Unlock instant, AI-driven research and patent intelligence for your innovation.

Run-length-based binary image connected region labeling method

A binary image, connected area technology, applied in image analysis, image data processing, instruments, etc., can solve problems affecting computing efficiency and time-consuming, and achieve the effect of improving computing efficiency

Inactive Publication Date: 2017-08-18
NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
View PDF4 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] As the size of the image increases, the number of comparison operations increases exponentially, seriously affecting the computational efficiency, and this link is one of the most time-consuming links in the entire CCL algorithm

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
  • Run-length-based binary image connected region labeling method
  • Run-length-based binary image connected region labeling method
  • Run-length-based binary image connected region labeling method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] The present invention will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0031] The invention proposes an FRL (Fast RunLabeling) algorithm for the first link of the run-based secondary scan CCL algorithm.

[0032] The binary image involved in the algorithm of the present invention has several rows of pixels, and the row labels are respectively i and i+ 1's top and bottom adjacent lines X i line and X i+1i rows, each with m trips R i and n trips R i+1 ,and R i Runs have markers Label . The graphics expressed by the binary image are ever-changing, and their run length distributions are different. The judgment of the connectivity relationship between the upper and lower adjacent row runs is carried out by means of comparison. In the present invention, the connectivity comparison is carried out according to the 8 connectivity judgment rules. in X i itinerary R i in left-to-right or right-to-left orde...

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

The invention relates to a run-length-based binary image connected region labeling method. According to the method, run lengths Ri+1 and Ri corresponding to adjacent rows Xi+1 and Xi of a binary image respectively are subjected to internal and external bi-circulating connectivity comparison; whether Ri is labeled or not is judged before each internal circulation is accessed; the unlabeled Ri is labeled; in an inter-row run length comparison process, a connection relationship of the run lengths is judged by comparing the sizes of initial column labels and stop column labels of the run lengths of the adjacent rows according to a position relationship among the run lengths; and after the comparison of every two run lengths between the rows is finished, one run length must exit from the comparison because the run length is impossibly connected with the subsequent run lengths of the compared rows, so that unnecessary subsequent comparison can be removed, the inter-row run length comparison time complexity is reduced to a linear order from a conventional exponential order, and the computing efficiency is effectively improved.

Description

technical field [0001] The invention relates to a run-length-based method for marking connected regions of a binary image, and belongs to the technical field of image analysis and recognition. Background technique [0002] A binary image refers to an image with only two grayscale values ​​for the image pixels, generally 0 and 255, which are convenient for intermediate calculations, and can also be set to 0 and 1. Binary images play an important role in machine vision, pattern recognition and other fields. In practical applications such as medical image analysis, motion detection, character recognition, and shape recognition, images are generally converted into binary images for analysis. Binary image connected region labeling is an important preprocessing algorithm in binary image analysis, referred to as CCL algorithm, and is one of the important underlying basic algorithms in machine vision, pattern recognition and other fields. The connected area generally refers to the...

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
IPC IPC(8): G06T7/11G06T7/187
Inventor 吕常魁陆江刘源罗冰心
Owner NANJING UNIV OF AERONAUTICS & ASTRONAUTICS