Image classification method based on supplemented text characteristic

A classification method and image technology, applied in the fields of instruments, character and pattern recognition, computer parts, etc., can solve problems such as the decline of image feature discrimination, affecting the classification results, etc., to improve the expressiveness, increase the amount of calculation, and improve the accuracy. Effect

Inactive Publication Date: 2017-03-22
TIANJIN UNIV
View PDF5 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to overcome the deficiencies in the prior art, the present invention aims to: solve the problem that the image feature discrimination caused by the lack of text fea

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 classification method based on supplemented text characteristic
  • Image classification method based on supplemented text characteristic
  • Image classification method based on supplemented text characteristic

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0056] An image classification method based on supplementary text features is proposed, which fuses the shape, boundary and color information in the image as supplementary information into the initial SIFT text features, and then constructs a dictionary and encodes features to obtain an effective image representation. Improved image classification accuracy.

[0057] The basic idea of ​​this method is: use the shape, boundary and color information in the image to supplement the basic text features, and solve the problem of missing text feature information by fusing these information into the text features, so that in the subsequent feature learning process Improve the expressiveness of features and improve the accuracy of final image classification. The specific method steps are as follows:

[0058] (6) Extract the SIFT feature, color feature, shape and boundary feature of the image in the data set respectively, and integrate the color, shape and boundary feature into the SIFT...

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 the field of digital image processing technology, and provides a method for image classification through supplementing a text characteristic for settling a problem of classification result deterioration caused by image characteristic discriminating property reduction because of text characteristic information loss in a bag of visual words. The image classification method based on the supplemented text characteristic comprises the following steps of (1), respectively extracting an SIFT characteristic, a color characteristic, and a shape-and-boundary characteristic of an image in a data set; (2), randomly selecting 200000 characteristics from the supplemented text characteristics and obtaining a dictionary B through a K-singular value decomposition method (K-SVD); (3), obtaining a sparse characteristic vector C through the studied dictionary B; (4), performing spatial maximal value gathering on the sparse characteristic; and (5), transmitting an image characteristic vector F into a linear SVM classifier, thereby performing training and testing respectively for obtaining an image classification result. The image classification method is mainly applied for digital image processing.

Description

technical field [0001] The invention relates to the technical field of digital image processing, in particular to a scene image classification method based on supplementary text features. Background technique [0002] Image classification, as the basis of image understanding, plays an important role in the field of computer vision. Although people have made a lot of efforts and made great progress in feature extraction and training, there is still no unified best classification method suitable for all images. [0003] In image classification, one of the most popular is the visual bag-of-word model (Bag-of-Word), which is an image classification model based on a statistical model, and its purpose is to obtain a more expressive representation of image features. The most widely used image features in this model are features based on image text information, such as SIFT, HOG, etc. After extracting the features of the image, it is necessary to use the obtained local features to...

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): G06K9/62G06K9/46
CPCG06V10/467G06V10/464G06V10/44G06V10/56G06F18/28G06F18/2135G06F18/214G06F18/2451G06F18/2411G06F18/253
Inventor 郭继昌王楠张帆
Owner TIANJIN 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

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