Multidimensional characteristic extraction method and device based on connected domain analysis

A connected domain analysis and multi-dimensional feature technology, which is applied in the direction of instruments, character and pattern recognition, computer components, etc., can solve the problems of slow blob analysis operation speed, limited feature extraction, and inaccurate analysis, so as to improve the operation speed, Satisfy the processing requirements, the effect of accurate feature quantity
CN106529550AActive Publication Date: 2017-03-22合肥九川智能装备有限公司
6 Cites 11 Cited by

Patent Information

Authority / Receiving Office
CN · China
Current Assignee / Owner
合肥九川智能装备有限公司
Publication Date
2017-03-22

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention discloses a multidimensional characteristic extraction method and device based on connected domain analysis. An obtained gray scale image is preprocessed to obtain a region of interest, the region of interest is subjected to first noise reduction to remove noise points, then the region of interest after the first noise reduction is subjected to boundary tracking and marking to obtain a target region, the target region is subjected to second noise reduction to remove noise blocks in the target region, and finally characteristic extraction is carried out. The accuracy of the image is improved by two times of noise reduction processing before extracting the characteristics, and the extracted characteristics are enabled to be more accurate; the gray scale image is compressed by run-length coding, and the run-length coding of the gray scale image conversion is operated in the preprocessing, two times of noise reduction and boundary tracking and connected characteristic marking of the gray scale image, so that the operation speed is improved, and processing demands of real-time images are met; and 20 characteristics can be extracted, and industrial field detection demands can be basically met.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention relates to the technical field of image processing, in particular to a method and device for extracting multi-dimensional feature quantities based on connected domain analysis. Background technique

[0002] A blob refers to a connected region composed of similar image features (such as color or texture, etc.). Blob analysis is an important part of computer vision and image understanding. It can easily locate the object and calculate the geometric feature quantity of the object without any prior knowledge of the position, shape and size of the object in the image, so that it can Objects are selected and classified based on these feature quantities.

[0003] The existing blob analysis process is to binarize the image first, and each pixel in the image must be designated as a target pixel or a background pixel, and then the binarized image is segmented to obtain the target and background; and then the target is connected domain mark, and f...

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