Feature extraction method for image scene recognition

A feature extraction and scene recognition technology, applied in the field of image scene recognition, can solve the problems of difficult subject features, combination, and high dimensions, and achieve the effect of improving the recognition accuracy.

Inactive Publication Date: 2015-02-25
JILIN UNIV
View PDF2 Cites 30 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005]By disclosing a dimensionality reduction method for Object Bank features, it solves the technical problem that its dimensions are too high and difficult to combine with theme features

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
  • Feature extraction method for image scene recognition
  • Feature extraction method for image scene recognition
  • Feature extraction method for image scene recognition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0119] The present invention relates to a picture Like the feature extraction method of scene recognition, the following is combined with the attached picture Each detail involved in the technical solution of the present invention is further described in detail with two examples. This embodiment uses a personal computer (PC) for simulation, and its software is based on a 64-bit Windows 7 operating system and a Matlab 2013a simulation environment. The two embodiments are respectively: outdoor scene recognition and sports scene recognition.

[0120] a. Outdoor scene recognition: using the published LabelMe eight-category outdoor scene dataset, the dataset has all picture The images are labeled as eight categories, the eight categories and the picture The number of pixels is: 360 for the beach, 328 for the forest, 260 for the highway, 308 for the city, 374 for the mountain, 410 for the field, 292 for the street, and 356 for the high-rise. The LabelMe eight-type outdoor scene ...

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 relates to a feature extraction method for image scene recognition. The feature extraction method comprises the first step of mining information in a group of training images of which the classes are known and the second step of recognizing test images to be recognized. The first step comprises the sub-steps of preprocessing the images, extracting target features of the images, decreasing the dimensions of the target features, executing the LDA model training algorithm, generating scene environment features of the training images, carrying out feature combination and executing the SVM training algorithm. The second step comprises the sub-steps of preprocessing the testing images, generating code words of the testing images, generating scene environment features of the testing images, extracting target features of the testing images, decreasing the dimensions of the target features of the testing images, carrying out feature combination on the testing images and generating image classes through a trained SVM classifier. By means of the feature extraction method, the calculation amount of an existing method is deceased, the application range is expanded, and the recognition accuracy is improved.

Description

technical field [0001] The invention belongs to image scene recognition technology, in particular to a feature extraction method for image scene recognition. Background technique [0002] The purpose of image scene recognition is to obtain the semantic information of the image and give its category label. It is an important research content in the fields of computer vision, pattern recognition and machine learning, and it is also an indispensable technology in practical fields such as image library management and image retrieval. The method based on bag of features (Bag of Features) and topic model is a research boom in recent years, and many new achievements and progress have been made. This type of method draws on the natural language processing process, treats the image as a collection of local observations and builds a feature bag, uses the feature bag to build a topic model, and generates features or directly generates categories. In addition, the object recognition t...

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): G06K9/62
CPCG06N3/02G06F18/21G06F18/23213G06F18/2411
Inventor 臧睦君刘通宋伟伟李阳王珂
Owner JILIN UNIV
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