Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A Content-Based Image Aesthetic Quality Improvement Method

An image aesthetics, image technology, applied in the field of artificial intelligence, to achieve the effect of simple and easy to achieve aesthetic quality

Inactive Publication Date: 2019-01-29
SOUTH CHINA UNIV OF TECH
View PDF4 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

None of these patents deal with how to improve the image quality, especially the perceived aesthetic quality of the image

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 Content-Based Image Aesthetic Quality Improvement Method
  • A Content-Based Image Aesthetic Quality Improvement Method
  • A Content-Based Image Aesthetic Quality Improvement Method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0053] The content-based image aesthetic quality improvement method of this embodiment includes the following steps:

[0054] S1 image content perception and recognition, the process is as figure 1 Shown:

[0055] S1.1 Collect four categories of image photos from the Internet, namely human faces, buildings, night scenes and other categories of images, each category has 10,000 images, and the images are formed into a training set; the other categories of images The images are images other than human faces, buildings, and night scenes;

[0056] S1.2 Extract the SIFT feature (Scale-invariant feature transform) of each image in the training set, and send it to the multi-class SVM (Support Vector Machine) support vector machine for training, and obtain the four categories of image scores Interface model

[0057] S1.3 Send the image to be adjusted into the interface model of the four major categories of images obtained in step S1.2 to obtain the corresponding category output:

[0058] S2 ad...

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 present invention discloses a content-based image aesthetic quality improvement method. According to a pre-trained category classifier, images to be adjusted are classified into four categories, namely face category images, building category images, and night scene images. category images and other category images. For the four major categories of images, the corresponding image aesthetic quality is improved. Face category images are processed by facial dermabrasion with bilateral filtering; building category images are processed by adjusting horizontal and vertical planes; night scene category images are processed by removing dynamic blur; other category images are processed by image cropping to adjust image composition. In improving the aesthetic quality of images, the present invention will perform adaptive adjustment according to the image content, and the algorithm is simple to implement and can be easily adapted to be implemented on mobile terminals with weak computing capabilities.

Description

Technical field [0001] The present invention relates to the field of artificial intelligence technology, in particular to a method for improving the quality of image aesthetics based on content. Background technique [0002] At present, in terms of image quality evaluation, there are a large number of invention patents disclosed, but in terms of image quality improvement, only individual invention patents are disclosed. Among them, the patent application CN104427347A proposes a method for improving the image quality of a network camera video surveillance system, which relates to a method for improving the image quality of a network camera video surveillance system. The cost threshold is compared to obtain the best candidate motion vector, and the quality of the lost image is improved according to the obtained best candidate motion vector. As a result, the time-domain error concealment data processing weighted by the multi-block mode is realized. At the same time, it is simple a...

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): G06T3/00G06T3/60
CPCG06T3/60G06T3/02G06T3/04
Inventor 郭礼华
Owner SOUTH CHINA UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com