Furniture style identification and generation method

A furniture and style technology, applied in the field of furniture style recognition and generation, can solve the problems of design result matching error, high labor cost of designers, weak innovation ability, etc., achieve low threshold, avoid solidification of design thinking, avoid legal risks or economic the effect of consequences

Pending Publication Date: 2022-07-29
ZHEJIANG SCI-TECH UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In the design method, due to the late start of modern design in my country, there is still a big gap between the creative method and the world's advanced level, mainly in the following aspects: First, designers need to spend a lot of time and energy from the original Selection of knowledge that inspires creative inspiration from case materials has resulted in weak innovation capabilities; secondly, traditional design methods often rely to a large extent on the designer’s personal experience, and design works also have a strong designer’s personal will, which is easy to create. Affected by the designer's subjective emotions and abilities, there is certain uncertainty, and the designer's labor cost is high; finally, in terms of mining user needs, insight into design problems, and program evaluation and review, it is still stuck in questionnaires, interviews, and behavioral observations. , brainstorming, subjective evaluation and other design research methods, it is difficult to touch the subconscious ideas and feedback of users, which leads to matching errors between the design results and the real demands of users; at the same time, with the advancement of technology and the design style tends to be simplified With the development, the homogenization of furniture products is becoming more and more serious, which puts forward higher requirements for designers' innovation ability

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
  • Furniture style identification and generation method
  • Furniture style identification and generation method
  • Furniture style identification and generation method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0042] The present invention will be further described below in conjunction with the accompanying drawings:

[0043] A furniture style recognition and generation method, such as Figure 1-4 shown, including the following steps:

[0044] (1) Designate a piece of furniture, use appropriate label vocabulary, and mark the existing style of the furniture;

[0045] (2) Select a convolutional neural network to establish an image recognition classification model;

[0046] (3) Establish a furniture style database;

[0047] (4) Batch cut out multiple furniture pictures to obtain furniture pictures with pure white background;

[0048] (5) Input the processed furniture picture into the Style GAN2 network twice to generate the result;

[0049] (6) Generate image and video files;

[0050] (7) Observe and browse the generated images and videos for inspiration;

[0051] (8) Manually complete the product appearance design and present the final effect.

[0052] Firstly, some furniture st...

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 a furniture style identification and generation method, which comprises the following steps: (1) setting a furniture label database and a classification database, setting a plurality of label vocabularies in the label database, and setting a plurality of types of label vocabularies in the classification database; setting a classification database to classify the existing styles of the furniture, inputting a furniture picture or information, and calling the label database and the classification database to initially classify the furniture; (2) selecting a convolutional neural network to establish a plurality of image recognition and classification models; (3) establishing a furniture style database; (4) carrying out batch matting on the plurality of furniture pictures to obtain furniture pictures with pure white backgrounds; (5) inputting the processed furniture picture into a Style GAN2 network in two times to generate a result; (6) generating image and video files; (7) observing and browsing the generated image and video, and identifying a preferred scheme; (8) completing design and optimization of a product appearance design scheme, presenting a design drawing and displaying the design drawing to an interface; the method has the advantages that the creativity is inexhaustible; thinking of a designer is trained, and efficient and stable output is achieved; the designed threshold is low, and more creativity is stimulated; some legal risks or economic consequences are avoided, and design thinking solidification is avoided.

Description

technical field [0001] The invention relates to the field of furniture design, in particular to a furniture style identification and generation method. Background technique [0002] After decades of development, my country's furniture industry has formed a certain industrial scale. The production and export of furniture has occupied a very important position in the international furniture industry. With the trend of economic globalization and the development and wide application of the Internet, the Bringing more intense competition to enterprises, forcing enterprises to constantly seek new technologies, new methods and new means in order to improve their core competitiveness in the market, so as to obtain survival and development, in this context, design ability is particularly important , design ability has become a new driving force in some industries; now, the furniture industry is also at the key node of transformation and upgrading. How to make the ancient furniture indu...

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): G06V20/10G06V10/762G06V10/764G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06N3/045G06F18/23G06F18/241
Inventor 李雪莲朱海鹏张佳琪
Owner ZHEJIANG SCI-TECH 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