Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Object identification method and system based on shape fragments

An object recognition and fragment technology, applied in the field of computer vision, can solve the problems of flexible objects with unstable appearance and difficult to recognize objects, and achieve a good recognition effect.

Inactive Publication Date: 2014-02-26
ZHANGJIAGANG INST OF IND TECH SOOCHOW UNIV
View PDF0 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In view of this, the present application provides an object recognition method and system based on shape fragments, which are used to solve the problem that traditional methods are difficult to recognize flexible objects and objects with unstable appearance characteristics

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
  • Object identification method and system based on shape fragments
  • Object identification method and system based on shape fragments
  • Object identification method and system based on shape fragments

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0046] see figure 1 , figure 1 It is a flow chart of an object recognition method based on shape fragments disclosed in the embodiment of this application.

[0047] Such as figure 1 As shown, the method includes:

[0048] Step 101: Using the same extraction method, respectively extract the edge shape fragments of the training image and the edge shape fragments of the test image;

[0049] Specifically, we adopt the same extraction method to extract edge shape segments for training images and test images respectively.

[0050] Step 102: using the edge shape fragments of the training image to construct an object edge shape fragment model;

[0051] Step 103: Select a specific edge shape segment from the edge shape segments of the test image as a candidate edge shape segment, the similarity between the specific edge shape segment and the edge shape segment in the object edge shape segment model must be greater than the first threshold;

[0052] Specifically, according to the ...

Embodiment 2

[0058] We use the same method to extract the edge shape fragments of the training image and the test image, but the objects are different. The following takes the extraction of edge shape fragments of training images as an example. The specific extraction method is as follows:

[0059] see figure 2 , figure 2 It is a flowchart of a method for extracting edge shape segments disclosed in the embodiment of this application.

[0060] Such as figure 2 As shown, the method includes:

[0061] Step 201: Perform edge processing on the training image to obtain an edge image;

[0062] Specifically, we can use the Canny operator to perform edge processing on the training image.

[0063] Step 202: Using the chain code method, connect all the edge points whose distance between the edge points is smaller than the second threshold, and divide the connected edge points into an edge group;

[0064] Specifically, the size of the second threshold is set manually, and an adaptive value ca...

Embodiment 3

[0073] In this embodiment, we introduce the process of constructing the edge shape segment model of the object: specifically, we can use the object modeling method represented by the code table, and use the multi-scale processing method when constructing the model, so when the training set and the test set When the scale factor between is within a certain range, it has scale invariance. In addition, this embodiment can adopt supervised training to obtain the object edge shape segment model, that is, the area where the object is located needs to be marked in the training set, and most databases provide the object area in the training set, such as the ETHZ shape library.

[0074] It should be noted that when using the object modeling method represented by the code table, in addition to describing the edge shape segment of the training image as the attribute of the edge shape segment of the training image in the code table, we can also add the edge shape segment of the training im...

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 an object identification method based on shape fragments. The method comprises the steps of extracting edge shape fragments of a training image and edge shape fragments of a test image; constructing an edge shape fragment model of an object according to the edge shape fragments of the training image; selecting specific edge shape fragments from the edge shape fragments of the test image as candidate edge shape fragments, wherein the similarity between the specific edge shape fragments and an edge shape fragment in the edge shape fragment model of the object must be larger than a first threshold; calculating the maximum probability value of Hough space by means of Hough transformation to determine the reference point position of an object to be detected; screening the candidate edge shape fragments according to the reference point position of the object to be detected to obtain an actual object profile fragment. The object identification method based on the shape fragments effectively solves the problem that a traditional method can not be used for identifying flexible objects or objects with unstable appearance features.

Description

technical field [0001] The present application relates to the technical field of computer vision, and more specifically, to an object recognition method and system based on shape fragments. Background technique [0002] Object detection and pose estimation are active research topics in the field of computer vision. Existing object detection methods generally identify objects based on local or global features of the object, but this method is generally applied in the absence of background noise, and is rarely used in the recognition process of objects in natural environments. For flexible objects and objects with unstable appearance characteristics (such as the appearance of objects that are sensitive to light, and the appearance of objects is disturbed, such as people often change clothes, etc.), the existing detection methods based on local or global features of objects are difficult to accurately identify. Therefore, a new object recognition method is needed to effectivel...

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): G06K9/46
Inventor 陈国栋王振华孙立宁孙荣川任子武林睿
Owner ZHANGJIAGANG INST OF IND TECH SOOCHOW UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com