의 절대값이 높이와 폭중 작은 값의 1/4보다 작으면 제3군으로 분류하여 인식을 수행하고, 그 이외의 입력영상은 제4군으로 분류하여 인식을 수행하는 것을 특징으로 하는 문서 인식 방법.In document recognition, if the height of the input image is divided into four groups according to the characteristics of the input image, the recognition is performed by classifying it into the first group if the height of the input image is smaller than 1/2 of the width, and the number of vertical clusters is 1 and horizontal. If the number of clusters is not 1, it is classified as a second group. If the height of the input image is more than three times the width or the absolute value of the difference between the height and the width is smaller than 1/4 of the smaller of the height and width, And classifying the data into a third group, and recognizing the other input images by classifying the fourth group. 제1항에 있어서, 제1군은 작은 기호군으로 (.,‘’“- ­=*)을 포함하고,제2군은 분리된 심볼로서(: ; = ?)를 포함하며, 제3군은(〔〕〈〉8)({})를 포함하고, 제4군은 (1234567890?*+&$/#%)를 포함하도록 분류하는 것을 특징으로 하는 문서 인식 방법.The method of claim 1, wherein the first group includes (., '' “-= *) As a small symbol group, the second group includes (:; =?) As a separate symbol, and the third group includes ([] <> 8) ({}), and the fourth group is classified so as to include (1234567890? * + & $ / #%). 제2항에 있어서, 제1군은 수평 수직 방향의 클러스터의 수와 입력 영상의 문자열에서의 위치, 입력영상의 하단부의 굴곡과 수평방향의 런랭스 및 입력영상의 높이와 폭의 비를 이용하여 인식하며, 제2군은 입력영상의 상하 클러스터의 최대 런랭스와 하단 클러스터의 수평 런랭스,입력영상의 수평 및 수직 길이를 이용하여 인식하며, 제3군은 영상의 좌우 투영 특성을 이용하여 인식하고, 제4군은 정규화된 8×8메쉬를 이용하여 인식하는 것을 특징으로 하는 문서 인식 방법.The method of claim 2, wherein the first group uses the number of clusters in the horizontal and vertical directions, the position in the character string of the input image, the curvature of the lower end of the input image and the run length in the horizontal direction, and the ratio of the height and width of the input image. The second group recognizes using the maximum run length of the upper and lower clusters of the input image, the horizontal run length of the lower cluster, and the horizontal and vertical lengths of the input image, and the third group uses the left and right projection characteristics of the image. And the fourth group recognizes using the normalized 8x8 mesh. ※ 참고사항 : 최초출원 내용에 의하여 공개하는 것임.※ Note: The disclosure is based on the initial application.
KR1019910010479A 1991-06-24 1991-06-24 Document recognition method KR930008060B1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
KR1019910010479A KR930008060B1 (en) 1991-06-24 1991-06-24 Document recognition method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
KR1019910010479A KR930008060B1 (en) 1991-06-24 1991-06-24 Document recognition method

Publications (2)

Publication Number Publication Date
KR930001094A true KR930001094A (en) 1993-01-16
KR930008060B1 KR930008060B1 (en) 1993-08-25

Family

ID=19316194

Family Applications (1)

Application Number Title Priority Date Filing Date
KR1019910010479A KR930008060B1 (en) 1991-06-24 1991-06-24 Document recognition method

Country Status (1)

Country Link
KR (1) KR930008060B1 (en)

Also Published As

Publication number Publication date
KR930008060B1 (en) 1993-08-25

Similar Documents

Publication Publication Date Title
Ascher et al. A means for achieving a high degree of compaction on scan-digitized printed text
US5212739A (en) Noise tolerant optical character recognition system
MX9703685A (en) Fontless structured document image representation for efficient rendering.
KR960025221A (en) Handwritten Character Recognition Device with Improved Correction Features for Stroke Segmentation and Correction Method for Stroke Segmentation for Handwritten Character Recognition
MX9703686A (en) Fontless structured document image representations for efficient rendering.
KR970017047A (en) Apparatus and method for extracting a title from a document image
EP0854433A3 (en) Caption and photo extraction from scanned document images
KR890017630A (en) Character recognition device and method
RU2596600C2 (en) Methods and systems for processing images of mathematical expressions
KR920001367A (en) Bidirectional Graphics Attribute Conversion Profile
EP0343786A3 (en) Method and apparatus for reading and recording text in digital form
KR910016186A (en) Collapse Conversion Method
CN116757165B (en) Method for projecting effect tool to OFD file based on layout data stream file base plate
RU2626656C2 (en) Method and system of determining orientation of text image
KR910015178A (en) Image data processing device
KR930002973A (en) Pattern Recognition Device
KR920019198A (en) Pattern Feature Extraction Method
KR930001094A (en) Document recognition method
JP3852218B2 (en) Image processing method and image processing apparatus
KR920008625A (en) Image color separation device
KR910012982A (en) Specific Data Selection Method for Data Processing Equipment
EP1229497B1 (en) Run length based connected components and contour following for enhancing the performance of circled region extraction algorithm
JPH03225579A (en) Device for segmenting character pattern
KR910020594A (en) Candidate Character Classification in Character Recognition
KR910020590A (en) Compression Method of Document Image by RunLance

Legal Events

Date Code Title Description
A201 Request for examination
G160 Decision to publish patent application
E701 Decision to grant or registration of patent right
GRNT Written decision to grant
FPAY Annual fee payment

Payment date: 19961230

Year of fee payment: 5

LAPS Lapse due to unpaid annual fee