Image processing method applied to hand jewelry augmented reality system

An augmented reality and image processing technology, applied in image data processing, graphics and image conversion, data processing applications, etc., can solve problems such as complex backgrounds and failures, and achieve the effects of reducing return rates, improving real experience, and reducing capital backlogs

Active Publication Date: 2017-11-17
CHONGQING TECH & BUSINESS UNIV
View PDF20 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The enhancement of hand accessories may face various complex environments, that is to say, the background of the hand obtained by the camera of the mobile phone may be very complicated
This method of detecting hands will fail if there is a color in the background that is the same or similar to the color of the hand

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
  • Image processing method applied to hand jewelry augmented reality system
  • Image processing method applied to hand jewelry augmented reality system
  • Image processing method applied to hand jewelry augmented reality system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0047] 1. Train the model of hand detection

[0048] Some simple methods (such as hand color) are often used to get the outline of the hand. However, if the background of the hand is more complex, if some background colors are similar to the color of the hand, the hand will not be recognized correctly. If supervised learning is used to train a reliable model for hand detection through training data, the recognition rate of hands will be greatly improved. All images in the training data set have a fixed size, here the length of the image is 224, and the width is 224, such as image 3 shown. The training data set consists of two parts: (1) Hand images based on complex backgrounds, and the i-th such image is denoted as X i ; (2) the black-and-white image corresponding to the image (that is, a binary image, the pixels of which only take two values ​​of 0 and 1), the black pixel (pixel value 0) of the black-and-white image is the background, and the white pixel (pixel value 1) ...

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 image processing method applied to a hand jewelry augmented reality system, and belongs to the technical field of computer image processing. The method includes following steps: S1, regarding a deep convolutional neural network as a hand detection model; S2, adjusting weight parameters of the deep convolutional neural network, and enabling the error between a hand image and a corresponding reference image to be minimum; S3, acquiring hand images in various complex backgrounds, and inputting the images to the deep convolutional neural network to obtain a hand contour image; S4, calculating the position of the finger according to the hand contour image, and calculating the length of the finger according to the position of the finger; S5, calculating the wearing positions of the jewelry on the finger and the wrist; and S6, superposing a jewelry image on the wearing position corresponding to the finger or the wrist. According to the method, the hand image in complex backgrounds can be detected, the positions of the finger and the wrist are rapidly calculated, and the hand jewelry image is superposed on the hand.

Description

technical field [0001] The invention belongs to the technical field of computer image processing, and relates to an image processing method applied to a hand decoration augmented reality system. Background technique [0002] Jewelry (such as rings, watches, bracelets, etc.) is an important decoration in people's daily life. With the rise of online shopping, people often buy jewelry online. However, when purchasing online, usually only the pictures of jewelry can be seen, and users cannot experience the situation when wearing them. Therefore, the return rate of jewelry is quite high, which brings unnecessary troubles to both customers and merchants. In addition, for some precious jewelry (such as famous watches, etc.), they are usually sold in physical stores. In order to meet the needs of more customers, merchants usually purchase many styles of jewelry, which will cause a large backlog of funds for the merchants. Therefore, how to increase the customer's experience in pur...

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): G06K9/00G06T3/00G06N3/04G06N3/08G06Q30/06
CPCG06N3/08G06Q30/0643G06T3/00G06V40/107G06N3/045
Inventor 刘波
Owner CHONGQING TECH & BUSINESS UNIV
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