A method for image impression prediction based on multi-view and multi-feature

A prediction method and impression technology, applied in the field of image processing, can solve the problem of not being able to fit well, and achieve the effect of promoting processing and improving advertising effect.

Active Publication Date: 2021-12-21
NANKAI UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Considering that a single manual feature often cannot fit the high-level image perception information well

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
  • A method for image impression prediction based on multi-view and multi-feature
  • A method for image impression prediction based on multi-view and multi-feature

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0014] The specific implementation manners of the present invention will be further described in detail below in conjunction with the accompanying drawings. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0015] The present invention is a method for predicting image impressionability based on multi-view and multi-features. figure 1 It shows the presentation form of image impression under multiple angles. figure 2 The relationship between different attribute features and impressionability under multiple angles is shown, and the purpose of predicting image impressionability based on the integration of features that capture different information is proposed. The process is described in detail below:

[0016] a. The present invention proposes a special image attribute - impressionability, and gives the definition of impressionability: image impressionability, that is, the impact of a picture...

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 image impression prediction method based on multi-view and multi-features, which belongs to the technical field of image processing. Image impressionability is a special image attribute. The prediction of impressionability is to be able to judge and recommend pictures that are more in line with human expectations in a short time, reducing the time consumption of the screening process. The design of this method refers to the classic image attribute analysis structure, based on the theoretical basis of psychology and visual image analysis, summarizes six main clues, combines multi-level visual features to model each main clue, and finally achieves the prediction of impression. Purpose. Using this method to detect image impressions can better simulate human perception and be used for more advanced visual tasks.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a method for predicting image impressionability based on multi-view and multi-features. Background technique [0002] Image attribute is a semantically related problem in the field of computer vision, which is a challenging task. High-level image attributes, such as memory, popularity, interest, etc., can better help human image understanding. Many applications that need to judge or screen creative works benefit from it. Therefore, the understanding and judgment of image attributes has also received more and more researchers' attention. [0003] Traditional image attributes are generally based on repeated manual interactions to obtain correct annotation information. For example, the paper "What makes an image memorable?" published in CVPR (8) in 2011 proposed memory. This paper designed a memory labeling system, which divided the labeled image into two par...

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): G06K9/46G06K9/62
CPCG06V10/462G06F18/24
Inventor 杨巨峰程明明孙延梁杰王恺
Owner NANKAI 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