Attention mechanism-based image aesthetics quality evaluation method

A technique for image aesthetics and quality evaluation, applied in the field of computer vision

Active Publication Date: 2019-11-19
BEIJING INSTITUTE OF TECHNOLOGYGY
View PDF7 Cites 25 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, how to preserve the global information and local information of the image at the same time, and how to effectively extract the aesthetic features of the image are still the biggest difficulties in this task.

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
  • Attention mechanism-based image aesthetics quality evaluation method
  • Attention mechanism-based image aesthetics quality evaluation method
  • Attention mechanism-based image aesthetics quality evaluation method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0055] This embodiment is a network structure in which a two-way attention mechanism is added after the sixth layer of an 8-layer depth separable convolutional layer, and the data set uses the AVA data set.

[0056] An attention-based image aesthetic quality evaluation method, such as figure 1 shown, including the following steps:

[0057] Step 1: Preprocess training data:

[0058] Obtain pictures and corresponding labels on public datasets as training datasets. First, the image is scaled to a size of 256×256, and then randomly cropped into a 224×224 image, and then the image is randomly flipped, including horizontal flip and vertical flip. This random cropping and flipping operation can effectively avoid the problem of overfitting, which is equivalent to increasing the number of training samples, especially for small data sets. And the picture label is normalized according to formula 1 to obtain the real score probability distribution of the picture. The picture score rang...

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 an attention mechanism-based image aesthetics quality evaluation method, and belongs to the technical field of computer vision. The method comprises the steps of firstly processing training data, then designing a network structure model, adopting a lightweight deep network as a backbone network, and integrating the backbone network into an attention mechanism module; designing a loss function for training the network based on a data equalization thought; finally, training a network structure model by using the processed training data to obtain a network model capable of automatically evaluating the aesthetic quality of an image; and performing aesthetic scoring on the input picture based on the model, and applying the model to shooting to assist a user to shoot a more beautiful picture in real time. Compared with the prior art, the network structure model adopted by the invention can more effectively extract the characteristics of images, the adopted loss function greatly enhances the data learning ability of the model. Compared with other methods, the accuracy is improved, and the parameter quantity of the model is reduced.

Description

technical field [0001] The present invention relates to an image aesthetic quality evaluation method based on an attention mechanism, in particular to a light-weight convolutional neural network, integrated into an attention mechanism module, using a loss function based on data balance for training, and automatically obtaining image aesthetics The method for quality scoring belongs to the technical field of computer vision. Background technique [0002] Image Aesthetic Quality Assessment (Image Aesthetic Quality Assessment) is to use computer to simulate human vision for understanding and feeling of beauty, according to the aesthetic quality of the image, it is divided into high-quality / low-quality pictures, or an objective evaluation score is made. Due to the abstraction, subjectivity, and differences of audiences in image aesthetics, it is a very challenging task for computers to objectively evaluate images in terms of aesthetics. [0003] Image aesthetic quality evaluati...

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): G06T7/00
CPCG06T7/0002G06T2207/20081G06T2207/20084G06T2207/30168
Inventor 宋丹丹杨知水
Owner BEIJING INSTITUTE OF TECHNOLOGYGY
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