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

Image type labeling method based on phrase bag model

A technology that includes models and phrases, applied in character and pattern recognition, instruments, computer components, etc., to achieve the effects of eliminating sensitivity, improving discrimination, and high performance

Inactive Publication Date: 2012-11-14
INST OF AUTOMATION CHINESE ACAD OF SCI
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0010] In order to solve the problems existing in the existing word bag model, the purpose of the present invention is to introduce the structural position information between local feature points without affecting the robustness of the existing word bag model, improve the quality of image representation, and then improve the automatic labeling The performance of the system, for this the present invention provides a kind of image classification labeling method based on phrase bag model

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
  • Image type labeling method based on phrase bag model

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach

[0036] The specific embodiment of the present invention is described as follows:

[0037] Step S1: For any image I i , using wavelet-based local feature point detectors to obtain all local feature points P in the image i ={p ij}, j=1, 2, ..., N i , where N i for image I i The number of all local feature points in , in the experiments of the present invention N i It is set to 1000, that is, 1000 local feature points are detected in each image;

[0038] Step S2: For the local feature point p obtained in step S1 ij ,Using local features to describe the sub-scale invariant feature transform (SIFT), describe the texture features of the local area around it, and form a local feature point p ij The vector description f ij , we call f ij is the feature point p ij Corresponding visual words, in the experiment of the present invention, the vector f obtained by SIFT descriptor ij is a 128-dimensional vector;

[0039] Step S3: For the local feature point p obtained in step S1 ...

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 image type labeling method based on a phrase bag model, which introduces position information among vision words based on the existing bag-of-words model representation and provides the phrase bag model representation strategy. The method effectively solves the contradiction between insufficient discrimination because the traditional bag-of-words models lack position information and sensitivity to target displacement after adding the blocked position information, eliminates the sensitivity to target displacement in the image while introducing the position informationamong the vision words and increasing discrimination, effectively improves the performance of the image type labeling system and has important application value.

Description

technical field [0001] The invention belongs to the technical field of pattern recognition and information processing, and relates to an image category labeling method based on a phrase bag model, in particular to an image classification method. Background technique [0002] Due to the low price of digital products such as digital cameras, pictures and video data can be easily taken and stored in an electronic form that is convenient for computer processing. At the same time, the rapid development of Internet resources makes the majority of users begin to face a huge data resource. It has become unrealistic to simply use manpower to maintain and organize these data. Therefore, developing a technology to complete the automatic labeling of image and video data has become a hot issue. [0003] In general, how to properly represent images is more important than the classification techniques that are later used to classify these representations. The reason can be explained thr...

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 Patents(China)
IPC IPC(8): G06K9/62
Inventor 肖柏华张琳波王春恒惠康华邵允学蔡新元
Owner INST OF AUTOMATION CHINESE ACAD OF SCI