Saliency perception image cutting method and device, computing equipment and storage medium

An image cropping and saliency technology, applied in the field of computer vision, can solve problems such as model overfitting and insufficient utilization of image saliency information, and achieve the purpose and advantages of concise and easy-to-understand effect

Active Publication Date: 2021-07-23
杭州喔影网络科技有限公司
View PDF5 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In this embodiment, a saliency-aware image cropping method, device, computing device and storage medium are provided to solve the problems of insufficient utilization of image saliency information and possible overfitting of the model in related technologies

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
  • Saliency perception image cutting method and device, computing equipment and storage medium
  • Saliency perception image cutting method and device, computing equipment and storage medium
  • Saliency perception image cutting method and device, computing equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0048] In order to understand the purpose, technical solution and advantages of the present application more clearly, the present application is described and illustrated below in conjunction with the accompanying drawings and embodiments.

[0049]Unless otherwise defined, the technical terms or scientific terms involved in the application shall have the general meanings understood by those skilled in the technical field to which the application belongs. In this application, words like "a", "an", "an", "the", "these" and the like do not denote quantitative limitations, and they may be singular or plural. The terms "comprising", "comprising", "having" and any variants thereof referred to in this application are intended to cover non-exclusive inclusion; for example, processes, methods and The system, product or device is not limited to the steps or modules (units) listed, but may include steps or modules (units) not listed, or may include other steps or modules inherent to the ...

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 saliency perception image cutting method and device, computing equipment and a storage medium, the saliency perception image cutting method comprises cutting model training and image cutting, and the cutting model training comprises the steps of creating an initial cutting image based on a saliency region of an original image, and performing image cutting based on the initial cutting image, generating a plurality of candidate cutting pictures in a grid anchor mode, then extracting features of an original image, and cutting the extracted image features by using a saliency-oriented region-of-interest pooling operator and a saliency-oriented discarded region pooling operator to obtain an alignment feature graph of the region-of-interest and the discarded region; and finally, feeding the alignment feature map into an aesthetic evaluation network capable of predicting the aesthetic score of the cut image for training, and obtaining a completely trained cut model. According to the method and the device, the problems of insufficient utilization of image saliency information and possible over-fitting of the model in the prior art are solved.

Description

technical field [0001] The present application relates to the field of computer vision, in particular to a saliency-aware image cropping method, device, computing device and storage medium. Background technique [0002] Image cropping aims to find image crops with the best aesthetic quality, and is widely used in image post-processing, visual recommendation, and image selection. Image cropping becomes a laborious job when a large number of images need to be cropped. Therefore, automatic image cropping has attracted increasing attention in the research community and industry in recent years. [0003] Early cropping methods explicitly designed various hand-operated features based on photographic knowledge (e.g., rule of thirds and center, etc.). With the development of deep learning, a large number of researchers are committed to developing cropping methods in a data-driven manner, and the release of some benchmark datasets for comparison has greatly promoted the progress of...

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): G06K9/32G06K9/34G06N3/04
CPCG06V10/25G06V10/267G06N3/045
Inventor 袁峰徐武将王冕徐亦飞李浬桑葛楠
Owner 杭州喔影网络科技有限公司
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