Unlock instant, AI-driven research and patent intelligence for your innovation.

End-to-end multi-task feature fusion method for Chinese painting classification

A feature fusion and multi-task technology, applied in the direction of instruments, character and pattern recognition, computer components, etc., can solve the problems of information loss and generalization ability, and achieve the effect of improving overfitting and classification accuracy

Active Publication Date: 2020-08-04
TIANJIN UNIV
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] The present invention provides an end-to-end multi-task feature fusion method for Chinese painting classification. The present invention solves the problems that Chinese painting classification lacks a large number of diverse training data, and is prone to information loss and poor generalization ability. Features require more expertise, mainly including the following three points:

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
  • End-to-end multi-task feature fusion method for Chinese painting classification
  • End-to-end multi-task feature fusion method for Chinese painting classification
  • End-to-end multi-task feature fusion method for Chinese painting classification

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0034] The embodiment of the present invention provides an end-to-end multi-task feature fusion method for Chinese painting classification, see figure 1 , the method includes the following steps:

[0035] 1. Multi-task feature fusion (MTFFNet) architecture

[0036] A multi-task feature fusion (MTFFNet) architecture for traditional Chinese painting classification, the proposed model MTFFNet is as follows figure 1 shown.

[0037] It can be seen that the whole network is mainly composed of two task branches, namely RGB image feature learning and stroke feature learning, both of which integrate DenseNet as a backbone network component. The top layer is the RGB image feature learning branch. This task takes the original image of Chinese painting as input and learns high-level semantic information describing painting features from an RGB perspective. The bottom layer is the stroke information learning branch. This task takes the gray level co-occurrence matrix (GLCM) image as inp...

Embodiment 2

[0061] Below in conjunction with concrete experiment, carry out feasibility verification to the scheme in embodiment 1, see the following description for details:

[0062] 1. Experimental settings

[0063] Use deep learning framework tensorflow and keras to realize the model of the present invention. MTFFNet is trained using stochastic gradient descent (SGD) with a batch size of 64 images. According to the settings of AlexNet (ImageNet Classification with Deep Convolutional Neural Networks), the learning rate of the current training iteration number i is set to:

[0064]

[0065] Among them, p is the total number of iterations to ensure the convergence of the model, and p is set to 100, so that when the learning rate has been set and the model is trained, the model can finally converge only when the learning rate decreases over time. Use LIBSVM (ALibrary for Support Vector Machines) toolbox to implement SVM classifier, use Gaussian kernel function and gradient optimizatio...

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 end-to-end multi-task feature fusion method for Chinese painting classification, and the method comprises the steps: building a multi-task feature fusion network model whichconsists of a top RGB image feature learning branch and a bottom stroke feature learning branch, wherein a dense connection network serves as a backbone network for the two branches; wherein the top-layer RGB image feature learning branch takes an original image of a traditional Chinese painting as input, the bottom-layer stroke feature learning branch takes a feature map of a gray-level co-occurrence matrix as input, and different modal features are learned in an end-to-end mode; and selecting a multi-kernel learning SVM as a final classifier. The problems that Chinese painting classification lacks a large amount of diversified training data, information loss is likely to occur and the generalization ability is poor are solved, and more professional knowledge is needed for extracting features from the images.

Description

technical field [0001] The present invention relates to the computer field of machine learning, and in particular to an end-to-end multi-task feature fusion method for classification of Chinese paintings, through image low-level (such as edge, texture, etc.) Learn to classify Chinese paintings. Background technique [0002] Chinese art, especially Chinese painting, as the representative of the oldest art form, has made great contributions to the world cultural heritage. However, how to effectively protect these paintings is an urgent problem to be solved. Fortunately, the development of digital media and intelligent information processing technology in recent years has provided us with another way to digitize these precious ancient paintings and display them on the Internet. However, how to effectively manage and classify Chinese paintings has always been a challenging problem. [0003] The classification of Chinese paintings has been studied for decades, and some studies...

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): G06K9/62
CPCG06F18/2411G06F18/253
Inventor 孙美君王晓玉
Owner TIANJIN UNIV