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

Clothing salient region detection method

A region detection and salient technology, applied in instruments, biological neural network models, character and pattern recognition, etc., can solve problems such as only extraction, and achieve the effect of increasing robustness and improving average accuracy.

Active Publication Date: 2018-06-15
UNIV OF SCI & TECH BEIJING
View PDF12 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The technical problem to be solved by the present invention is to provide a method for detecting significant areas of clothing to solve the problem in the prior art that only manually set image features can be extracted

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
  • Clothing salient region detection method
  • Clothing salient region detection method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0042] In order to make the technical problems, technical solutions and advantages to be solved by the present invention clearer, the following will describe in detail with reference to the drawings and specific embodiments.

[0043] Aiming at the existing problem that only manually set image features can be extracted, the present invention provides a clothing conspicuous region detection method.

[0044] Such as figure 1 As shown, the clothing conspicuous region detection method provided by the embodiment of the present invention includes:

[0045] S101, acquiring a training set and a cross-validation set, both of which include: an image containing a significant region of clothing;

[0046] S102, using the training set to train multiple regional convolutional neural networks with different structures based on Region ProposalNetwork (RPN), to obtain weight parameters of each regional convolutional neural network;

[0047] S103, using the cross-validation set as an input of e...

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 provides a clothing salient region detection method. Through the method, the success rate of clothing salient region detection can be increased. The method comprises the steps that a training set and a cross-validation set are acquired, wherein each of the training set and the cross-validation set contains an image of a clothing salient region; the training set is utilized to train multiple region convolutional neural networks with different structures based on a region proposal network, and weight parameters of each region convolutional neural network are obtained; and the cross-validation set is used as input of each region convolutional neural network for detection, and the region convolutional neural network with the highest average accuracy of salient region detection isacquired to serve as an optimal model of clothing salient region detection. The method is suitable for clothing salient region detection in electronic commerce.

Description

technical field [0001] The invention belongs to the field of e-commerce, specifically relates to the fields of big data, artificial intelligence and deep learning, and in particular refers to a method for detecting prominent areas of clothing. Background technique [0002] China is the world's largest clothing producer. Therefore, among various e-commerce platforms, clothing e-commerce has an absolute advantage. [0003] Researchers in the field of visual system have found that when the human visual system (HVS) faces complex scenes, its attention will quickly focus on several high-contrast, high-unique, and high-rare visual objects or regions. , and prioritize these objects or regions, this process is called visual salience. [0004] In the field of clothing, users pay more attention to the content of the clothing itself in the picture. Even if they care about the effect of the upper body, they will focus on the part of the clothing, while the background and so on are oft...

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
IPC IPC(8): G06K9/46G06N3/04
CPCG06V10/462G06N3/045
Inventor 肖若秀陈诚王志良桑天雨
Owner UNIV OF SCI & TECH BEIJING