Complex structure file image inclination quick detection method

A document image and detection method technology, applied in the field of document image processing and rapid detection of complex structure document image tilt, can solve the problems of scarcity, complex document layout structure, scattered distribution of text parts, etc.

Inactive Publication Date: 2008-03-26
PEKING UNIV
View PDF0 Cites 29 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] (2) The layout structure of the document is complex, including horizontal version (the main direction of the text is horizontal) / vertical version (the main direction of the text is vertical); single-column / multi-column, etc.
[0012] (5) The text part in the document may be scattered or sparse

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Complex structure file image inclination quick detection method
  • Complex structure file image inclination quick detection method
  • Complex structure file image inclination quick detection method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0083] 1. Pretreatment

[0084] The purpose of the preprocessing part is to do some necessary processing on the input binary image to make it suitable for the subsequent part of the RBL algorithm. The preprocessing part mainly consists of the following steps:

[0085] Noise reduction: Document images obtained by scanning and other methods will have more or less noise. Since the noise of a binary image is generally considered to be uniformly distributed from the perspective of probability, most of the noise exists in the form of isolated points. Based on this, the RBL algorithm performs noise reduction by removing small connected regions. First, calibrate the connected regions of the image through the LC algorithm (L.Di Stefano, A.Bulgarelli, "A simple and efficient connected components labeling algorithm". International Conference on Image Analysis and Processing, 1999, Page(s): 322-327) , define sum as the number of foreground pixels contained in the region, and then remov...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

This invention relates to a tilt rapid detection method of complex structure document image, belongs to document image processing field. This invention first extracts the borders of connected region between the text and non-text region from the image, then through the filter of extracted border to obtain rubang border and corresponding tilt angle, get the tilt angle of the whole image through weighted medium value. It is showed through numerous experiments that the algorithm has the characteristics of fast, high precision, with wide range of applications.

Description

Technical field: [0001] The invention relates to a method for quickly detecting the inclination of a complex structure document image, which belongs to the category of document image processing. Background technique: [0002] Document image processing generally includes image acquisition, image enhancement, noise reduction, tilt detection and correction, page analysis, image retrieval or optical character recognition (OCR), etc. Among them, the acquisition process of the document image is to convert the paper document into a digital image through digital equipment such as a scanner or a digital camera. In this process, due to paper placement and other reasons, it is inevitable that the generated image will have a certain degree of inclination. . [0003] For document processing systems for OCR or image retrieval, tilt detection is usually a preprocessing part of the system. Since the subsequent processing of document images is usually very sensitive to the tilt of the imag...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/32
Inventor 刘宏吴奇查红彬陆叶
Owner PEKING UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap