Connected domain extraction method and device

An extraction method and technology of connected domains, applied in the field of connected domain extraction methods and devices, can solve problems such as low efficiency and large processing resources

Inactive Publication Date: 2018-07-31
ゼジャンハーレイテクノロジーカンパニーリミテッド
View PDF6 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The present invention provides a method and device for extracting connected domains, which are used to solve the pr

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
  • Connected domain extraction method and device
  • Connected domain extraction method and device
  • Connected domain extraction method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0048] figure 1 A schematic diagram of a connected domain extraction process provided by an embodiment of the present invention, the process includes:

[0049] S101: Convert the image to be extracted into a binary image.

[0050] The method for extracting connected domains provided by the embodiments of the present invention is applied to electronic devices, and the electronic devices may be image acquisition devices, such as video cameras, cameras, etc., or devices such as mobile phones, personal computers (PCs), and tablet computers.

[0051] A binary image means that each pixel in the image has only two values ​​or grayscale states, usually "0" or "1". In the dot matrix image composed of "1" (target point), the adjacent target points are extracted. Its purpose is to find all connected domains in the image, and mark all pixels belonging to the same connected domain with a unique label value. Wherein, when the electronic device marks the connected domain of the binary imag...

Embodiment 2

[0065] In order to facilitate marking the pixels in the binary image, on the basis of the above embodiments, in the embodiment of the present invention, the sequentially scanning each pixel in the binary image includes:

[0066]Scan each pixel in the binary image in order from top to bottom and left to right; or,

[0067] Scan each pixel in the binary image in order from left to right and from top to bottom; or,

[0068] Scan each pixel in the binary image in a sequence from bottom to top and from right to left; or,

[0069] Each pixel in the binary image is scanned from right to left and from bottom to top.

[0070] If each pixel in the binary image is scanned in the order from top to bottom and left to right, for the scanned pixel, according to the first gray value of the current pixel, which is the same as the current pixel The marking value of the adjacent first target pixel point and the second target pixel point, determining the marking value of the current pixel point...

Embodiment 3

[0077] In order to avoid repeatedly recording the same equivalent pair into the equivalent code table, on the basis of the above embodiments, in the embodiment of the present invention, the first tag value and the second tag value are used as Equivalent pair, before recording in the equivalent code table, the method also includes:

[0078] judging whether there is an equivalence pair including the first tag value and the second tag value in the equivalent code table;

[0079] If not, proceed to the next step.

[0080] Specifically, if the first mark value and the second mark value of the first target pixel point and the second target pixel point adjacent to the current pixel point are not equal and are not 0, it is judged whether there is a An equivalence pair of a mark value and the second mark value, if yes, then explain that the equivalence pair of the first mark value and the second mark value is included in the equivalent code table, needn't the equivalence of the second...

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 discloses a connected domain extraction method and device, and the method comprises the steps: converting a to-be-extracted image into a binary image; sequentially scanning all pixels inthe binary image, determining a mark value of the current pixel of the scanned pixels according to a first gray scale value of the current pixel, a mark value of a first target pixel adjacent to thecurrent pixel and a mark value of a second target pixel; taking the first mark value and the second mark value as an equivalent pair if the first and second mark values of the first target pixel, adjacent to the current pixel, and the second target pixel are not equal and are not equal to zero, and recording the mark values into an equivalent code table; determining an equivalent sequence according to the equivalent pairs in the equivalent table; and determining the pixels with the mark values being target mark values in the binary image as a connected domain of a to-be-extracted image according to each target mark value in the equivalent sequence. The invention provides a simple and efficient connected domain extraction scheme.

Description

technical field [0001] The invention relates to the technical field of image recognition, in particular to a method and device for extracting connected domains. Background technique [0002] Connected domain extraction is often the first step in image recognition and an important part of image recognition technology. Connected domain extraction can provide accurate positioning for feature shooting of science fiction movies, and can also be used for image recognition and target information extraction in the security industry. It is even used in radar systems to obtain parameters such as position, phase, angle and speed of moving targets. For example, connected domain extraction can be used for license plate recognition, text recognition, subtitle recognition, vehicle tracking, pedestrian intrusion detection, etc. [0003] The existing connected domain extraction methods can be mainly divided into two categories. The first category is to first scan each pixel in the binary im...

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): G06K9/34
CPCG06V10/267
Inventor 李梦妮李铭郭鹰鸿
Owner ゼジャンハーレイテクノロジーカンパニーリミテッド
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