Hybrid Gauss model matching method based on improved soil moving distance

A technology of mixed Gaussian model and matching method, which is applied in the field of efficient and robust measurement algorithm, can solve the problems of calculation efficiency and noise sensitivity, and achieve the effect of wide application prospect and accurate and efficient calculation

Active Publication Date: 2016-12-21
DALIAN UNIV OF TECH
View PDF4 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the traditional EMD algorithm still has the problems of computational efficiency and noise sensitivity. This method

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
  • Hybrid Gauss model matching method based on improved soil moving distance
  • Hybrid Gauss model matching method based on improved soil moving distance
  • Hybrid Gauss model matching method based on improved soil moving distance

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019] The invention proposes an improved bulldozing distance algorithm system based on a deep convolutional neural network. The core of the technology is to use a deep convolutional neural network to extract image features and model the image through GMM, and to achieve the matching between GMMs through the I-EMD algorithm, in which the Riemannian geometric structure design of Gaussian distribution is used to measure the distance between Gaussian distributions . The specific implementation of the present invention comprises the following steps (the system flowchart and the schematic diagram on image classification are respectively as attached figure 1 , with figure 2 shown):

[0020] Step 1: Extract the deep convolutional neural network features of the image. Scale-transform the image to obtain images of 3 different scales, perform convolution operation on the 3-scale images with the 19-layer VGGNet trained in advance, and take the last layer of convolutional layer (16th ...

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 provides an algorithm system applicable to image classification and image retrieval. The algorithm mainly comprises image modeling and and image matching modules. During image modeling, for improving characteristic description capability, a deep convolution neural network is utilized to extract depth characteristics of an image for the first time, and the hybrid Gauss model is utilized for modeling to represent the image on the basis; during image matching, for two problems of efficiency of a soil moving distance algorithm and noise sensitivity, the accurate, efficient and improved soil moving distance algorithm is proposed, Gauss noise and sparse constraints are additionally considered in an algorithm design process, moreover, through the improved designed soil moving distance algorithm, design defects of a geodesic distance measurement algorithm in the prior art are solved, after a Riemannian geometric structure of Gauss distribution is considered, three types of geodesic distance measurement modes are designed, Gauss distribution distances can be accurately measured.

Description

technical field [0001] The present invention relates to the technical fields of computer vision, probability statistics, and Riemannian geometry. It specifically utilizes deep convolutional neural network features to model mixed Gaussian models, and proposes an efficient and robust measure for the similarity measurement between mixed Gaussian models. algorithm. Background technique [0002] In the process of image processing, image feature representation, as the first step of image processing, plays a very important role. The feature representation of the image mainly expresses the image as one or more matrices in the mathematical sense through a series of algorithms. Image feature representation methods at this stage are mainly divided into two categories: features based on handcrafted features and features based on deep convolutional neural networks. The former is simple and efficient to calculate, including Scale-invariant feature transform (SIFT), Histogram of Oriented...

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): G06K9/62G06K9/64
CPCG06V10/75G06F18/2411
Inventor 李培华王旗龙郝华
Owner DALIAN UNIV OF TECH
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